Amazon is famous for being customer-focused. Jeff Bezos’ shareholder letters over the years emphasise this focus. Here’s one excerpt:
Senior leaders that are new to Amazon are often surprised by how little time we spend discussing actual financial results or debating projected financial outputs. To be clear, we take these financial outputs seriously, but we believe that focusing our energy on the controllable inputs to our business is the most effective way to maximize financial outputs over time. Our annual goal setting process begins in the fall and concludes early in the new year after we’ve completed our peak holiday quarter. Our goal setting sessions are lengthy, spirited, and detail oriented. We have a high bar for the experience our customers deserve and a sense of urgency to improve that experience.
The pioneers of ‘one-click’ buying and free one-day delivery set the bar high for transacting online. But you don’t need to be a web design expert to notice all the nudges pushing you to buy.
On this randomly picked Amazon product page below, I count at least eight elements to make you buy the product now.
Amazon India site. click to enlarge.
The lock icon signals a “secure transaction”, so we trust the site. “Offers” sweeten the deal and “Amazon’s Choice” build confidence.
The other nudges create FOMO (fear of missing out): “Deal of the day! 69% off”, “Order within[countdown timer]”, “In stock” convey scarcity, urging us to act fast.
Everything on the page says, “This is a great product at a steal of a price, but only for now. Supplies might not even last the day. Buy!”
If you needed a backpack and saw this, you’d feel lucky to save big. You’d click “Buy Now” and feel good.
But the three-month price history of the product might make you feel differently.
The “deal” ₹899 price is the typical price. You’d be unlucky to pay 50% more. And this “deal” is 6% higher than in May, 12% higher than March/April.
Did Amazon do anything wrong legally or in spirit? You got a decent backpack at an ok price when needed. Research even says discounts trigger happiness and trust. If true, the nudges made us better off than if the page just said, “The usual price. Plenty in stock. Buy whenever.”
FOMO nudges are everywhere.
booking.com
Hotel and travel sites like booking.com say, “Only two rooms/seats left at this price”. Food delivery apps emphasise “this weekend only” discounts. Fashion retailers like Zara are famous for “limited edition” collections. Nike also offers limited edition sneakers on their SNKRS app that sell out quickly. The list can go on.
FOMO in Finance and Investing
In Investing, FOMO gets tricky.
The only equivalent of the “26L water-resistant backpack” or “1 king bed, 330 sqft garden-facing room” is the “7.5% 366-day Fixed deposit”. You know exactly what you’re getting and when you’re getting it. Every other investment product has uncertainty baked in, no matter what the marketing deck says.
That active smallcap PMS investment strategy could be UP or DOWN 70% next year. Even the low-cost index fund with the long-term 12% return expectation will certainly return significantly higher or lower than 12% next year.
It’s like ordering a backpack but getting anything from an mountaineering-grade backpack to a jute sack! The range of probable outcomes in investing is ridiculous.
Like the examples above, Finance and Investing is a business. This means the players also adapt and nudge to “close the sale”. Every seller of anything investment-related does it—every seller. The difference is in the levers they employ and the degree to which they use them.
Four common nudges sellers of investment products use:
1. Offer many products
Also known as “Spray and Pray”.
A brilliant strategy can get hammered in any given year. A completely random strategy can have a blockbuster year. Therefore the wider the product assortment, the higher the chance that at least one looks good in the near term.
So they offer several options, variants of the same core philosophy, or completely different strategies named after buzzword-filled themes. It doesn’t matter. And deftly shift emphasis to what looks good at the time and therefore look brilliant all the time.
Intermediaries and platforms do this even better.
2. Shiny new things to match trending narratives
When the student is ready, the teacher appears. – Lao Tsu or the Buddha (depending on who you believe)
In investing: When the market is ready, the investment product appears
If you’re an email hoarder, look through your archives for NFO (New Fund Offer) emails going as far back as possible.
Two things will stand out:
NFOs cluster around market highs. The time when everyone and their cousin is getting interested in equities is the time new funds appear. Applies to IPOs too.
Thematic and Sectoral narratives coincide with respective fund launches. International (read US stocks) surging? International Fund of Funds appear. Have defence stocks been going gangbusters? Boom. Three new “India Defence Indigenization Megatrend” funds launch.
If you practice inbox zero, try plotting various sectoral NFO dates on the respective sector index chart. Most points will plot near sector index peaks.
3. Always certain
When asked, “What will X event do to sector Y” they exude certainty.
What is the impact of the Russia-Ukraine on IT services margins? De-dollarisation? Generative AI? The next NVIDIA? The subject doesn’t matter. Confidence does.
Financial media demands quick and easy answers. Correctness is optional, and nuance is an inconvenience.
If they don’t offer answers, someone else will. So sound bites/articles/tweet threads explaining it all simplistically, its impact and what investors should expect. Since no one’s keeping a scorecard, so there is no downside.
Oh, and the most common conclusion: “Bullish on Indian equities. The next decade will be awesome.”
4. Say you’re missing out!
“This strategy just did a gazillion% last month. Get on board now so you don’t get left behind.”
Subtle as a sledgehammer, but it must work, given how often we see it.
Combined with the first lever of many products, highlighting recent performance of the month’s flavour is a cannot miss sales nudge.
And so, Caveat Emptor
means Buyer beware in Latin.
Businesses exist to generate returns for their shareholders. They must stand out in crowded marketplaces against similar and usually intense competition and make the sale. The business of investing is no different.
In a way, it doesn’t matter that an Amazon “Deal of the Day” is just the usual price. As long as the product it delivers is the one it shows and is of decent quality.
Whether the hotel really only has two rooms left when you booked doesn’t matter as long as the room you check into matches the pictures and has the amenities listed on the booking page.
But investing is different because the same input leads to a range of outcomes, especially short-term, but even in the long term. Investing businesses employ nudges to make the sale: Many different products, participating in trendy narratives, sounding more confident than they feel, and inducing FOMO based on recent winners are just some of them.
Where does that leave the regular investor looking for the right way to invest?
Even on longer time horizons, you are guessing between the good, the so-so and the bad. A below-par investment manager will almost certainly erode wealth over longer time horizons. But even Buffett has underperformed the S&P500 for significant periods; there was also that time he incurred an opportunity cost of $12B from buying Dexter Shoes with BRK stock.
The good and bad investment managers are hard to tell apart. Hard but not impossible if you’ve been paying attention to what they say and do. They’ll all nudge; you just need to be aware of them. So, you can adjust your behaviour for your benefit, just like it’s helpful to be aware that 24 people are not actually currently on the hotel booking site about to book the very same room you’re considering.
Finally:
Focus on costs and taxes
See through confident certainty. Anyone who seems sure of market moves or investment outcomes is overconfident at best, deceptive at worst.
Markets are unpredictable, even for experts. Beware managers implying special foresight.
Consider range of outcomes, not averages, and certainly not the “last 90 days”
Question trendy narratives. Be especially wary of related investment pushes
Balance is key. Diversify. Don’t rely entirely solely on any strategy, fund or narrative
Stay flexible and open-minded. The future is unpredictable, and cycles are everywhere
Ignore the hype – and stay focused on what really counts for your returns over time.
As of writing this, markets have been recovering and making new highs. Soon there will be no shortage of sales nudges implying innate brilliance and visions of quick returns. The more you understand them, the less effective the nudges become.
Last quarter, there were 484 mentions of ROCE in the filings of just the 50 Nifty companies.
ROCE stands for “Return on Capital Employed.”: how well a company is generating profits from its capital. It is considered a critical part of the puzzle of finding quality businesses.
ROCE typically helps differentiate between ordinary and high-quality businesses.
Imagine we’re looking at two restaurants in the same town, Restaurant A and Restaurant B. Both offer delicious food and have a steady stream of customers. How would you identify the better prospect to invest in?
Restaurant A is a swanky place that spent a lot of money on renovations, high-end kitchen equipment, and a renowned chef. Their food is excellent, and they charge high prices. However, due to the high overhead costs, their net income isn’t as high as you might expect from looking at the price of the dishes on their menu. Their ROCE, which measures how much profit they generate for each dollar of capital they’ve employed, might not be very high. Despite the high prices they charge, they’re not turning their capital into profit as efficiently as they could.
