Hanging out with the lads

One of my favourite podcasts this year has been The Rest is History with Tom Holland and Dominic Sandbrook. It is simultaneously insanely informative and insanely funny, and I’ve been listening to it as regularly as I can this year.

A few months back, a prequel to The Lord Of The Rings called “Rings of Power” came out on Amazon. To commemorate that, Rest is History did a few episodes on JRR Tolkien. It’s a fascinating profile, but one line especially stood out.

Holland was talking about how Tolkien found himself a steady girlfriend when he was 13 (and got himself excommunicated from the church in the process – he was Catholic and she was Protestant, I think). And then he said “that part of his life having been settled, he now focussed on other things, such as hanging out with the lads”.

I find this to be a rather profound line. “Hanging out with the lads”. And having found myself a steady girlfriend for the first time relatively late in life (when I was nearly 27), I can look back at my life and think of the value of this phrase.

When you are single, among other things, you become a “life detector” (this phrase comes from one friend, who used it to describe another, saying “she is a life detector. She puts blade on anything that moves”). Especially if, as a youngster, you have watched good but illogical movies such as Dil To Pagal Hai.

You may not realise it until you are no longer single, but being single takes a toll on your mental health. Because you are subconsciously searching for a statistically significant other, you mind has less time and space for other things. And you miss out on more enjoyable things in life.

Such as “hanging out with the lads”.

I have written (forgot where, and too lazy to find the link now) about how being no longer single was fantastic in terms of simply appreciating other women. You could say they were nice, or beautiful, or intelligent, or whatever, and it would be a simply honest comment without any “ulterior motives”. More importantly, you could very simply tell her that, without worrying whether she will like you back, what caste she belongs to (if you were into that kind of stuff) and so on.

I listened to the podcast on Tolkien when it came out a few months ago, but got reminded of it over the weekend. I spent most of my weekend in IIMB, at our 15th year batch reunion (ok, it’s been 16 years since we graduated but our party was postponed by a year due to Covid). As part of the reunion (and unlike our 10th reunion in 2016), we had a real “L^2 party” (check here to see what L^2 parties used to be (for me) back in the day).

So effectively, this Saturday I was at my first ever L^2 party after I had graduated from IIMB. In other words, I was at my first ever L^2 party where I was NOT single (my wife wasn’t there, though. Pretty much no one from our batch brought spice or kids along).

However, despite the near 17-year gap from the last L^2 I had attended, I could feel a different feeling. I found myself far more willing to “hang out with the lads” than I had been in 2004-6. I had a lot of fairly strong conversations during the time. I held random people and danced (thankfully the music got better after a while).

Through the entire party I was at some kind of perfect peace with myself. Yeah, you might find it strange that a 40-year-old guy is writing like this, but whatever. Early on, I sent a video of the party to my wife. She sent back a video of our daughter trying to imitate the way I was “dancing”.

And it was not just the party. I spent a day and a half at IIMB, hanging out with the “lads” (which included a few women from our batch), having random conversations about random things, just laughing a lot and exchanging stories. Nobody spoke about work. There was very little small talk. Some conversations actually went deep. It was a great time.

With the full benefit of hindsight, I had as much fun as I did in this period (ok i might be drawing random connections, but what the hell)  because I was secure in the fact that I am in a steady relationship, and have a family. And it took me a long time to realise this, well after I had stopped being single.

 

 

 

 

Key Person Risk and Creative Professions

I’m coming to the conclusion that creative professions inevitably come with a “key person risk”. And this is due to the way teams in such professions are usually built.

I’ll start with a tweet that I put out today.

(I had NOT planned this post at the time when I put out this tweet)

I’ll not go into defining creative professions here, but I will leave it to say that you typically know it when you see one.

The thing with teams in such professions is that people who are good and creative are highly unlikely to get along with each other. Going into the animal kingdom for an analogy, we can think of dividing everyone in any such professions into “alphas” and “betas”. Alphas are the massively creative people who usually rise to lead their teams. Betas are the rest.

And given that any kind of creativity is due to some amount of lateral thinking, people good at creative professions are likely to hallucinate a bit (hallucination is basically lateral thinking taken to an extreme). And stretching it a bit more, you can say that people who are good at creative tasks are usually mad in one way or another.

