I’ve forgotten which stage of lockdown or “unlock” e-commerce for “non-essential goods” reopened, but among the first things we ordered was a Scrabble board. It was an impulse decision. We were on Amazon ordering puzzles for the daughter, and she had just about started putting together “sounds” to make words, so we thought “scrabble tiles might be useful for her to make words with”.
The thing duly arrived two or three days later. The wife had never played Scrabble before, so on the day it arrived I taught her the rules of the game. We play with the Sowpods dictionary open, so we can check words that hte opponent challenges. Our “scrabble vocabulary” has surely improved since the time we started playing (“Qi” is a lifesaver, btw).
I had insisted on ordering the “official Scrabble board” sold by Mattel. The board is excellent. The tiles are excellent. The bag in which the tiles are stored is also excellent. The only problem is that there was no “scoreboard” that arrived in the set.
On the first day we played (when I taught the wife the rules, and she ended up beating me – I’m so horrible at the game), we used a piece of paper to maintain scores. The next day, we decided to score using an Excel sheet. Since then, we’ve continued to use Excel. The scoring format looks somewhat like this.
So each worksheet contains a single day’s play. Initially after we got the board, we played pretty much every day. Sometimes multiple times a day (you might notice that we played 4 games on 3rd June). So far, we’ve played 31 games. I’ve won 19, Priyanka has won 11 and one ended in a tie.
In any case, scoring on Excel has provided an additional advantage – analytics!! I have an R script that I run after every game, that parses the Excel sheet and does some basic analytics on how we play.
For example, on each turn, I make an average of 16.8 points, while Priyanka makes 14.6. Our score distribution makes for interesting viewing. Basically, she follows a “long tail strategy”. Most of the time, she is content with making simple words, but occasionally she produces a blockbuster.
I won’t put a graph here – it’s not clear enough. This table shows how many times we’ve each made more than a particular threshold (in a single turn). The figures are cumulative
Threshold
Karthik
Priyanka
30
50
44
40
12
17
50
5
10
60
3
5
70
2
2
80
0
1
90
0
1
100
0
1
Notice that while I’ve made many more 30+ scores than her, she’s made many more 40+ scores than me. Beyond that, she has crossed every threshold at least as many times as me.
Another piece of analysis is the “score multiple”. This is a measure of “how well we use our letters”. For example, if I start place the word “tiger” on a double word score (and no double or triple letter score), I get 12 points. The points total on the tiles is 6, giving me a multiple of 2.
Over the games I have found that I have a multiple of 1.75, while she has a multiple of 1.70. So I “utilise” the tiles that I have (and the ones on the board) a wee bit “better” than her, though she often accuses me of “over optimising”.
It’s been fun so far. There was a period of time when we were addicted to the game, and we still turn to it when one of us is in a “work rut”. And thanks to maintaining scores on Excel, the analytics after is also fun.
I’m pretty sure you’re spending the lockdown playing some board game as well. I strongly urge you to use Excel (or equivalent) to maintain scores. The analytics provides a very strong collateral benefit.
Through a combination of luck and competence, my home state of Karnataka has handled the Covid-19 crisis rather well. While the total number of cases detected in the state edged past 2000 recently, the number of locally transmitted cases detected each day has hovered in the 20-25 range.
It might make news that Karnataka has crossed 2000 covid-19 cases (cumulatively).
However, the state has only 20-25 locally transmitted cases per day (increasing at a very slow rate)
Perhaps the low case volume means that Karnataka is able to give out data at a level that few others states in India are providing. For each case, the rationale behind why the patient was tested (which is usually the source where they caught the disease) is given. This data comes out in two daily updates through the @dhfwka twitter handle.
There was this research that came out recently that showed that the spread of covid-19 follows a classic power law, with a low value of “alpha”. Basically, most infected people don’t infect anyone else. But there are a handful of infected people who infect lots of others.
The Karnataka data, put out by @dhfwka and meticulously collected and organised by the folks at covid19india.org (they frequently drive me mad by suddenly changing the API or moving data into a new file, but overall they’ve been doing stellar work), has sufficient information to see if this sort of power law holds.