Restaurant B is a more modest establishment. They’ve kept their costs down by leasing cheaper equipment and hiring a less well-known (but still competent) chef. They charge lower prices, but they serve more customers and their net income is surprisingly high. Their ROCE might be quite good, because they’re generating a lot of profit for each dollar of capital they’ve employed. They’re using their capital more efficiently.
If both restaurants are profitable and have a loyal customer base, you might think they’re equally good businesses. But as an investor, you’d probably prefer Restaurant B. Why? Because a high ROCE indicates that the business is better at generating profit from its capital. It’s a more efficient business model, and that’s a sign of a high-quality business.
The link between ROC and Returns over the years
We did a longitudinal analysis spanning ten years centred on classifying companies on the continuum from high to low ROC and looking at their shareholder returns. The objective was to see what patterns emerge that might be considered generally acceptable to the way the stock market rewards shareholders.
We started with over 800 companies that were operational 10 years ago. We classified this cohort into 10 deciles (10 – best, 1 – worst) based on their 3-year average ROCE at that point. By taking a three-year average, we improve our chances of getting a better representation of each company’s financial reality than any one year. In addition, we also track their three-year average ROC in year T-7, T-4, and T-1, where T is current year.
Then we look at their total returns over the 10-year period to check for any obvious patterns. Whether the high ROC companies 10 years ago continue to be high ROC companies today. And to what extent did high ROC translate to shareholder return?
Here’s what we found.
Return on Capital is only mildly sticky
When the 812 companies were split into deciles from 1 (worst) to 10 (best), each decile had about 81 companies. The table shows how those companies break down as of one year ago on the same metric.
Over the last 10 years, those companies either improved their relative decile, got worse, or stayed in the same decile.
Figure 1 below shows that split. The numbers in the table indicate where the companies ended up.
The table should be read row-wise: For example, Top row: Of the 82 companies in the top (10th) decile ten years ago, 34 continue to be in the top decile as of 1 year ago, the remaining 48 slipped to lower deciles – 11 to the 9th decile, 9 to 8th decile, 6 to the 7th decile and so on.
Bottom row (above the total): Of the 80 companies in the bottom decile ten years ago, 8 are now in the top decile, 2 in the 9th decile, 4 in the 8th decile and so on.
Probably an easier way but with less information is to visualise decile movement from 10 years ago to 1 year ago by percentage of companies.
4 out of 10 companies that were top decile 10 years ago were still top decile 1 year ago. This means 6 out of 10 companies from 10 years ago are no longer top decile. Of course, decile 10 companies had nowhere to improve to.
1 in 4 top-decile ROCE companies a decade ago are now in the bottom half of their cohort of 800+ companies
The highest proportion of companies showing improvement were in deciles 1, 2 and 3. Put another way, the companies at the bottom of the pile showed the most improvement
4 in 10 companies across the whole set worsened on their ROCE decile, while the same number also improved on the same metric
Not apparent on this chart: 45% of companies are within +1 or -1 decile of their starting ROC decile a decade ago. The remaining 55% saw larger moves in their relative Return on Capital.
The 34 top-decile companies from a decade ago are still in the top ROC decile
The 34 companies that continue to be top ROC decile
Castrol India ranked #3 on ROC 10 years ago and continues to be in the 10% on the same metric. But look at its Total Return to shareholders over that period. Glaxo Smithkline improved its Return on Capital from 10 years ago and shows a cumulative 38% return. This begs the question how effective is a high relative return on capital at predicting future returns.
A glorious past doesn’t necessarily mean glorious shareholder returns
Chart shows median annualised 10-year return from the ten deciles, each with 80 to 82 companies.
Chart shows the aggregate ten-year return from the companies in the ten deciles. Remember the ROCE considered was the 3-year arithmetic mean at the time.
The right-most column shows the decile-wise 10-year return of the top-to-bottom ROC deciles as of 10 years ago. The bottom decile (decile 1) has the worst 10-year return. The median return from the 7th decile turns out to be the best followed by the 6th decile.
The top ROCE decile of stocks delivered median 431% cumulative total return over ten years. That’s just over 18% annualised
The highest returns seem to have come from the 7th ROCE decile 10 years ago that were in the top decile recently. Referring back to Fig 1 above shows that’s a set of 8 companies. The heatmap shows how the best-returning companies are the ones in the top deciles recently.
Also, the median stock went up 395%, almost 4x over ten years. That is 17.4% annualised. Keep in mind, the cohort of 800+ companies includes many small and micro caps at the time which explains the significantly higher return than the Nifty over the same period.
This makes you wonder, how much did consistency of 3yr Return on Capital affect total return?
Because Returns on Capital fluctuate absolutely, not just relatively
The first table considered how much companies shift on relative scale of comparison. This one looks at how consistent companies are on return on capital with their own past.
We measured consistency as the Standard Deviation of ROCE across 10Y, 7Y, 4Y and 1Y ago divided by the Average ROCE over that time frame. This measure is called the Coefficient of variation, which looks to only measure how much a metric changed over time. Lower the CV, the more consistent the company was on its 3-year average ROC over 10 years.
The top decile companies on consistency had the lowest CV (most consistent) while the bottom decile had the highest variation (least consistent).
The bottom ROC-decile companies 10-years ago were the least consistent since then, which is a probably a good thing for them
The more consistent companies are in the top few ROC deciles (top left portion of the heatmap), which makes you wonder if they also delivered significant return
Chart shows consistency decile-wise returns
Chart below maps ROC consistency with starting ROC decile on aggregate 10-year return.
The more consistent the return on capital, the better the long-term returns. The bottom row shows overall returns by consistency; there’s a significant drop as you move from left to right.
The highest returns came from companies in the top-left quadrant i.e. decent and consistent ROC.
15 companies had with highest ROC 10 years ago and were consistent with those healthy ROCs over the last 10 years. They delivered healthy returns but interestingly not the highest returns of their cohort.
So far, the analysis looked at relative ranks of the universe.
But, what if its the trajectory that matters more than where a company starts from?
Trajectory of ROC matters (a lot)
The columns in the table bear explanation. We had 4 ROCE metrics, T-10, T-7, T-4 and T-1. Each ROCE number is the average ROCE of the last 3 years, which means the four ROCE metrics cover 13 years of yearly ROCE.
The scoring for ROCE trajectory is simple. Starting from the ROCE 10y ago, for each subsequent measurement, the company gets +1 if its ROCE improved over the previous and -1 if it worsens. So, any company can score maximum +3 i.e. improvements in each subsequent measurement, +1: improvements in 2 measurements and a decline in one, -1: improvement in 1 measurement and declines in two measurements or -3: consistently worsening ROCE over ten years.
Note how a company at a subpar 4% starting ROCE improving to 6%, then 8%, then 11% scores +3, while a company at 30% 10 years ago declining to 28%, then 26% and then 24% scores -3. We deliberately stayed away from more elaborate methods that take the degree of change into account.
16% companies saw continued decline in ROCE over the last 10y. This includes 29 top-decile companies. Unsurprising top-decile names that have seen consistent decline : BAJAJ-AUTO, BHEL, IL&FS, SUNPHARMA, HINDCOPPER, OPTOCIRCUITS. Some surprising names: TITAN, ASIANPAINTS
1 top decile ROCE company from 10y ago continued to improve ROCE over the last 10y! P&G
30 companies out of 813 consistently improved ROCE from 10Y ago. Notable mentions: KPRMILLS, DEEPAKNITRITE, SAREGAMA, INDIANHOTELS, TANLA PLATFORMS
80% of companies were the in the middle. Seeing increases and decreases. 48% saw one improvement and two declines, and 33% saw two improvements and one decline.
The table now shows the median returns of companies in each category.
Overall, there is a stark difference between median returns of companies that improved ROCE versus those that did not
Highest returns as a group came from 5 companies that were middle of the pack 10y ago: Deepak Nitrite, KPR Mill, Lincoln Pharma, Mold-Tek Tech, Gufic Biosciences. The 7,000%+ return came solely from Balaji Amines.