As I had written briefly this morning, it is not usual for mad people (especially of a similar nature of madness) to get along with each other. So if you have a creative alpha leading the team, it is highly unlikely that he/she will have similar alphas in the next line of leadership. It is more likely that the next line of leadership will have people who are good complements to the alpha leader.

For example, in the ongoing World Cup, I’ve seen several tactical videos that have all said one thing – that Rodrigo De Paul’s primary role in the Argentinian team is to “cover for Messi”. Messi doesn’t track back, but De Paul will do the defending for him. Messi largely switches off, but De Paul is industrious enough to cover for Messi. When Messi goes forward, De Paul goes back. When Messi drops deep, De Paul makes a forward run.

This is the most typical creative partnership that you can get – one very obviously alpha creative supported by one or more steady performers who enable the creative person to do the creative work.

The question is – what happens when the creative head (the alpha) leaves? And the answer to this are going to be different in elite sport and the corporate world (and I’m mostly talking about the latter in this post).

In elite sport, when Messi retires (which he is likely to do after tomorrow’s final, irrespective of the result), it is virtually inconceivable that Argentina will ask De Paul to play in his position. Instead, they will look into others who are already playing in a sort of Messi role, maybe (or likely) at an inferior level and bring them up. De Paul will continue to play his role of central midfielder and continue to support whoever comes into Messi’s role.

In corporate setups, though, when one employee leaves, the obvious thing to do is to promote that person’s second in command. Sometimes there might be a battle for succession among various seconds in command, and the losers also leave the company. For most teams, where seconds in command are usually similar in style to the leader, this kind of succession planning works.

For creative teams, however, this usually leads to a disaster. More often than not, the second in command’s skills will be very different from that of the leader. If the leader had been an alpha creative (that’s the case we’re largely discussing here), the second in command is more likely to be a steady “water carrier” (a pejorative term used to describe France’s current coach Didier Deschamps).

And if this “water carrier” (no offence meant to anyone by this, but it is a convenient description) stays in the job for a long time, it is likely that the creative team will stop being creative. The thing that made it creative in the first place was the alpha’s leadership (this is especially true of small teams), and unless the new boss has recognised this and brings in a new set of alphas (or identifies potential alphas in the org and quickly promotes them), the team will start specialising in what was the new boss’s specialisation – which is to hold things steady and do all the right things and cover for someone who doesn’t exist any more.

So teams in creative professions have a key man risk in that if a particularly successful alpha leaves, the team as it remains is likely to stagnate and stop being creative. The only potential solutions I can think of are:

  • Bring in a new creative from outside to lead the team. The second in command remains just that
  • Coach the second in command to identify diverse (and creative alpha) talents within the team and recognise that there are alphas and betas. And the second in command basically leads the team but not the creative work
  • Organise the team more as a sports team where each person has a specific role. So if the attacking midfielder leaves, replace with a new attacking midfielder (or promote a junior attacking midfielder into a senior attacking midfielder). Don’t ask your defensive midfielders to suddenly become an attacking midfielder
  • Put pressure from above for alphas to have a sufficient number of other alphas as the next line of command. Retaining this team is easier said than done, and without betas the team can collapse.

Of course, if you look at all this from the perspective of the beta, there is an obvious question mark about career prospects. Unless you suddenly change your style (easier said than done), you will never be the alpha, and this puts in place a sort of glass ceiling for your career.

Eating Alone

In the last 2 weeks, about 4 times I had lunch in my office cafeteria. After a small health scare in early October (high HbA1c), I carry my own (self-made) lunch to office every day now (since I can’t reliably find low carb food around). On these days, I took my lunch to the cafeteria and ate along with colleagues, some of whom had brought there own lunches and others bought from the on-site caterer.

This, to me, however, is highly unusual behaviour. First of all, taking lunch to office is highly unusual – something that till recently I considered an “uncle thing to do”. Of course, now that I’m 40, doing “uncle things” is par for the course.

More importantly, eating lunch in the cafeteria is even more unusual behaviour for me. And in the last couple of days, most days I’ve sat there because a colleague who sits near me and brings lunch as well has called me on his way to the cafeteria.

A long time ago, an old friend had recommended to me this book called “never eat alone“. I remember reading it, but don’t remember anything of its contents (and its average goodreads rating of 3.8 suggests my opinion is not isolated). From what I remember, it was about networking and things like that.