For every patient who was tested thanks to being a contact of an already infected patient, the “notes” field of the data contains the latter patient’s ID. This way, we are able to build a sort of graph on who got the disease from whom (some people got the disease “from a containment zone”, or out of state, and they are all ignored in this analysis).
From this graph, we can approximate how many people each infected person transmitted the infection to. Here are the “top” people in Karnataka who transmitted the disease to most people.
Patient 653, a 34 year-old male from Karnataka, who got infected from patient 420, passed on the disease to 45 others. Patient 419 passed it on to 34 others. And so on.
Overall in Karnataka, based on the data from covid19india.org as of tonight, there have been 732 cases where a the source (person) of infection has been clearly identified. These 732 cases have been transmitted by 205 people. Just two of the 205 (less than 1%) are responsible for 79 people (11% of all cases where transmitter has been identified) getting infected.
The top 10 “spreaders” in Karnataka are responsible for infecting 260 people, or 36% of all cases where transmission is known. The top 20 spreaders in the state (10% of all spreaders) are responsible for 48% of all cases. The top 41 spreaders (20% of all spreaders) are responsible for 61% of all transmitted cases.
Now you might think this is not as steep as the “well-known” Pareto distribution (80-20 distribution), except that here we are only considering 20% of all “spreaders”. Our analysis ignores the 1000 odd people who were found to have the disease at least one week ago, and none of whose contacts have been found to have the disease.
I admit this graph is a little difficult to understand, but basically I’ve ordered people found for covid-19 in Karnataka by number of people they’ve passed on the infection to, and graphed how many people cumulatively they’ve infected. It is a very clear pareto curve.
The exact exponent of the power law depends on what you take as the denominator (number of people who could have infected others, having themselves been infected), but the shape of the curve is not in question.
Essentially the Karnataka validates some research that’s recently come out – most of the disease spread stems from a handful of super spreaders. A very large proportion of people who are infected don’t pass it on to any of their contacts.
If you think you’re a data visualisation junkie, it’s likely that you’ve read Edward Tufte’s Visual Display Of Quantitative Information. If you are only a casual observer of the topic, you are likely to have come across these gifs that show you how to clean up a bar graph and a data table.
And if you are a real geek when it comes to visualisation, and you are the sort of person who likes long-form articles about the information technology industry, I’m sure you’ve come across Eugene Wei’s massive essay on “remove the legend to become one“.
The idea in the last one is that when you have something like a line graph, a legend telling you which line represents what can be distracting, especially if you have too many lines. You need to constantly move your head back and forth between the chart and the table as you try to interpret it. So, Wei says, in order to “become a legend” (by presenting information that is easily consumable), you need to remove the legend.
My equivalent of that for bar graphs is to put data labels directly on the bar, rather than having the reader keep looking at a scale (the above gif with bar graphs also does this). It makes for easier reading, and by definition, the bar graph conveys the information on the relative sizes of the different data points as well.
There is one problem, though, especially when you’re drawing what my daughter calls “sleeping bar graphs” (horizontal) – where do you really put the text so that it is easily visible? This becomes especially important if you’re using a package like R ggplot where you have control over where to place the text, what size to use and so on.
The basic question is – do you place the label inside or outside the bar? I was grappling with this question yesterday while making some client chart. When I placed the labels inside the bar, I found that some of the labels couldn’t be displayed in full when the bars were too short. And since these were bars that were being generated programmatically, I had no clue beforehand how long the bars would be.
So I decided to put all the labels outside. This presented a different problem – with the long bars. The graph would automatically get cut off a little after the longest bar ended, so if you placed the text outside, then the labels on the longest bar couldn’t be seen! Again the graphs have to come out programmatically so when you’re making them you don’t know what the length of the longest bar will be.