Interestingly, from the top-decile cohort, the highest returns came from the companies that saw 1 decline over a 3y period and 2 increases. List includes Navin Fluorine, Abbott india, Coforge, JB Chems & Pharma, Havells India, Page Industries. Emami Ltd is surprising in only having gone up 94% in 10Y inspite of what seem to be healthy ROCEs
The 29 companies top-decile that saw declines in ROCE unsurprisingly did only about as well as the universe, but not too shabby. Outperformers exist even in this list: TITAN, LUMAX AUTO, SUPRAJIT ENGG, CERA SANITARYWARE
Conclusion: ROC is necessary but not sufficient
Expecting just one metric to explain returns for a broad universe of stocks over 10 years is overly simplistic. Factors like growth and valuations play critical roles. However Return on Capital is an important indicator of how commodity or non-commodity a business is.
Knowing the high-ROCE companies today doesn’t necessarily tell us where they will be in the future. Common sense tells us that a business earning inordinately high return on capital will see others enter the space thus increasing competition and reducing returns for all involved.
The exceptions are those companies that have advantages (moat) that cannot be replicated. Most often we seem to conflate a temporarily high return on capital with the presence of a moat that will allow those returns to continue.
Most companies see their high returns on capital erode over time, either because of increased competition, or an advantage that was short-lived to begin with. Hence, ROC ranks tend to be fluid.
Then there are the aberrations where the ROC lens does not explain the shareholder returns or lack thereof.
Historically, only a small set of companies (Figure 3) have been able to maintain superior ROC over a decent stretch of time. But even that hasn’t ensured higher shareholder return. Just look at Castrol.
On the other hand, companies with distinctly ordinary early Returns on capital have seen strong shareholder returns. The catch being they were able to consistently improve their ROC over time signalling an improving business. (Figure 11) Being able to identify businesses that are currently earning moderate but not non-existent return on their capital with a roadmap to improve over time would be the sweet spot of companies most likely to deliver excess return.
This post is for information only and should not be considered to buy or sell any stocks. The objective of the analysis in the post is to get a general sense of the role Return on Capital plays in shareholder returns. Do let us know if there any glaring omissions in the way we have looked at the data and how we could improve the analysis. We’re on twitter @CalmInvestor and @Capitalmind_in.
By now everyone has heard about chatgpt, and most likely other publicly available Large Language Models (LLMs) like Anthromorphic’s claude, Google’s Bard and Microsoft’s Bing Chat (built on chatgpt).
Predictably there are hundreds of takes about the impact of AI on work and life in general. Depending on where you fall on the pessimism-optimism spectrum, this can range all the way from “AI will initiate ‘Skynet’ type human annihilation” to “AI will find a cure for every type of cancer”.
I’ll leave the blue-sky visioning of AI’s potential impacts to the people most qualified to do it i.e. management consulting firms and think tanks.
But I can say this with certainty, AI has applications for every professional, no matter what their field. Anyone who works at a computer can potentially harness AI to get more effective at their job.
“I really worry that people are not taking this seriously enough … this fundamentally is going to be a shift in how we work and how we interact at a level that’s as big as anything we’ve seen in our lifetimes.”
Ethan Mollick (Associate Professor, Wharton Business School)
GPT 4 can, given the right inputs, write python code to analyse and visualise data. You give it inputs about what you want the code to do, and chatgpt writes the code for you to copy, paste and run in a python environment. This alone has been a game-changer for our team looking to do repeatable analysis on large datasets that MS Excel would struggle with. But this workflow has its challenges. It can take a few iterations to get the instructions right to get working code.
Enter Code Interpreter. Code Interpreter is a native python environment within chatgpt that can take uploaded files, read and analyse them. By the way, the name ‘Code Interpreter’ is misleading because it doesn’t interpret code fed to it but writes and executes code given simple English-language prompts.
Here’s a simple example of what Code Interpreter can do:
I downloaded the historical Nifty TRI closing values since inception from niftyindices.com and uploaded it to chatgpt-4 checking the ‘Code Interpreter’ option. What follows are the prompts (formatted as quotes) and chatgpt’s responses. Note, my inputs are only the quoted text prefixed with the word “Prompt:”, all other text are verbatim responses from chatgpt.
Prompt: attached file has closing index values. convert the ‘Date’ column to datetime and sort ascending. Then please come up with insights from the data. Use charts where appropriate.
The data provided contains the following columns:
‘Date’: This column has been converted to a datetime format and ranges from June 30, 1999 to the latest available date.
‘Nifty TRI’: This seems to be an index value, presumably related to a Total Return Index.
Next, I’ll perform some basic exploratory data analysis, create some visualizations, and generate insights based on this data.
The chart illustrates the historical performance of the Nifty TRI (Total Return Index) over time, from June 1999 to the most recent data point.
The line chart shows a generally upward trend, indicating that the Nifty TRI has increased over this period. This suggests that the overall market, as represented by this index, has grown during this time.
However, it’s important to note the presence of some significant fluctuations and volatile periods. These likely correspond to various economic events and market conditions. Let’s examine the data more closely to identify periods of significant growth and decline.
To do this, I’ll calculate the year-over-year returns for the Nifty TRI. This will provide a clearer picture of how the index has performed on an annual basis.
This chart shows the year-over-year (YoY) return of the Nifty TRI, which provides a more granulated view of the index’s performance.
A few key observations can be made:
Volatility: The YoY return fluctuates quite significantly from year to year, demonstrating the inherent volatility of the index. This is expected in any equity-based index due to market dynamics and macroeconomic factors.
Negative Returns: There are several years where the index has negative returns, suggesting periods of market downturn or recession. For instance, the downturn in the year 2000 likely corresponds to the burst of the dot-com bubble, while the steep drop in 2008 is indicative of the global financial crisis.
Positive Returns: Conversely, there are also years with very high positive returns, indicating periods of robust market growth. The sharp rise in 2003, for example, may be due to the recovery from the early 2000s recession and the subsequent economic expansion.
Recent Performance: In the most recent years, the index shows positive growth with some periods of relatively flat or negative returns.
These insights provide an understanding of the index’s historical performance and its susceptibility to broader market and economic events. As always, past performance is not indicative of future results, but it can provide a useful context for understanding the possible risks and returns associated with this index.
Prompt: are there other charts you can make to help understand the data better and glean more insight?
Absolutely, we can create additional charts that may provide further insights into the data.
Rolling Returns: This chart will show the rolling return over a specific period (e.g., 1 year). This can help us understand the distribution of returns someone could expect if they had invested at any random point.
Monthly Returns Heatmap: This chart will show the returns for each month of each year, providing insights into any seasonal patterns or trends.
Histogram of Returns: This chart will show the distribution of returns, giving us an idea of the frequency of certain levels of returns.
Let’s start by calculating and plotting the 1-year rolling return.
This chart shows the 1-year rolling return of the Nifty TRI. The rolling return is the return an investor would have earned if they had invested exactly 1 year prior to any given date.
Key insights from this chart include:
Periods of High Returns: Similar to the YoY return chart, we can see periods of high returns. However, in this chart, those returns are smoothed out over a rolling 1-year period rather than being tied to the calendar year.
Periods of Negative Returns: Also similar to the YoY return chart, there are extended periods of negative 1-year rolling returns. This suggests that there were periods where, regardless of when an investor entered the market in that year, they would have experienced negative returns a year later.
Volatility: The rolling return shows more constant fluctuations, which is a clear sign of volatility in the index. This is valuable information for an investor, as it reflects the risk level of the index.
Next, let’s move on to creating a monthly returns heatmap. This will require calculating the monthly returns first.
This heatmap shows the monthly returns of the Nifty TRI for each month of each year. The color coding makes it easy to identify periods of high (green) and low (red) returns.
Key insights from this chart include:
No Obvious Seasonal Patterns: At a glance, there doesn’t seem to be an obvious seasonal pattern to the returns. Some months have high returns in certain years and low returns in others. This suggests that the Nifty TRI isn’t strongly influenced by the time of year.
Periods of High and Low Returns: Similar to previous charts, there are periods of high and low returns. The heatmap makes it easier to identify these periods. For instance, the period around 2008 and 2009 shows several months with negative returns, corresponding to the global financial crisis.
Finally, let’s create a histogram to visualize the distribution of the monthly returns. This will provide insight into the frequency of certain levels of return.