However, as far as I am concerned, especially when it comes to lunch on a working day, I actually prefer to eat alone (whether it is at my desk or at a nearby restaurant). Maybe it is because my first “job” (it was actually an internship, but not my first ever internship) was in London, on a trading floor of an investment bank.

On trading floors, lunch at desk is the done thing. In fact, I remember being told off once or twice in my internship for taking too long a lunch break. “You can take your long break after trading hours. For lunch, though, you just go, grab and come and eat at the desk”, I had been told. And despite never again working in an environment like that (barring 4-5 weeks in New York in 2010-11), this habit has struck with me for life.

There are several reasons why I like to eat alone, either at a restaurant or at my desk. Most importantly, there is a time zone mismatch – on most days I either don’t eat breakfast, or would have gone to the gym in the morning. Either ways, by 12-1230, I’m famished and hungry. Most others in India eat lunch only beyond 1.

Then, there is the coordination problem. Yes, if everyone gets lunchboxes (or is okay to but at the cafeteria) and goes to the cafeteria, then it is fine. Else you simply can’t agree on where to go and some of you end up compromising. And a suboptimal lunch means highly suboptimal second half of the day.

Then, there is control over one’s time. Sometimes you can get stuck in long conversations, or hurry up because the other person has an impending meeting. In either case, you can’t enjoy your lunch.

Finally, when you have been having a hectic work day, you want to chill out and relax and do your own thing. It helps to just introspect, and be in control of your own mind and thoughts and distractions while you are eating, rather than losing control of your stimulations to someone else.

Of course it can work the other day as well – cafeteria lunches can mean the possibility of random catchups and gossip and “chit chat” (one reason I’ve done a few of those in the last few weeks), but in the balance, it’s good to have control over your own schedule.

So I don’t really get the point of why people think it’s a shame to eat alone, or thing something is wrong with you if you’re eating alone. I know of people who have foregone meals only because they couldn’t find anyone to go eat with. And I simply don’t understand any of this!

Quiz Time

This morning was Mahaquizzer, KQA’s (used to be) annual national solo written championships. When I had seen the invite a few days back, I had somehow registered in my head that the quiz was between 11:00 am and 12:30 pm.

The website says,

Reporting time for participants will be 10:00 AM

The quiz will be held across all cities from 10:30 am – 12:00 pm

But in my head I had it as 10:30 registration and quiz starting at 11:00. And so around 10, I went in for a long shower. And came out and just for the heck of it, picked my phone to confirm what time the event was. And panicked.

It was 10:55 by the time I reached the venue and started doing the quiz. This meant that rather  than the allotted 90 minutes, I only had 65 minutes to answer the 150 questions. I got into my “speed zone” (I used to be good at solving problems really really fast – that’s how I did very well in CAT etc.) and started working my way through the paper.

It was ~ 11:55 by the time I got done with my first parse of the paper, which meant there was little time for me to revise. And so for a lot of questions I ended up paying far less attention than I should have. And I left some 5-10 questions unattempted (more because I didn’t have a good answer rather than due to lack of time itself).

When the answers were given out presently, I figured I ended up making 67 out of 150. There were a few bad misses. My intuitive thought then was that had I had the full 90 minutes, I could have done better in some 5-10 questions and maybe ended up with 75 out of 150. My misreading of the time had cost me 5-10 points (and I’ll know in a few days how many places in the national rnanking).

Thinking about this, I headed out for lunch with 3 other quizzers (all of whom scored much more than me this morning). Through the lunch, we discussed all the questions. It turned out that for a bunch of questions, some of these people had over-analysed and over-thought, and ended up getting the wrong answer. Because I was doing the quiz in some insane speed mode, I didn’t have the luxury to over-analyse – I had written down the simplest and most intuitive answers I could think of.

Suddenly, by the end of the lunch (by which time we had analysed the full paper), I wasn’t sure any more on how much more I would have got had I had more time. Yes, there were 5-10 questions that would have definitely benefited from my paying more attention. On the other hand, there was another bunch of questions where more attention might have actually been damaging – I would have ended up over-analysing and turned my correct answers into wrong ones.