I finally settled on this middle ground – if the bar is at least half as long as the longest bar in the chart set, then you put the label inside the bar. If the bar is shorter than half the longest bar, then you put the label outside the bar. And then, the text inside the bar is right-justified (so it ends just inside the end of the bar), and the text outside the bar is left-justified (so it starts exactly where the bar ends). And ggplot gives you enough flexibility to decide the justification (‘hjust’) and colour of the text (I keep it white if it is inside the bar, black if outside), that the whole thing can be done programmatically, while producing nice and easy-to-understand bar graphs with nice labels.
Obviously I can’t share my client charts here, but here is one I made for the doubling days for covid-19 cases by district in India. I mean it’s not exactly what I said here, but comes close (the manual element here is a bit more).
In fact, there is wide divergence within states as well Within states, we see high divergence in doubling rates across districts pic.twitter.com/jIU9CmitRx
There has been a massive jump in the number of covid-19 positive cases in Karnataka over the last couple of days. Today, there were 44 new cases discovered, and yesterday there were 36. This is a big jump from the average of about 15 cases per day in the preceding 4-5 days.
The good news is that not all of this is new infection. A lot of cases that have come out today are clusters of people who have collectively tested positive. However, there is one bit from yesterday’s cases (again a bunch of clusters) that stands out.
I guess by now everyone knows what “travelled from Delhi” is a euphemism for. The reason they are interesting to me is that they are based on a “repeat test”. In other words, all these people had tested negative the first time they were tested, and then they were tested again yesterday and found positive.
Why did they need a repeat test? That’s because the sensitivity of the Covid-19 test is rather low. Out of every 100 infected people who take the test, only about 70 are found positive (on average) by the test. That also depends upon when the sample is taken. From the abstract of this paper:
Over the four days of infection prior to the typical time of symptom onset (day 5) the probability of a false negative test in an infected individual falls from 100% on day one (95% CI 69-100%) to 61% on day four (95% CI 18-98%), though there is considerable uncertainty in these numbers. On the day of symptom onset, the median false negative rate was 39% (95% CI 16-77%). This decreased to 26% (95% CI 18-34%) on day 8 (3 days after symptom onset), then began to rise again, from 27% (95% CI 20-34%) on day 9 to 61% (95% CI 54-67%) on day 21.
About one in three (depending upon when you draw the sample) infected people who have the disease are found by the test to be uninfected. Maybe I should state it again. If you test a covid-19 positive person for covid-19, there is almost a one-third chance that she will be found negative.
The good news (at the face of it) is that the test has “high specificity” of about 97-98% (this is from conversations I’ve had with people in the know. I’m unable to find links to corroborate this), or a false positive rate of 2-3%. That seems rather accurate, except that when the “prior probability” of having the disease is low, even this specificity is not good enough.
Let’s assume that a million Indians are covid-19 positive (the official numbers as of today are a little more than one-hundredth of that number). With one and a third billion people, that represents 0.075% of the population.
Let’s say we were to start “random testing” (as a number of commentators are advocating), and were to pull a random person off the street to test for Covid-19. The “prior” (before testing) likelihood she has Covid-19 is 0.075% (assume we don’t know anything more about her to change this assumption).
If we were to take 20000 such people, 15 of them will have the disease. The other 19985 don’t. Let’s test all 20000 of them.
Of the 15 who have the disease, the test returns “positive” for 10.5 (70% accuracy, round up to 11). Of the 19985 who don’t have the disease, the test returns “positive” for 400 of them (let’s assume a specificity of 98% (or a false positive rate of 2%), placing more faith in the test)! In other words, if there were a million Covid-19 positive people in India, and a random Indian were to take the test and test positive, the likelihood she actually has the disease is 11/411 = 2.6%.
If there were 10 million covid-19 positive people in India (no harm in supposing), then the “base rate” would be .75%. So out of our sample of 20000, 150 would have the disease. Again testing all 20000, 105 of the 150 who have the disease would test positive. 397 of the 19850 who don’t have the disease will test positive. In other words, if there were ten million Covid-19 positive people in India, and a random Indian were to take the test and test positive, the likelihood she actually has the disease is 105/(397+105) = 21%.