This histogram shows the distribution of monthly returns for the Nifty TRI. The line represents the kernel density estimation (KDE), which estimates the probability density function of the variable.
Key insights from this chart include:
Normal Distribution: The distribution of returns appears to be approximately normal, which is often assumed in various financial theories and models. However, there appear to be some deviations from a perfect normal distribution, such as a slight negative skew and some evidence of kurtosis (fat tails).
Negative Skew: The slight skew to the left indicates that there are more months with negative returns than would be expected in a perfectly symmetrical distribution. This suggests that while most months have positive returns, negative returns can be more severe when they do occur.
Kurtosis (Fat Tails): The histogram seems to exhibit “fat tails”, meaning there are more extreme positive and negative returns than would be expected in a normal distribution. This is common in financial data and indicates that large market movements, both up and down, can occur more frequently than a normal distribution would suggest.
These various charts provide a multifaceted view of the data, each offering unique insights. From understanding the overall trend to detecting volatility, observing seasonality, and discerning the distribution of returns, we can derive a comprehensive understanding of the Nifty TRI’s historical performance.
Prompt: any more insights from the data?
Sure, here are a few more analyses we can do:
Calculating Descriptive Statistics: This will give us a summary of the central tendency, dispersion, and shape of the distribution of returns.
Analyzing Drawdowns: Drawdowns are a measure of peak-to-trough decline during a specific period for an investment. They are usually quoted as the percentage between the peak and the trough. This can provide us with insights into the risk of the index.
Compound Annual Growth Rate (CAGR): CAGR measures the mean annual growth rate of an investment over a specified period of time longer than one year. This can provide us with a sense of the average annual growth rate.
Let’s start with calculating descriptive statistics.
Here are the descriptive statistics for the Nifty TRI and the Monthly Returns:
Nifty TRI:
Mean: 8812.16
Standard Deviation: 7156.07
Minimum: 927.03
25th Percentile: 2507.01
Median (50th Percentile): 6830.53
75th Percentile: 12951.29
Maximum: 29231.71
Monthly Return:
Mean: 1.29%
Standard Deviation: 6.43%
Minimum: -26.37%
25th Percentile: -2.29%
Median (50th Percentile): 1.35%
75th Percentile: 5.14%
Maximum: 28.08%
Key insights from these statistics include:
The average monthly return is positive at 1.29%, but there’s a significant standard deviation of 6.43%, indicating a high level of volatility.
The minimum monthly return is -26.37%, indicating that the index has experienced significant drawdowns in the past.
The maximum monthly return is 28.08%, suggesting that there have also been periods of significant growth.
Next, let’s calculate the maximum drawdown and the Compound Annual Growth Rate (CAGR).
Here are the additional insights:
Maximum Drawdown: The maximum drawdown for the Nifty TRI is approximately 5.28. This means that from its peak, the index has seen a reduction to roughly 20% of its peak value at its worst. This is a measure of the worst case loss if you bought at the peak and sold at the subsequent trough.
Compound Annual Growth Rate (CAGR): The CAGR for the Nifty TRI is approximately 13.81%. This means that, on average, the index has grown by this percentage per year over the period of the dataset.
In summary, this data analysis provides several insights into the Nifty TRI’s historical performance. Understanding these aspects, such as the overall trend, volatility, monthly and yearly returns, return distribution, maximum drawdown, and CAGR, can help investors make informed decisions about their investment strategies.
Notice above that Code Interpreter seems to have made an error with the drawdown calculation “maximum drawdown for the the Nifty TRI is approximately 5.28” which makes no sense.
Prompt: here’s the file again with index closing values. please use this to redo the drawdown calculation and identify the worst drawdown. also plot a graph visually representing drawdowns
The maximum drawdown for the Nifty TRI is approximately -0.595, or -59.5%. This means that from its peak, the index has seen a reduction to roughly 40.5% of its peak value at its worst point.
Now, let’s plot a graph visually representing drawdowns. This graph will provide a visual representation of the depth, duration, and recovery of each drawdown period.
I apologize for the oversight; it seems the matplotlib.pyplot library wasn’t imported due to the previous execution reset. Let’s import the necessary libraries and try the plot again.
This chart shows the drawdowns over time for the Nifty TRI. Drawdowns are represented by the drops below the 0% line. The shaded red area visually represents the extent and duration of each drawdown.
Key insights from this chart include:
Severity of Drawdowns: The depth of the drops below the 0% line indicates the severity of each drawdown. The most severe drawdown, as we calculated earlier, was approximately -59.5%.
Duration of Drawdowns: The length of each red shaded area along the time axis represents the duration of each drawdown. Some drawdowns are short-lived, while others last for extended periods.
Frequency of Drawdowns: Drawdowns are a regular occurrence in this index, reflecting the inherent volatility and risk in the market.
The most severe drawdown appears to occur during the 2007-2009 period, which corresponds to the global financial crisis. During this time, the market experienced significant declines, which is reflected in the depth of the drawdown during this period.
Remember, a drawdown is a peak-to-trough decline during a specific recorded period of an investment. A drawdown is usually quoted as the percentage between the peak and the trough.
At this point, let’s say we’d like to dive deeper into the analysis of drawdowns, their frequency, severity and time taken to recover.
Prompt: here’s a file with daily index closing values. Convert the date column to datetime and sort ascending. then do some analysis about drawdowns in the nifty. Mainly, how often does the nifty fall more than 10% from its peak. And when it does, how much more does it typically fall, and how long does it take to recover from its lowest point. Please represent the analysis in tabular form and graphical form where appropriate
Alright, let’s break down the tasks:
Read the file and convert the date column to datetime format, then sort by date in ascending order.
Analyze the drawdowns in the Nifty: a. Identify the peak values. b. Calculate the percentage drop from each peak. c. Determine how often the Nifty falls more than 10% from its peak. d. When it falls more than 10%, calculate the typical further fall. e. Calculate the time it takes to recover from its lowest point.
Let’s start with the first task.
Finished working
Show work
The data has been successfully sorted in ascending order based on the date.
Next, we’ll proceed with analyzing the drawdowns in the Nifty. Here’s the plan:
Compute the running maximum of the Nifty TRI.
Compute the drawdown, which is the percentage drop from the running maximum.
Identify instances where the drawdown exceeds 10%.
For each such instance, compute:
The maximum drawdown from the peak.
The time taken to recover to the peak value.
Let’s start by computing the running maximum and the drawdown.
Finished working
Show work
We’ve computed the running maximum and the percentage drawdown for each day.
Next, we’ll identify periods where the drawdown exceeds 10% and compute the following for each such period:
The maximum drawdown from the peak.
The time taken to recover to the peak value.
To do this, we’ll define a drawdown period as a continuous sequence of days where the index is below its previous peak. The start of a drawdown period is when the index falls below its previous peak, and it ends when the index surpasses this peak.
Let’s identify these drawdown periods and compute the metrics of interest.
Finished working
Show work
Here’s a tabular summary of the drawdowns in the Nifty where the index fell more than 10% from its peak:
Start Date: The date when the drawdown began.
Max Drawdown (%): The maximum percentage fall from the peak during the drawdown period.
Recovery Time (days): The number of days it took for the index to recover to its previous peak.
Next, we’ll visually represent this data. We’ll plot the drawdowns over time with the depth of the drawdown (Max Drawdown %) on the y-axis and the Start Date on the x-axis. This will help in visually understanding the magnitude and frequency of significant drawdowns.
The bar chart illustrates the significant drawdowns in the Nifty where the index fell more than 10% from its peak. Each bar’s height indicates the maximum percentage drop from the peak during the respective drawdown period, and the position on the x-axis denotes the starting date of the drawdown.
From this visual representation, we can observe periods of significant drops, like the one around 2008 (which aligns with the global financial crisis) and the drop in early 2020 (corresponding to the pandemic’s start).
To address the remaining parts of your request, we’ll now compute:
The average drop (beyond 10%) during these significant drawdowns.
The average recovery time for these drawdowns.
Let’s calculate these metrics.
Finished working
Show work
Here are the calculated metrics:
Average Drop (beyond 10%): The Nifty typically falls approximately 23.02% from its peak during significant drawdowns.