So I  will never really know how much more (or less) I might have got had I had the full quota of time this morning.

And now that I think of it – it is the case with my blogposts also sometimes. Most of the times I just want to bang it out and publish it, so I get into one zone and start writing. And it will be a stream of thought that will go on to this page, where you will read it .

However, when I try to write more leisurely, I make a right royal mess of it. I over-analyse, over-edit, spend needless time worrying about things I shouldn’t be worrying about, etc. In my own opinion, the best blogposts are those I have written in a “mad speed zone”. Editing can only make my writing worse.

PS: Because I was quizzing today (in the afternoon I attended Asiasweep along with Kodhi. Doing a quiz with Kodhi is always a lot of fun because we end up laughing about random things through the quiz). I deliberately decided to skip my ADHD medication for the day. And that worked out well, since I was able to make all sorts of random connections and work out the answers.

In quizzing, a little bit of hallucination can be a good thing!

Chat GPT and Information Content

For the last week or so I’ve been fooling around with Chat GPT. It’s been a lot of fun, if you can endure the verbosity of its answers. Yesterday, at work, I used it for tech support when some people I was talking to were using too much jargon.

Before I came home from work yesterday, my last conversation was with a couple of recruiters, about a role that I’m hiring for. So when I got home, on a whim, I wondered if I could check out of Chat GPT could write job descriptions for me.

I asked:

write a job description for a senior data scientist at India’s largest logistics company. 4-7 years exp. Needs to have experience in ML, OR and statistics, and be able to work close to business and on ambiguous problems

It answered (pasting in full since the screenshot above is limited):

Job Title: Senior Data Scientist

Company: India’s Largest Logistics Company

Location: India

Experience: 4-7 years

We are seeking an experienced and highly skilled Senior Data Scientist to join our team at India’s largest logistics company. In this role, you will be responsible for using machine learning, operations research, and statistics to drive business insights and decision making.

As a Senior Data Scientist, you will have a deep understanding of data science techniques and technologies, and will be able to apply them to complex and ambiguous problems. You will be able to work closely with business teams to understand their needs and to develop solutions that drive value for the company.

To be successful in this role, you should have at least 4-7 years of experience in data science, and should have a strong background in machine learning, operations research, and statistics. You should be able to work independently and be comfortable working on complex and ambiguous problems.

Responsibilities:

  • Use machine learning, operations research, and statistics to drive business insights and decision making
  • Work closely with business teams to understand their needs and develop solutions
  • Develop and maintain data pipelines and systems
  • Collaborate with other data scientists and cross-functional teams to develop and implement solutions

Qualifications:

  • Bachelor’s or Master’s degree in a quantitative field, such as computer science, statistics, or engineering
  • At least 4-7 years of experience in data science
  • Strong background in machine learning, operations research, and statistics
  • Ability to work independently and on complex and ambiguous problems
  • Excellent communication and collaboration skills
  • Experience with Python, R, or other programming languages is a plus

We offer a competitive salary and benefits package, as well as opportunities for growth and advancement. If you are an experienced data scientist with a passion for driving business insights and decision making, we encourage you to apply.

In the past when I’ve been hiring, I’ve been a bit annoyed by people asking for job descriptions. I’ve largely found them to be fluff and boilerplate, and I’ve tried to get away with a sentence or two. However, due to the insistence of recruiters and candidates alike, I’ve ended up writing elaborate job descriptions. I don’t need to any more.

This post, however, is not about hiring (but yeah – I am hiring, and the above job description is reasonably accurate). It’s about information content in general.

Traditionally, information content has been measured in bits. A bit is the amount of information contained in an equi-probable binary event.

Sometimes when we find that someone is too verbose and using too many words when fewer would suffice, we say that their bit rate is low. We also use “low bit rate” to describe people such as former Prime Minister Atal Behari Vajpayee, who would speak incredibly slowly.

However, beyond the bit, which is a fairly technical concept, it has been difficult to quantify information content. Sometimes you read an article or a story and find that there is nothing much to it. But given the natural language, and the context of various words, it is impossible to quantify the information content.

Now, with Chat GPT, maybe it becomes a bit easier (though one would need a “reverse chat GPT algo”, to find the set of prompts required for Chat GPT to churn out a particular essay). Above, for example, I’ve shown how much fluff there generally is to the average job description – a fairly short prompt generated this longish description that is fairly accurate.