If there were ten million Covid-19 positive people in India, only one-fifth of the people who tested positive in a random test would actually have the disease.
Take a sip of water (ok I’m reading The Ken’s Beyond The First Order too much nowadays, it seems).
This is all standard maths stuff, and any self-respecting book or course on probability and Bayes’s Theorem will have at least a reference to AIDS or cancer testing. The story goes that this was a big deal in the 1990s when some people suggested that the AIDS test be used widely. Then, once this problem of false positives and posterior probabilities was pointed out, the strategy of only testing “high risk cases” got accepted.
And with a “low incidence” disease like covid-19, effective testing means you test people with a high prior probability. In India, that has meant testing people who travelled abroad, people who have come in contact with other known infected, healthcare workers, people who attended the Tablighi Jamaat conference in Delhi, and so on.
The advantage with testing people who already have a reasonable chance of having the disease is that once the test returns positive, you can be pretty sure they actually have the disease. It is more effective and efficient. Testing people with a “high prior probability of disease” is not discriminatory, or a “sampling bias” as some commentators alleged. It is prudent statistical practice.
Again, as I found to my own detriment with my tweetstorm on this topic the other day, people are bound to see politics and ascribe political motives to everything nowadays. In that sense, a lot of the commentary is not surprising. It’s also not surprising that when “one wing” heavily retweeted my article, “the other wing” made efforts to find holes in my argument (which, again, is textbook math).
One possibly apolitical criticism of my tweetstorm was that “the purpose of random testing is not to find out who is positive. It is to find out what proportion of the population has the disease”. The cost of this (apart from the monetary cost of actually testing) are threefold. Firstly, a large number of uninfected people will get hospitalised in covid-specific hospitals, clogging hospital capacity and increasing the chances that they get infected while in hospital.
Secondly, getting a truly random sample in this case is tricky, and possibly unethical. When you have limited testing capacity, you would be inclined (possibly morally, even) to use it on people who already have a high prior probability.
Finally, when the incidence is small, we need a really large sample to find out the true range.
Let’s say 1 in 1000 Indians have the disease (or about 1.35 million people). Using the Chi Square test of proportions, our estimate of the incidence of the disease varies significantly on how many people are tested.
If we test a 1000 people and find 1 positive, the true incidence of the disease (95% confidence interval) could be anywhere from 0.01% to 0.65%.
If we test 10000 people and find 10 positive, the true incidence of the disease could be anywhere between 0.05% and 0.2%.
Only if we test 100000 people (a truly massive random sample) and find 100 positive, then the true incidence lies between 0.08% and 0.12%, an acceptable range.
I admit that we may not be testing enough. A simple rule of thumb is that anyone with more than a 5% prior probability of having the disease needs to be tested. How we determine this prior probability is again dependent on some rules of thumb.
I’ll close by saying that we should NOT be doing random testing. That would be unethical on multiple counts.
I must warn that this is a super long post. Also I wonder if I should put this on medium in order to get more footage.
Most models of disease spread use what is known as a “SIR” framework. This Numberphile video gives a good primer into this framework.
The problem with the framework is that it’s too simplistic. It depends primarily on one parameter “R0”, which is the average number of people that each infected patient infects. When R0 is high, each patient infects a number of other people, and the disease spreads fast. With a low R0, the disease spreads slow. It was the SIR model that was used to produce all those “flatten the curve” pictures that we were bombarded with a week or two back.
There is a second parameter as well – the recovery or removal rate. Some diseases are so lethal that they have a high removal rate (eg. Ebola), and this puts a natural limit on how much the disease can spread, since infected people die before they can infect too many people.
In any case, such modelling is great for academic studies, and post-facto analyses where R0 can be estimated. As we are currently in the middle of an epidemic, this kind of simplistic modelling can’t take us far. Nobody has a clue yet on what the R0 for covid-19 is. Nobody knows what proportion of total cases are asymptomatic. Nobody knows the mortality rate.