Average Recovery Time: On average, it takes about 358 days (or roughly 12 months) for the Nifty to recover to its previous peak after a significant drawdown.
In summary, while significant drawdowns of more than 10% are not frequent, when they do occur, the average further decline is around 23%. Recovery to previous peak levels typically takes about a year.
Would you like any further analysis or visualizations?
Prompt: can you write out a table with each instance of the 17 instances shown in the chart, the maximum drawdown seen and the number of days to recover
I’ve created an image of the table detailing the significant drawdowns in the Nifty.
Would you like any further assistance?
Prompt: is there a way to improve the look of the table to make it professional and readable
Certainly! Here are a few ways we can enhance the table’s appearance to make it look more professional and readable:
Add Gridlines: Introduce faint gridlines to separate rows and columns.
Improve Font: Use a consistent and clear font size.
Color Alternation: Use alternating row colors for better readability.
Header Styling: Distinguish the header row with a different background color and font style.
Cell Padding: Add padding to cells to make the content breathe.
Round Off: Round off the numbers for clarity.
Let’s implement these enhancements.
–End of chatgpt Code Interpreter session–
This could go on, but you’ve got the general idea by now.
Notice how the prompts were not elaborate or detailed but fairly open-ended. Using more specific prompts allows for more elaborate analysis and outcomes. Code Interpreter writes the code, catches errors and figures out alternative paths.
Of course, this is a simplistic example to highlight what Code Interpreter can do given some data. Getting the right outcome requires some tweaking of the inputs, which typically comes down to writing more structured prompts.
But look at what it could do just in this simple session:
Monthly returns heatmap
One-year rolling returns
Drawdowns chart
Monthly returns distribution histogram
Time to recover from drawdowns
Having done these at various points using both Excel and code, my estimate is the time required for exploratory analysis reduces by 80-90%.
Not just that, Code Interpreter can unpack zip files containing multiple files, combine them and do further analysis. It can also read pdf files to summarise or look for data in them.
The closest analogy to using chatgpt and Code Interpreter is like everyone having access to a smart yet inexperienced intern conversant with Python programming. If your job requires any data and analysis, you should be using Code Interpreter to see how you can speed up and improve. Imagine, this is just the beginning!
NSE has a ton of equity indices, 96 of them. Removing a bunch of the repetitive ones, we are still left with over 50. Chart below shows their CAGR since inception. All the way from 23% (Midcap150 Momentum50) to -3% (Realty). The Nifty has clocked 14% over 24 years.
Worst drawdowns. Realty fell 93% from peak, IT *gasp* 90% from March 2000 to Oct 2001.
CAGR calculations assume you invest on inception date and never again. So we also see how a monthly SIP would’ve done in each of those indices. The worst 3 SIP performers: Media, High Beta 50 and Realty The best 3: Midcap150 Momentum 50, Alpha 50, Smallcap250 Quality 50.
Chart shows the difference between SIP XIRR and CAGR. A look at the Realty index chart highlights why the CAGR is so much worse than what a monthly SIP would’ve done.
How the various indices did versus the Nifty on SIP XIRR and Volatility.
4: Worse than the Nifty on both return and volatility (Red ‘X’ marks the Nifty)
Media
Infrastructure
Oil & Gas
Realty
Nifty100 Liquid15
High Beta 50
Commodities Metal
Lower return than the Nifty, but also lower volatility Nifty
Total Market
Nifty 100 Alpha 30
Nifty 200
CPSE
Nifty100 Quality30
Dividend Opportunities 50
Nifty 100
Healthcare
Smallcap 250
Growth Sectors 15
Pharma
Higher SIP return but also higher volatility
Nifty Bank
Nifty 200 Alpha 30
Fin Services ex-Bank
Midcap Select
Fin Services
Nifty 500 Value 50
Nifty 500
Next 50
IT
Midcap Liquid 15
Nifty Equal Wt.
Alpha 50
Energy
Consumer Durables
Auto
Nifty 200 Momentum 30
Microcap 250
Higher SIP return and Lower Volatility than the Nifty
LowVol 50
LargeMid 250
Nifty100 Low Vol 30
Midcap 100
MidSmall 400
FMCG
Mid150 Quality50
Small250 Quality50
Midcap150 Momentum 50
Nifty100 Equal Wt.
Nifty500 Multicap
Nifty50 Value 20
Nifty200 Quality 30
Noncyclical Consumer
Caveats when drawing conclusions from index data:
Inception dates of the various indices compared are different, some go back to 1995, others to 2005, still others have later inception dates. The “youngest” index in this comparison is Nifty100 Liquid15, with an inception date in 2010. This could make an index look better or worse than it would had it been around for a longer duration.
We found (many) issues with http://niftyindices.com data. Garbage values, repeated dates and a few others. We corrected most, but possible some slipped through here.
Index inception dates are not publish dates. Most NSE indices were published only recently, presumably the ones that backtested well. This means some indices probably look good only with the benefit of hindsight.
Not all indices are consistently investable, The Alpha50 index is one such example where the Kotak Alpha 50 ETF struggled to add one of the constituents of the index due to lack of liquidity as the stock hit upper circuits before it turned around and started doing the same thing on the way down. So, a high “model” index return is not actual return.
Follow @CalmInvestor on twitter
NSE has a ton of equity indices, 96 of them. Removing a bunch of the repetitive ones, we are still left with over 50. Chart below shows their CAGR since inception. All the way from 23% (Midcap150 Momentum50) to -3% (Realty). The Nifty has clocked 14% over 24 years. (1/10) pic.twitter.com/LP43sFOkUi
My top 10 highlights from the book: The Success Equation: Untangling Skill and Luck in Business, Sports and Investing by Michael Mauboussin
Much of what we experience in life results from a combination of skill and luck. A basketball player’s shot before the final buzzer bounces out of the basket and his team loses the national championship. A pharmaceutical company develops a drug for hypertension that ends up as a blockbuster seller for erectile dysfunction. An investor earns a windfall when he buys the stock of a company shortly before it gets acquired at a premium. Different levels of skill and of good and bad luck are the realities that shape our lives. And yet we aren’t very good at distinguishing the two.
If you take concrete steps toward attempting to measure those relative contributions, you will make better decisions than people who think improperly about those issues or who don’t think about them at all.
When luck has little influence, a good process will always have a good outcome. When a measure of luck is involved, a good process will have a good outcome but only over time.
When an activity is mostly skill, we need not worry much about the size of the sample unless the level of skill is changing quickly. For activities with a good dose of luck, skill is very difficult to detect with small samples. As the sample increases in size, the influence of skill becomes clearer.
Sports are the easiest activities to analyze because the rules are relatively stable over time and there is lots of data. Other social processes, including business, have fewer rules and boundaries than sports and therefore tend to be more complex. Still, many of the same analytical methods are valid. Markets in general are the most difficult to analyze because prices are established through the interaction of a large number of individuals.
Randomness and luck are related, but there is a useful distinction between the two. You can think of randomness as operating at the level of a system and luck operating at the level of the individual.
There’s a quick and easy way to test whether an activity involves skill: ask whether you can lose on purpose.
Skill shines through only if there are a sufficient number of decisions to weed out bad luck.
Any activity that combines skill and luck will eventually revert to the mean. Slow reversion is consistent with activities dominated by skill, while rapid reversion comes from luck being the more dominant influence.
In his book The Theory of Gambling and Statistical Logic, Richard Epstein, a game theorist trained in physics, notes that there is no way to assure that you’ll succeed if you participate in an activity that combines skill and luck. But he does say, “It is gratifying to rationalize that we would rather lose intelligently than win ignorantly. Luck may or may not smile on us, but if we stick to a good process for making decisions, then we can learn to accept the outcomes of our decisions with equanimity.”
My top 10 highlights from the book: The Signal and the Noise: The Art and Science of prediction by Nate Silver
The need for prediction arises not necessarily because the world itself is uncertain, but because understanding it fully is beyond our capacity. We can never make perfectly objective predictions. They will always be tainted by our subjective point of view. Prediction is important because it connects subjective and objective reality.
Risk, as first articulated by the economist Frank H. Knight in 1921 is something that you can put a price on. Uncertainty, on the other hand, is risk that is hard to measure.