So you can define the information content of a piece or essay in terms of the number of words in the minimum set of prompts required for Chat GPT (or something like it) to come up with it. If you are a boring stereotypical writer, the set of prompts required will be lower. If you are highly idiosyncratic, then you will need to give a larger number of prompts for Chat GPT to write like you. You know where I’m going.

This evening, in office, a colleague commented that now it will be rather easy to generate marketing material. “Even blogs might become dead, since with a few prompts you can get that content”, he said (it can be a legit service to build off the Chat GPT API to take a tweet and convert it into an essay).

I didn’t tell him then but I have decided to take it up as a challenge. I consider myself to be a fairly idiosyncratic writer, which means I THINK there is a fair bit of information content in what I write, and so this blog will stay relevant. Let’s see how it goes.

PS: I still want to train a GAN on my blog (well over a million words, at last count) and see how it goes. If you know of any tools I can use for this, let me know!

 

Dhoni and Japan

Back in MS Dhoni’s heyday, CSK fans would rave about his strategy that they called as “taking it deep”. The idea was that while chasing  a target, Dhoni would initially bat steadily, getting sort of close but increasing the required run rate. And then when it seemed to be getting out of hand, he would start belting, taking the bowlers by surprise and his team to victory.

This happened many times to be recognised by fans as a consistent strategy. Initially it didn’t make sense to me – why was it that he would purposely decrease the average chances of his team’s victory so that he could take them to a heroic chase?

But then, thinking about it, the strategy seems fair – he would never do this in a comfortable chase (where the chase was “in the money”). This would happen only in steep (out of the money) chases. And his idea of “taking it deep” was in terms of increasing the volatility.

Everyone knows that when your option is out of the money, volatility is good for you. Which means an increase in volatility will increase the value of the option.

And that is exactly what Dhoni would do. Keep wickets and let the required rate increase, which would basically increase volatility. And then rely on “mental strength” and “functioning under pressure” to win. It didn’t always succeed, of course (and that it didn’t always fail meant Dhoni wouldn’t come off badly when it failed). However, it was a very good gamble.

We see this kind of a gamble often in chess as well. When a player has a slightly inferior position, he/she decides to increase chances by “mixing it up a bit”. Usually that involves a piece or an exchange sacrifice, in the hope of complicating the position, or creating an imbalance. This, once again, increases volatility, which means increases the chances for the player with the slightly inferior position.

And in the ongoing World Cup, we have seen Japan follow this kind of strategy in football as well. It worked well in games against Germany and Spain, which were a priori better teams than Japan.

In both games, Japan started with a conservative lineup, hoping to keep it tight in the first half and go into half time either level or only one goal behind. And then at half time, they would bring on a couple of fast and tricky players – Ritsu Doan and Kaoru Mitoma. Basically increasing the volatility against an already tired opposition.

And then these high volatility players would do their bit, and as it happened in both games, Japan came back from 0-1 at half time to win 2-1. Basically, having “taken the game deep”, they would go helter skelter (I was conscious to not say “hara kiri” here, since it wasn’t really suicidal). And hit the opposition quickly, and on the break.

Surprisingly, they didn’t follow the same strategy against Croatia, in the pre-quarterfinal, where Doan started the game, and Mitoma came on only in the 64th minute. Maybe they reasoned that Croatia weren’t that much better than them, and so the option wasn’t out of the money enough to increase volatility through the game. As it happened, the game went to penalties (basically deeper than Japan’s usual strategy) where Croatia prevailed.

The difference between Dhoni and Japan is that in Japan’s case, the players who increase the volatility and those who then take advantage are different. In Dhoni’s case, he performs both functions – he first bats steadily to increase vol, and then goes bonkers himself!

Portfolio with a dominant stock

Last night, I read this post I had written shortly before I turned 29. I had embarked on a “Project thirty“, a year on project I had sponsored for myself. The plan was to do everything I had wanted to do but had never been able to, and the only condition that I had put for myself had been that I wouldn’t take up a full time job until the end of the “project”.