And things are changing well-at-a-faster-rate. Governments are imposing distancing of various forms. First offices were shut down. Then shops were shut down. Now everything is shut down, and many of us have been asked to step out “only to get necessities”. And in such dynamic and fast-changing environments, a simplistic model such as the SIR can only take us so far, and uncertainty in estimating R0 means it can be pretty much useless as well.
In this context, I thought I’ll simulate a few real-life situations, and try to model the spread of the disease in these situations. This can give us an insight into what kind of services are more dangerous than others, and how we could potentially “get back to life” after going through an initial period of lockdown.
The basic assumption I’ve made is that the longer you spend with an infected person, the greater the chance of getting infected yourself. This is not an unreasonable assumption because the spread happens through activities such as sneezing, touching, inadvertently dropping droplets of your saliva on to the other person, and so on, each of which is more likely the longer the time you spend with someone.
Some basic modelling revealed that this can be modelled as a sort of negative exponential curve that looks like this.
T is the number of hours you spend with the other person. is a parameter of transmission – the higher it is, the more likely the disease with transmit (holding the amount of time spent together constant).
The function looks like this:
We have no clue what is, but I’ll make an educated guess based on some limited data I’ve seen. I’ll take a conservative estimate and say that if an uninfected person spends 24 hours with an infected person, the former has a 50% chance of getting the disease from the latter.
This gives the value of to be 0.02888 per hour. We will now use this to model various scenarios.
Delivery
This is the simplest model I built. There is one shop, and N customers. Customers come one at a time and spend a fixed amount of time (1 or 2 or 5 minutes) at the shop, which has one shopkeeper. Initially, a proportion of the population is infected, and we assume that the shopkeeper is uninfected.
And then we model the transmission – based on our , for a two minute interaction, the probability of transmission is %.
In hindsight, I realised that this kind of a set up better describes “delivery” than a shop. With a 0.1% probability the delivery person gets infected from an infected customer during a delivery. With the same probability an infected delivery person infects a customer. The only way the disease can spread through this “shop” is for the shopkeeper / delivery person to be uninfected.
How does it play out? I simulated 10000 paths where one guy delivers to 1000 homes (maybe over the course of a week? that doesn’t matter as long as the overall infected rate in the population otherwise is constant), and spends exactly two minutes at each delivery, which is made to a single person. Let’s take a few cases, with different base cases of incidence of the disease – 0.1%, 0.2%, 0.5%, 1%, 2%, 5%, 10%, 20% and 50%.
The number of NEW people infected in each case is graphed here (we don’t care how many got the disease otherwise. We’re modelling how many got it from our “shop”). The right side graph excludes the case of zero new infections, just to show you the scale of the problem.
Notice this – even when 50% of the population is infected, as long as the shopkeeper or delivery person is not initially infected, the chances of additional infections through 2-minute delivery are MINUSCULE. A strong case for policy-makers to enable delivery of all kinds, essential or inessential.
2. SHOP
Now, let’s complicate matters a little bit. Instead of a delivery person going to each home, let’s assume a shop. Multiple people can be in the shop at the same time, and there can be more than one shopkeeper.
Let’s use the assumptions of standard queueing theory, and assume that the inter-arrival time for customers is guided by an Exponential distribution, and the time they spend in the shop is also guided by an Exponential distribution.
At the time when customers are in the shop, any infected customer (or shopkeeper) inside can infect any other customer or shopkeeper. So if you spend 2 minutes in a shop where there is 1 infected person, our calculation above tells us that you have a 0.1% chance of being infected yourself. If there are 10 infected people in the shop and you spend 2 minutes there, this is akin to spending 20 minutes with one infected person, and you have a 1% chance of getting infected.
Let’s consider two or three scenarios here. First is the “normal” case where one customer arrives every 5 minutes, and each customer spends 10 minutes in the shop (note that the shop can “serve” multiple customers simultaneously, so the queue doesn’t blow up here). Again let’s take a total of 1000 customers (assume a 24/7 open shop), and one shopkeeper.