Whenever you have a large number of candidate variables applied to a rarely occurring phenomenon, there is the risk of overfitting your model and mistaking the noise in the past data for a signal. “With four parameters I can fit an elephant,” the mathematician John von Neumann once said of this problem. “And with five I can make him wiggle his trunk.”
The idea behind frequentism is that uncertainty in a statistical problem results exclusively from collecting data among just a sample of the population rather than the whole population. The frequentist approach toward statistics seeks to wash its hands of the reason that predictions most often go wrong: human error. It views uncertainty as something intrinsic to the experiment rather than something intrinsic to our ability to understand the real world. The frequentist method also implies that, as you collect more data, your error will eventually approach zero: this will be both necessary and sufficient to solve any problems.
The bigger problem, however, is that the frequentist methods—in striving for immaculate statistical procedures that can’t be contaminated by the researcher’s bias—keep him hermetically sealed off from the real world. These methods discourage the researcher from considering the underlying context or plausibility of his hypothesis, something that the Bayesian method demands in the form of a prior probability. Thus, you will see apparently serious papers published on how toads can predict earthquakes, or how big-box stores like Target beget racial hate
Making predictions based on our beliefs is the best (and perhaps even the only) way to test ourselves. One of the nice characteristics of the Bayesian perspective is that, in explicitly acknowledging that we have prior beliefs that affect how we interpret new evidence, it provides for a very good description of how we react to the changes in our world.
Absolutely nothing useful is realized when one person who holds that there is a 0 percent probability of something argues against another person who holds that the probability is 100 percent. Many wars—like the sectarian wars in Europe in the early days of the printing press—probably result from something like this premise.
One property of Bayes’s theorem, in fact, is that our beliefs should converge toward one another—and toward the truth—as we are presented with more evidence over time. A heuristic approach to problem solving consists of employing rules of thumb when a deterministic solution to a problem is beyond our practical capacities.
Some theorists have proposed that we should think of the stock market as constituting two processes in one. There is the signal track, the stock market of the 1950s that we read about in textbooks. This is the market that prevails in the long run, with investors making relatively few trades, and prices well tied down to fundamentals. It helps investors to plan for their retirement and helps companies capitalize themselves. Then there is the fast track, the noise track, which is full of momentum trading, positive feedbacks, skewed incentives and herding behavior. Usually it is just a rock-paper-scissors game that does no real good to the broader economy—but also perhaps also no real harm. It’s just a bunch of sweaty traders passing money around. However, these tracks happen to run along the same road, as though some city decided to hold a Formula 1 race but by some bureaucratic oversight forgot to close one lane to commuter traffic. Sometimes, like during the financial crisis, there is a big accident, and regular investors get run over.
How good we think we are at prediction and how good we really are may even be inversely correlated.
This post, first published on capitalmind.in, wasn’t meant to be a post, but just a few things I scribbled for myself as things about money I’d tell my younger self. The list grew, and so here it is.
The ten money messages I’d want my younger self to absorb:
(1) You don’t need to think about investing as much as you think you do
“The investor who starts a SIP at 25 ends up with double the corpus of the one who starts ten years later, even with a bigger SIP! Behold the magic of compounding!”
“Do you realise how much healthcare will cost when you’re 60?”
The Investment Industry wants you to think there’s a train, and it is leaving without you.
The takeaway from most investment-related messaging, for most folks busy with their already full work schedules, is that they are not doing “enough” with their money. They’ll have you believe you must be on top of every rupee, directing it to the best investment options. Any delays mean you are compromising your financial future. The guilt of not doing enough investing is almost as ubiquitous as mom guilt, what working mothers are constantly told they have to bear.
Because FUD (Fear, Uncertainty and Doubt) is an influential sales tool for most things, including investment products.
Relax. Investing is not an overnight miracle pill weight-loss transformation but a lifelong habit; give it time. You are better off thinking more about many things than where to invest: your family, health, and increasing earning power.
(2) Investing won’t make you wealthy; your earnings will
As a newly minted employee, you heard what your manager’s manager’s boss earns, and you refused to believe someone could make that much. That number sounds inaccessible. Over time, you will not even realise as you pass that mark and then some. A simple CAGR calculation of now and then will prove your earnings growth rate outperformed your portfolio and probably most holdings in your portfolio.
Taking a challenging work assignment and succeeding will significantly impact future opportunities and, therefore, more wealth than finding the “best” investment vehicle today.
The highest probability 100+ bagger you can own is your earning capability. You can maximise your earnings by moving countries and industries, becoming an entrepreneur, upskilling formally or informally, or even being good where you are.
Getting good at something valuable is your best shot at maximising future net worth.
Most people overestimate their investments’ future growth rate and underestimate their earnings’ future growth rate.
(3) Let’s face it; there is no “number”
We’ve been told Step 1 of being a responsible adult is building a financial plan that lays out all the big things you may want and need in your life and putting a number against them. Then, to find out that to meet that number, the right time to start a SIP was about when you were conceived.
I find the whole “x will cost XX in 15 years” type of thinking stressful. Fifteen years of any compounding will result in a daunting number with respect to today’s earnings. I suggest turning that thought around. Something will only cost XX if enough people can afford it. Unless you predict your earnings capability will be inferior to your peers, you should be able to afford everything you do today and then some.
Of course, being good at managing your expectations for the future helps.
(4) Just care a little about beating inflation
Inflation is not this evil thing eroding our wealth. It is a natural side-effect of a normal, growing economy. As long as you are not on a fixed income, you don’t need to be stressing about what a loaf of bread will cost ten years from now.
You should have your surplus working to at least match inflation post-taxes. And equities are the most accessible way of matching and even beating inflation by a distance. Why? Because if inflation means rising prices, it follows those will reflect in the prices of goods and services companies make, inflating their earnings at least in line with inflation.
(5) Spreadsheets don’t work as advertised with important decisions
A Buy versus Rent spreadsheet will not decide one of your life’s most significant money decisions. A comparison of mileage and running costs will not determine your choice of vehicle. The same goes for important decisions like where to live, who to marry, whether to have children, etc. There is no objective way to input how something makes you feel into a cell. This is hard to process for those who pride themselves on their ability to make objective decisions.
A clear sign that a decision has too much Excel but too little thinking is when you’ve plugged in everything you could think of and are far from convinced about the answer. Sometimes, it means something really important is not on the sheet. Mostly, it means your emotions have already made up your mind.
You learn with time to trust your gut on some of the more important things. And that’s OK.
(6) Know your money personality
Growing up in our household, money was like the sun. You always felt its presence or absence, but you never looked directly at it. So, money or any concerns about money were never discussed.
Maybe your parents were overly careful with money, and you resented that. Or you experienced traumatic shortages from a business that went bad, and so you are a compulsive saver who cannot spend. Or maybe you went the other way and tend to spend big instead. I have met very few people who don’t carry baggage about money from their upbringing.
In his book “Happy Money”, Ken Honda talks about the eight money personalities.
Knowing you and your spouse’s core attitudes to money is valuable. Doesn’t mean you have to fight it, but helps to know which side your margin for error lies.
The compulsive spender needs a way to add a delay to big-ticket purchases, like enforcing a 48-hour cool-off period. The compulsive saver must be reminded of the value of things and experiences to unclench. Knowing where your tendencies lie helps you plan to mitigate their worst.
The most financially successful people recognise the importance of money and give it the consideration it deserves, but not more.
(7) Recognise if you have a SCALE problem
One consequence of actively avoiding thinking about money for most of your life is that it’s a struggle to make decisions involving substantial sums of money.
Starting a new SIP? Let’s do 10k / month since that’s the ever-present round number. Never mind that it’s now just 2% of your salary, and this effort won’t move the needle.
So the “unactioned” money keeps getting bigger in the scheme of things, and the bigger it gets, the scarier it becomes to decide about. Procrastinating about it becomes easier, and it stays.
This is one reason why Real Estate investments are easier because that is one area where large ticket decisions are expected and do not seem to faze people.
If you know you struggle with scale, becoming aware of it can help so you can make it easier by breaking it down into smaller chunks or, better yet, have someone else do it.
(8) Avoid borrowed lenses to view the world
Let’s say you decide to buy a new car. If you’re an avid road tripper and a team-BHP regular, your process and outcome will look a certain way. Different from if you think of a car as a utility to get from Point A to B.