The project, largely speaking, was successful. It laid the bed for what was a fantastic decade of “portfolio life”, as I did several things with my time (though most of my income came from one of those things I did). I built a career as a freelance analytics ad data science consultant (which is how I made most of my money), wrote a newspaper column, became an adjunct professor, involved myself in public policy research and wrote a book.

In the middle of all this, i made time for myself to go spend a semester with my wife as she completed her MBA in Barcelona, and then followed her to London when she got a job there. It was all wonderful stuff.

And then, around the time I turned 38, partly fuelled by the pandemic, I brought my portfolio life to a close. Around then, my wife asked me what my “project forty” would be. “To stay in my job”, I had told her then. And now, that has been successfully completed.  As a bonus, according per my calculations, this is the job I would’ve stayed the longest ever in!

In any case, recently, my wife asked me the usual question once again. About what my “project” for my early forties is. She probably first asked me this a month ago or something, and I don’t think I had an answer then. And then last week, after we came back from our vacation to Tanzania, I spent 2 days at home just chilling.

My new personal computer (a 14″ M1) had arrived by then, and I spent the time setting it up, reading, writing, being on twitter and exploring cool new technologies such as Stable Diffusion and Chat GPT. It was absolutely enjoyable, those 2 days. It felt great having a non-work computer of my own (my previous one had conked 6 months back, though it had hardly been operational for a year before that). Those two days were spent like my project thirty days were. They were wonderful.

And so, by the time the tens place of my age number got its increment, I had the answer ready to give to my wife. On what my plan for my early forties is. It is “portfolio with a dominant stock”.

I really enjoyed the portfolio life I lived through most of my thirties. And want to get to a portfolio again. On the other hand, I’m in a job that I’ve settled fairly well into. And during the recent holiday to Tanzania, I also realised that it feels good to be able to spend on holidays like that without really thinking a hundred times.

So what is the solution? It is basically about having a portfolio with a “dominant stock” – the dominant stock being my job. My objective for my early forties is to continue having a full time job, but also have an interesting life on the side.

For now, what the interesting sides will be – I don’t have that much of an idea, and am likely to go back to things close to my old ones.

I want to travel a lot more.
I’m restarting my newsletter soon.
I want to start teaching once again. Part time only. Need to wing this somehow, somewhere.
Meet people regularly. Breakfasts. Lunches. Dinners. Drinkses.
I want to start playing a card game competitively. Either resume bridge or (more likely) learn something new such as poker.
I have no intention of writing another book (yet). Even if I do, it is likely to be via Substack.

It’s not going to be easy of course. Last 2 years, I’ve largely focussed on my job and family, and done little else (apart from this blog and lifting). I will need to prioritise properly, and manage my time well (something I’ve never been good at). But there is no harm putting out this goal, and in public, in the hope that having put this out will help me do better at it.

Let’s see where this goes! And any ideas are welcome.

JEE and academia

This is (hopefully) a quick post I’m dashing off from the sidelines of the Basavanagudi aquatic Center where I’ve brought my daughter for her weekly swimming lessons

I write this as I’m reading Eric Hoel’s post on why he is leaving academia. Basically he talks about all the “extra curricular activities” that an academic nowadays needs to do. Reviewing journals, being on student bodies and the like.

The other reason he quotes is about how restrictive academia is – again because he is being evaluated on multiple dimensions, rather than simply on the quality of his research and teaching.

Given all of this, following four years as an assistant professor at tufts, he has chosen to quit academia full time and become a writer of newsletters. and he writes that “being an academic is not so easy any more”.

I was reminded of an old post I’d written about Indian and American universities. American universities admit students based on “a holistic set of factors”. So your test scores are important but so are your sports and charity work and 10 different kinds of extra curricular activities and all that.

Indian universities (at least the ones I went to) are far simpler – they admit solely on the basis of test scores.

After reading some articles on how the US admission process was producing highly homogeneous classrooms at universities, id written a few years back on how the Indian system rocked – because admissions were based on a single criterion, there was tremendous diversity jn the classrooms on all other criteria.

Now based on Hoel’s post I’m wondering if the same is true of teachers as well – the more the dimensions on which we evaluate professors for recruitment and tenureship, the more homogeneous the professorial class gets. Instead if we were to evaluate professors on narrowly defined conventional criteria (teaching and research) we’ll get a far more richer and diverse professors body.