Notice that there is significant transmission of infection here, even though we started with 5% of the population being infected. On average, another 3% of the population gets infected! Open supermarkets with usual crowd can result in significant transmission.
Does keeping the shop open with some sort of social distancing (let’s see only one-fourth as many people arrive) work? So people arrive with an average gap of 20 minutes, and still spend 10 minutes in the shop. There are still 10 shopkeepers. What does it look like when we start with 5% of the people being infected?
The graph is pretty much identical so I’m not bothering to put that here!
3. Office
This scenario simulates for N people who are working together for a certain number of hours. We assume that exactly one person is infected at the beginning of the meeting. We also assume that once a person is infected, she can start infecting others in the very next minute (with our transmission probability).
How does the infection grow in this case? This is an easier simulation than the earlier one so we can run 10000 Monte Carlo paths. Let’s say we have a “meeting” with 40 people (could just be 40 people working in a small room) which lasts 4 hours. If we start with one infected person, this is how the number of infected grows over the 4 hours.
The spread is massive! When you have a large bunch of people in a small closed space over a significant period of time, the infection spreads rapidly among them. Even if you take a 10 person meeting over an hour, one infected person at the start can result in an average of 0.3 other people being infected by the end of the meeting.
10 persons meeting over 8 hours (a small office) with one initially infected means 3.5 others (on average) being infected by the end of the day.
Offices are dangerous places for the infection to spread. Even after the lockdown is lifted, some sort of work from home regulations need to be in place until the infection has been fully brought under control.
4. Conferences
This is another form of “meeting”, except that at each point in time, people don’t engage with the whole room, but only a handful of others. These groups form at random, changing every minute, and infection can spread only within a particular group.
Let’s take a 100 person conference with 1 initially infected person. Let’s assume it lasts 8 hours. Depending upon how many people come together at a time, the spread of the infection rapidly changes, as can be seen in the graph below.
If people talk two at a time, there’s a 63% probability that the infection doesn’t spread at all. If they talk 5 at a time, this probability is cut by half. And if people congregate 10 at a time, there’s only a 11% chance that by the end of the day the infection HASN’T propagated!
One takeaway from this is that even once offices start functioning, they need to impose social distancing measures (until the virus has been completely wiped out). All large-ish meetings by video conference. A certain proportion of workers working from home by rotation.
Now, I’m not happy with the result. I mean, I’m okay with the average value where the red dot has been put for me, and I think that represents my political leanings rather well. However, what I’m unhappy about is that my political views have been all reduced to one single average point.
I’m pretty sure that based on all the answers I gave in the survey, my political leaning across both the two directions follows a distribution, and the red dot here is only the average (mean, I guess, but could also be median) value of that distribution.
However, there are many ways in which people can have a political view that lands right on my dot – some people might have a consistent but mild political view in favour of or against a particular position. Others might have pretty extreme views – for example, some of my answers might lead you to believe that I’m an extreme right winger, and others might make me look like a Marxist (I believe I have a pretty high variance on both axes around my average value).
So what I would have liked instead from the political compass was a sort of heat map, or at least two marginal distributions, showing how I’m distributed along the two axes, rather than all my views being reduced to one average value.
A version of this is the main argument of this book I read recently called “The End Of Average“. That when we design for “the average man” or “the average customer”, and do so across several dimensions, we end up designing for nobody, since nobody is average when looked at on many dimensions.
Over ten years ago, I wrote this blog post that I had termed as a “lazy post” – it was an email that I’d written to a mailing list, which I’d then copied onto the blog. It was triggered by someone on the group making an off-hand comment of “doing regression analysis”, and I had set off on a rant about why the misuse of statistics was a massive problem.
Ten years on, I find the post to be quite relevant, except that instead of “statistics”, you just need to say “machine learning” or “data science”. So this is a truly lazy post, where I piggyback on my old post, to talk about the problems with indiscriminate use of data and models.