The problem happens when you recruit your petrolhead friend to decide for you. His lens of looking for the most drivable car might prioritise a car you don’t wholly appreciate but end up unwillingly spending more time and money caring for and servicing.
A lot of investment decisions get made that way. The active investor who subscribes to three different research services and reads lots of reports before putting a chunk of her net worth into a stock. She recommends it to a friend who would never open a research report except by mistake. The friend buys the stock but neglects to check again even as the actively engaged investor has moved on 18 months later as the company’s prospects changed.
Replace stock with Active mutual fund, PMS, or AIF; the idea still holds good.
There are investors closely tracking the holdings of their investment vehicles and those who would instead do anything but. Who has better investment outcomes is debatable.
When the hands-off investor temporarily convinces themselves they are interested in making lots of decisions, undesirable things happen.
Most people are better off with the dependable, low-frills car over the more exciting, higher-maintenance car because they only need to get from A to B. The same applies to investing.
(9) Back-seat driving is rarely worth the time
The economics of international trade between countries utilises a concept called ‘comparative advantage’ when deciding what to manufacture itself versus buy from another country. So, suppose a country needs commercial aircraft and baby diapers, and it makes aircraft more efficiently than other countries. Economically speaking, it will be better off specialising in making aircraft and importing diapers. Funnily, even if the country is better than its neighbours at diapers too, it is better off specialising in aircraft and buying diapers.
We apply this daily when deciding on having someone come in to cook, even though you might be an excellent cook yourself. Because the opportunity cost of cooking is high when considered against that time being utilised elsewhere, for example, to add new skills relevant at work.
But we also violate the opportunity cost principle all the time. We spend extra time looking for discount codes on small-ticket items, even though we know, taken together, that chunk of time is worth way more than the money we save.
The realm of money is no different. Investors hyperactively track what their chosen investment vehicles are doing and decide to reduce allocation here and increase there, exit this fund and add this new fund. The behaviour gap studies year after year show across the board that investor returns lag the returns of their investment vehicles. Which means they would be better off not tinkering.
But even assuming a healthy strike rate in making decisions to tinker with investments frequently, the incremental return is most likely negative and not worth the opportunity cost.
(10) Learn to spend
“But these must have been so expensive!” my mother said with wide-eyed shock when she noticed the tickets I had emailed her. My parents were about to visit my sister, and making the fifteen-hour flight a little more comfortable with better seats was a no-brainer. But I knew, left to them, they wouldn’t even consider it. They had never learnt to spend, least of all, on themselves.
Muscle imbalances occur when you strengthen one muscle but not its antagonistic pair, like the quadriceps and hamstrings, leading to a limited range of motion and increased injury risk. If you grew up in middle-class India, there’s a good chance your spending muscle is underdeveloped. That imbalance manifests itself differently across people. Some rationalise they enjoy saving more than spending, continuing to keep money on a pedestal. Others overcorrect by ticking all the “look, I have money” boxes with the upmarket address, German-badged car and club membership.
Being good at spending is the opposite of doing it to impress others. It is getting to know yourself well enough to articulate why you save and invest in the first place. And it’s harder than it sounds.
Those are my ten money messages. Yours, of course, might be completely different.
In the words of Tim O’Reilly:
“Money is like gasoline during a road trip. You don’t want to run out of gas on your trip, but you’re not doing a tour of gas stations.”
They hold the same constituents except in different weights.
The Nifty 50 is your traditional market cap-weighted index where each stock is allocated a weight in proportion of its free-float market cap. So HDFC Bank, after its merger with HDFC Ltd accounts for almost 14%, Reliance Industries nearly 10% and so on.
Source:
The Nifty 50 Equal Weight is an alternative weighting strategy. It includes the same 50 companies, except weighted equally. Weights are reset to equal-weight every quarter.
Same constituents but significantly different weights. Which one, the Nifty 50 or Nifty 5 Equal Weight has done better over the years?
If one had to guess, intuitively, it’d be the market cap weighted Nifty 50 given successful mega caps automatically get a higher allocation.
Capitalmind found the comparative data had interesting things to say.
Chart shows the Nifty 50 and Nifty 50 Equal Weight equity curve
Nifty Equal Weight has done better in 15 of 24 calendar years. This is Total Returns.
Drawdowns on the market cap and equal-weight versions are not too different.
One and Three-year rolling returns indicate Equal Weight does better in out and out bull markets (e.g. 2004 – 07) and worse in indifferent years (e.g. 2018 – 20)
The table summarises the comparison:
Analysis as of 09-sep-2023
Overall Comparison Summary of Nifty 50 vs. Nifty 50 Equal Weight from June 1999 to Sep 2023 shows Equal Weight ahead on all metrics.
A few things to consider before ditching the market-cap weighted Nifty50 for its Equal Weight variant:
History says Equal Weight tends to do better in roaring bull markets i.e. when most stocks rise and lags in indifferent or sideways markets. Intuitive considering the largest by market cap companies tend to be dominant in their respective sectors and not affected as much
There are several funds and ETFs that offer exposure to the Nifty50 but only two (as of writing this) that offer exposure to the Nifty50 Equal Weight.
The impact of the market cap weighting cuts both ways, When the handful of those companies do well, the Nifty handily outperforms the Equal Weight. Historically, most investment managers have struggled to beat the traditional market-cap weighted benchmark index for this reason.
Picking the Equal Weight over the Nifty 50 is like backing the underdog. But then, who doesn’t love an underdog story?
A recent tweet citing Mint analysis talks about how the probability of higher returns increases with increasing investment horizon.
The numbers looked a bit off, so I recreated the analysis using the Nifty 50 Total Returns Index.
The numbers in each of the cells are higher than what is shown in the analysis cited in the Mint article. For instance, the probability of returns exceeding 8% over a 10-year holding period goes up from 76% to 97%, a sizable difference. Similarly, the probability of exceeding 12% over 10+ years is only 51% (a coin toss) in the Mint piece but is 68% on the basis of our analysis, a significant increase.
The reason for the difference might be that the Mint analysis didn’t consider dividends from Nifty stocks. The yield has historically ranged between 0.6% to as much as 3%, with a median value of 1.32%.
Overall, the case for long-term investing gets stronger when you also consider dividends being reinvested.
I remember the precise moment I had my first doubts about books on management success.
In one of my earliest jobs, as a fresh management consulting associate, we used to get assigned books at random by the partners we reported to. Predictably, these were from management lessons and Business Strategy genres. Saturday mornings were set aside for us to present what we’d understood from those books to the rest of the office. A way to make sure we read them.
My BS detector first went off while reading this book called ‘Big Winners and Big Losers‘ by Alfred Marcus. As far as I know, this book didn’t end up on any bestseller lists, so here’s a quick summary:
The book analyses nine “big winner” companies and nine “big loser” companies over ten years from 1992-2002 to understand the key differences that lead to long-term success or failure.
The author identifies four essential qualities that differentiate the big winners from the big losers:
Niche strategy – Winners occupy a “sweet spot” in the market with a well-executed niche strategy. Losers fail to find or defend a niche.
Agility – Winners are agile and adapt to market changes. Losers tend to be rigid and cling to exhausted strategies.
Discipline – Winners maintain discipline to reduce costs and improve quality. Losers display ineptitude and lack financial discipline.
Focus – Winners remain focused on their capabilities and strengths. Losers lose focus and stray into too many areas.
According to the author, balancing these four qualities provides the framework for sustainable competitive advantage.
As I was skimming the book to finish my review and get back to billable work, I paused on an example of how “Focus” helped one successful company while lack of focus cost another. Something seemed off, so I flipped back to the “Agility” chapter.
One winning company had succeeded by remaining “focused” on its core business. Yet another winner was praised for being “agile” by changing its core offering. Similarly, one struggling company was criticized as “rigid” for not adapting its core, while another loser had “strayed” from its mainstay business. The business cases seemed selectively chosen to fit narratives around “Focus” versus “Agility.” Wait a minute.
Could it be that the rules of business success (and failure) are an elaborate exercise in hindsight bias? Of joining the dots after the fact?