This, however, is easier said than done. Quality of research is usually evaluated based on the quality and quantity of papers, and papers necessarily go through a peer review process.

And if your peers are all those who have succeeded in the “selected by holistic criteria” game, then you will have to conform to some of their biases to get good papers published.

All this said, I’m hopeful that in the next decade or so we will have a bunch of new and privately funded universities which Yale universities back tk what they used to be – centres of research and teaching , with professors selected on their credentials on these axes only, and a diverse body of students selected hopefully on a a small number of axes (such as test scores).

More on CRM

On Friday afternoon, I got a call on my phone. It was  “+91 9818… ” number, and my first instinct was it was someone at work (my company is headquartered in Gurgaon), and I mentally prepared a “don’t you know I’m on vacation? can you call me on Monday instead” as I picked the call.

It turned out to be Baninder Singh, founder of Savorworks Coffee. I had placed an order on his website on Thursday, and I half expected him to tell me that some of the things I had ordered were out of stock.

“Karthik, for your order of the Pi?anas, you have asked for an Aeropress grind. Are you sure of this? I’m asking you because you usually order whole beans”, Baninder said. This was a remarkably pertinent observation, and an appropriate question from a seller. I confirmed to him that this was indeed deliberate (this smaller package is to take to office along with my Aeropress Go), and thanked him for asking. He went on to point out that one of the other coffees I had ordered had very limited stocks, and I should consider stocking up on it.

Some people might find this creepy (that the seller knows exactly what you order, and notices changes in your order), but from a more conventional retail perspective, this is brilliant. It is great that the seller has accurate information on your profile, and is able to detect any anomalies and alert you before something goes wrong.

Now, Savorworks is a small business (a Delhi based independent roastery), and having ordered from them at least a dozen times, I guess I’m one of their more regular customers. So it’s easy for them to keep track and take care of me.

It is similar with small “mom-and-pop” stores. Limited and high-repeat clientele means it’s easy for them to keep track of them and look after them. The challenge, though, is how do you scale it? Now, I’m by no means the only person thinking about this problem. Thousands of business people and data scientists and retailers and technology people and what not have pondered this question for over a decade now. Yet, what you find is that at scale you are simply unable to provide the sort of service you can at small scale.

In theory it should be possible for an AI to profile customers based on their purchases, adds to carts, etc. and then provide them customised experiences. I’m sure tonnes of companies are already trying to do this. However, based on my experience I don’t think anyone is doing this well.

I might sound like a broken record here, but my sense is that this is because the people who are building the algos are not the ones who are thinking of solving the business problems. The algos exist. In theory, if I look at stuff like stable diffusion or Chat GPT (both of which I’ve been playing around with extensively in the last 2 days), algorithms for stuff like customer profiling shouldn’t be THAT hard. The issue, I suspect, is that people have not been asking the right questions of the algos.

On one hand, you could have business people looking at patterns they have divined themselves and then giving precise instructions to the data scientists on how to detect them – and the detection of these patterns would have been hard coded. On the other, the data scientists would have had a free hand and would have done some unsupervised stuff without much business context. And both approaches lead to easily predictable algos that aren’t particularly intelligent.

Now I’m thinking of this as a “dollar bill on the road” kind of a problem. My instinct tells me that “solution exists”, but my other instinct tells that “if a solution existed someone would have found it given how many companies are working on this kind of thing for so long”.

The other issue with such algos it that the deeper you get in prediction the harder it is. At the cohort (of hundreds of users) level, it should not be hard to profile. However, at the personal user level (at which the results of the algos are seen by customers) it is much harder to get right. So maybe there are good solutions but we haven’t yet seen it.

Maybe at some point in the near future, I’ll take another stab at solving this kind of problem. Until then, you have human intelligence and random algos.

 

Hot hands in safaris

We entered Serengeti around 12:30 pm on Saturday, having stopped briefly at the entrance gate to have lunch packed for us by our hotel in Karatu. Around 1 pm, our guide asked us to put the roof up, so we could stand and get a 360 degree view. “This is the cheetah region”, he told us.

For the next hour or so we just kept going round and round. We went off the main path towards some rocks. Some other jeeps had done the same. None of us had any luck.