After the 2011 World Cup final, we all, armchair experts, called MS Dhoni’s decision to promote himself ahead of Yuvraj Singh brave and tactically brilliant. We would have called it the daftest decision in sports history if the outcome had gone the other way. Hindsight Bias. Like choosing to go with that pitch in Ahmedabad. (No, too soon.)
Once you see it, you can’t unsee it.
You can dismiss ‘Big Winners and Big Losers’ given hardly anyone has heard of it. However, three management books that exhibit the same fundamental flaw have sold more than 10 million copies combined.
The original blockbuster that kickstarted the management success genre is ‘In Search of Excellence‘ by Mckinsey consultants Tom Peters and Robert Waterman.
‘In Search of Excellence’, published in 1982, is based on research into 43 “excellent” American companies across several industries like technology, consumer goods, and services. Through extensive interviews and study, the authors identified eight common attributes that drove the success of these organisations:
A bias for action
Close to the customer
Autonomy and entrepreneurship
Productivity through people
Hands-on, value-driven management
Sticking to the core business (niche focus)
Simple form, lean staff
Simultaneous loose-tight properties
All great qualities to have for any business. But hardly clearly defined.
Despite its massive commercial success, the biggest criticism of ‘In Search of Excellence’ was that by starting with successful companies to begin with, it had survivorship bias.
Like concluding that wearing Nike gear and practising a lot makes you a great tennis player because the world’s greatest tennis players wear Nike and practice a lot.
As it turned out, even great tennis players don’t stay great.
Here’s what happened to just some of the excellent companies soon after the book came out:
Wang Labs – Declared bankruptcy in 1992.
NCR – Significant declines and mass layoffs in the 1990s. Sold to AT&T in 1991.
Xerox – Fell from grace due to overseas competition. Massive losses in the early 2000s.
Data General – Collapsed and sold its assets to EMC in 1999.
Delta Airlines – Filed for bankruptcy in 2005 after years of losses.
Source: mckinsey.com
Among the companies that did not disappear, including the likes of IBM, HP, 3M, McDonald’s, Dana, and Emerson Electric, most struggled to beat the S&P500 over the two decades. Walmart, Intel, Merck, and J&J were notable exceptions that thrived.
Subsequent flagbearers of the business success genre addressed the survivorship bias problem by doing what Alfred Marcus did. They included a set of mediocre or “unsuccessful” companies for comparison with the great companies before drawing out the rules of corporate success. Contrasting ordinary companies against great companies should tell us what additional ingredients the latter have.
Built to Last: Successful Habits of Visionary Companies by Jim Collins, a McKinsey consultant and Jerry Porras, a Stanford Professor, did precisely that.
The book examines 18 “visionary” companies that have demonstrated enduring success and compares them to “similar” but less successful companies in the same industries. The research aims to identify the key factors that differentiate visionary firms.
They concluded visionary companies are guided by a core ideology that gives them a purpose beyond just making money. They also exhibit key dynamic traits like experimentation, embracing change, and stimulating progress, allowing them to evolve over time.
Several of those visionary companies faced trouble soon after the book was published.
Marriott – Faced significant losses in the early 2000s after overexpansion.
Walt Disney – Struggled after the death of Frank Wells in 1994, with multiple poor-performing films and leadership issues until the 2000s revival.
Citicorp struggled after the dotcom crash and various accounting scandals in the early 2000s
Motorola lost market share in the mobile phone business
Sony underwent massive restructuring, selling Columbia Pictures and Sony Music Entertainment to cover losses in its consumer durables business
Source: mckinsey.com
In 2011, Jim Collins returned with ‘Good to Great‘; this time, his co-author was Morten Hansen, a UC Berkeley professor.
The book, written after five years of research, set out to identify the factors that allow companies to make the transition from being good to truly great. They even defined “greatness” as having delivered 3x the market average over 15 years. It’s hard to argue against that definition, especially if you’re an investor.
The book found what the companies that make the transition from good to great have:
Level 5 Leadership: Are led by humble, determined leaders focused on the company, not themselves.
First Who, Then What: Get the right people on the bus first before figuring out where to drive.
Confront Brutal Facts: Confront the brutal truth of their situation to make good decisions.
Hedgehog Concept: Understand what they can be the best at and focus on that.
Culture of Discipline: Maintain a disciplined culture, people and approach.
Technology Accelerators: Avoid fads and only adopt technology that fits their hedgehog concept.
Again, these are solid logical concepts you’d want for your company, except maybe the hedgehog concept of only doing one thing to exclude everything else.
Sure enough, like for the other two books, only four of the 11 companies outperformed the market two decades after the book was published. One went bankrupt, while two others have been close at different times.
Source: mckinsey.com
So what does the exhaustive study of successful companies of the past tell us?
Past performance is no guarantee of future results
All these books resulted from years of data-gathering, painstaking classification of each bit of information (press releases, business publications, financial reports), and interviews with managers before the findings were finalised. You could not imagine doing more in the areas the authors explored and tackled.
Overall, across the 48 companies (with overlap) profiled as great and successful companies in those books, 21 (44%) outperformed the market in the two decades after. The remaining 56% did not beat the market. Investing in great companies to outperform the market was slightly worse than a coin toss.
Fifteen companies (almost 1 in 3) trailed the market by over 5% annually. Of those, several went bankrupt or were acquired at fire sale prices by other companies. The remaining companies delivered market returns or underperformed.
Past and current greatness is not even a guarantee of survival, let alone future dominance.
Causality, but the other way
If you worked at a company when it made record profits, chances are the atmosphere in the office was supportive. There were budgets to conduct manager training, offer flexible policies around days off, and offer more employee-friendly perks. You’d strongly agree if you were asked whether the company was good at people management.
Conversely, if the company was going through a few quarters of declining earnings or declining sales, budgets were likely cut, hiring and increments frozen and additional policies added for expense approvals. Someone asked about their time would shudder, saying it was their worst workplace.
Everyone looks good when things work. Good leadership, smart strategy, excellent execution. Then it stops working. And all of it looks dumb, but in retrospect.
Phil Rosenzweig calls it ‘The Halo Effect’. Given a currently successful company, all things about the company will seem to have been instrumental to that success. The opposite will look true for unsuccessful companies.
The interview responses, a vital component of reaching conclusions, were predetermined once the authors picked companies in their heyday to analyse.
Being in the right place at the right time is underrated
The one glaring thing missing from the extensive studies was understanding the companies’ external environments.
Walmart happened to be in the discount retailing space just when the concept of big box stores and shoppers driving to the suburbs to do their shopping took hold. Of course, it deserves credit for modernising its supply chain to cater to that model, while Kmart struggled to shift.
National Semiconductor, Wang Labs, and DEC were dominant in the era of centralised computing and mainframe computers. Intel stole their thunder when the field shifted to personal computers.
Philip Morris prospered in an era of big tobacco, ironically when anti-smoking policies forbade advertising, saving them costs while effectively ending the risk of new competition.
On the other hand, the maker of the finest horse carriages in the early 1900s couldn’t have done anything other than exit the business when Ford’s Model T started gaining mass acceptance.
The common theme for every company that did well was it was in the right place at the right time.
Few companies manage to swim against the tide when their core line of business comes under existential threat because of changing technology or broader demographic shifts.
I’m therefore naturally sceptical of analysis that goes like this:
Here are a bunch of great companies based on how they’ve done in the past Here are the things we found that make them great (visionary promoter, distribution network, etc.) Other companies do not have these excellent characteristics (because look at their results so far) Therefore, buying these companies and holding them for the next two decades is the best (and only) investment strategy.
Believing that great companies of the past automatically qualify as buy-and-forget stocks for the future is one of the most enduring fallacies in investing because the evidence shows the opposite. From the ‘The original Nifty Fifty‘ of the 1970s to businesses like Kodak, Xerox, Nokia, Blackberry, Sears, and GE that looked unbeatable at one stage only to decline into irrelevance, some quickly, others gradually.
Take recipes for greatness and claims of infallible investments with a grain of salt. Context and luck play an outsized role, often more than the easily visible and controllable things.
Even the greatest companies in history couldn’t fight the trend. We would do well to respect this fact.
Here are the things we found that make them great (visionary promoter, distribution network, etc.) 