By 2 pm we had seen nothing. Absolutely nothing. For a place like Serengeti, that takes some talent, given the overall density of animals there. We hadn’t even seen a zebra, or a wildebeest. Maybe a few gazelles (I could never figure out how to tell between Thomson’s and Grant’s through the trip, despite seeing tonnes of both on the trip). “This is not even the level of what we saw in Tarangire yesterday”, we were thinking.

And then things started to happen. First there was a herd of zebras. On Friday we had missed an opportunity to take a video of a zebra crossing the road (literally a “zebra crossing”, get it?). And now we had a whole herd of zebras crossing the road in front of us. This time we didn’t miss the opportunity (though there was no Spice Telecom).

Zebra crossing in Serengeti

And then we saw a herd of buffaloes. And then a bunch of hippos in a pool. We asked our guide to take us closer to them, and he said “oh don’t worry about hippos. Tomorrow I’ll take you to a hippo pool with over a fifty hippos”. And sped off in the opposite direction. There was a pack of lions fallen asleep under a tree, with the carcass of a wildebeest they had just eaten next to them (I posted that photo the other day).

This was around 3 pm. By 4 pm, we had seen a large herd of wildebeest and zebra on their great annual migration. And then seen a cheetah sitting on a termite hill, also watching the migration. And yet another pool with some 50 hippos lazing in it. It was absolutely surreal.

It was as if we had had a “hot hand” for an hour, with tremendous sightings after a rather barren first half of the afternoon. We were to have another similar “hot hand” on Monday morning, on our way out from the park. Again in the course of half an hour (when we were driving rather fast, with the roof down, trying to exit the park ASAP) we saw a massive herd of elephants, a mother and baby cheetah, a pack of lions and a single massive male lion right next to the road.

If you are the sort who sees lots of patterns, it is possibly easy to conclude that “hot hands” are a thing in wildlife. That when you have one good sighting, it is likely to be followed by a few other good sightings. However, based on a total of four days of safaris on this trip, I strongly believe that here at least hot hands are a fallacy.

But first a digression. The issue of “hot hands” has been a long-standing one in basketball. First some statisticians found that the hot hand truly exists – that NBA (or was it NCAA?) players who have made a few baskets in succession are more likely to score off their next shot. Then, other statisticians found some holes in the argument and said that it was simply a statistical oddity. And yet again (if i remember correctly) yet another group of statisticians showed that with careful analysis, the hot hand actually exists. This was rationalised as “when someone has scored a few consecutive baskets, their confidence is higher, which improves the chances of scoring off the next attempt”.

So if a hot hand exists, it is more to do with the competence and confidence of the person who is executing the activity.

In wildlife, though, it doesn’t work that way. While it is up to us (and our guides) to spot the animals, that you have spotted something doesn’t make it more likely to spot something else (in fact, false positives in spotting can go up when you are feeling overconfident). Possibly the only correlation between consecutive spottings is that guides of various jeeps are in constant conversation on the radio, and news of spottings get shared. So if a bunch of jeeps have independently spotted stuff close to each other, all the jeeps will get to see all these stuffs (no pun intended), getting a “hot hand”.

That apart, there is no statistical reason in a safari to have a “hot hand”. 

Rather, what is more likely is selection bias. When we see a bunch of spottings close to one another, we think it is because we have a “hot hand”. However, when we are seeing animals only sporadically (like we did on Sunday, not counting the zillions of wildebeest and zebra migrating), we don’t really register that we are “not having a hot hand”.

It is as if you are playing a game of coin tosses, where you register all the heads but simply ignore the tails, and theorise about clumping of heads. When a low probability event happens (multiple sightings in an hour, for example), it registers better in our heads, and we can sometimes tend to overrepresent them in our memories. The higher probability (or “lower information content”) events we simply ignore! And so we assume that events are more impactful on average than they actually are.

Ok now i’m off on a ramble (this took a while to write – including making that gif among other things) – but Nassim Taleb talks about it this in one of his early Incerto books (FBR or Black Swan – that if you only go by newspaper reports, you are likely to think that lower average crime cities are more violent, since more crimes get reported there).

And going off on yet another ramble – hot hands can be a thing where the element of luck is relatively small. Wildlife spotting has a huge amount of luck involved, and so even with the best of skills there is only so much of a hot hand you can produce.

So yeah – there is no hot hand in wildlife safaris.