I had written:
there is this popular view that if there is data, then one ought to do statistical analysis, and draw conclusions from that, and make decisions based on these conclusions. unfortunately, in a large number of cases, the analysis ends up being done by someone who is not very proficient with statistics and who is basically applying formulae rather than using a concept. as long as you are using statistics as concepts, and not as formulae, I think you are fine. but you get into the “ok i see a time series here. let me put regression. never mind the significance levels or stationarity or any other such blah blah but i’ll take decisions based on my regression” then you are likely to get into trouble.
The modern version of this is – everybody wants to do “big data” and “data science”. So if there is some data out there, people will want to draw insights from it. And since it is easy to apply machine learning models (thanks to open source toolkits such as the scikit-learn package in Python), people who don’t understand the models indiscriminately apply it on the data that they have got. So you have people who don’t really understand data or machine learning working with those, and creating models that are dangerous.
As long as people have idea of the models they are using, and the assumptions behind them, and the quality of data that goes into the models, we are fine. However, we are increasingly seeing cases of people using improper or biased data and applying models they don’t understand on top of them, that will have impact that affect the wider world.
So the problem is not with “artificial intelligence” or “machine learning” or “big data” or “data science” or “statistics”. It is with the people who use them incorrectly.
In his excellent podcast episode with EconTalk’s Russ Roberts, psychologist Gerd Gigerenzer introduces the concept of “fast and frugal trees“. When someone needs to make decisions quickly, Gigerenzer says, they don’t take into account a large number of factors, but instead rely on a small set of thumb rules.
The podcast itself is based on Gigerenzer’s 2009 book Gut Feelings. Based on how awesome the podcast was, I read the book, but found that it didn’t offer too much more than what the podcast itself had to offer.
Coming back to fast and frugal trees..
In recent times, ever since “big data” became a “thing” in the early 2010s, it is popular for companies to tout the complexity of their decision algorithms, and machine learning systems. An easy way for companies to display this complexity is to talk about the number of variables they take into account while making a decision.
For example, you can have “fin-tech” lenders who claim to use “thousands of data points” on their prospective customers’ histories to determine whether to give out a loan. A similar number of data points is used to evaluate resumes and determine if a candidate should be called for an interview.
With cheap data storage and compute power, it has become rather fashionable to “use all the data available” and build complex machine learning models (which aren’t that complex to build) for decisions that were earlier made by humans. The problem with this is that this can sometimes result in over-fitting (system learning something that it shouldn’t be learning) which can lead to disastrous predictive power.
In his podcast, Gigerenzer talks about fast and frugal trees, and says that humans in general don’t use too many data points to make their decisions. Instead, for each decision, they build a quick “fast and frugal tree” and make their decision based on their gut feelings about a small number of data points. What data points to use is determined primarily based on their experience (not cow-like experience), and can vary by person and situation.
The advantage of fast and frugal trees is that the model is simple, and so has little scope for overfitting. Moreover, as the name describes, the decision process is rather “fast”, and you don’t have to collect all possible data points before you make a decision. The problem with productionising the fast and frugal tree, however, is that each user’s decision making process is different, and about how we can learn that decision making process to make the most optimal decisions at a personalised level.
How you can learn someone’s decision-making process (when you’ve assumed it’s a fast and frugal tree) is not trivial, but if you can figure it out, then you can build significantly superior recommender systems.
If you’re Netflix, for example, you might figure that someone makes their movie choices based only on age of movie and its IMDB score. So their screen is customised to show just these two parameters. Someone else might be making their decisions based on who the lead actors are, and they need to be shown that information along with the recommendations.
Another book I read recently was Todd Rose’s The End of Average. The book makes the powerful point that nobody really is average, especially when you’re looking a large number of dimensions, so designing for average means you’re designing for nobody.
I imagine that is one reason why a lot of recommender systems (Netflix or Amazon or Tinder) fail is that they model for the average, building one massive machine learning system, rather than learning each person’s fast and frugal tree.
The latter isn’t easy, but if it can be done, it can result in a significantly superior user experience!
After 20 games played, Liverpool are sitting pretty on top of the Premier League with 58 points (out of a possible 60). The only jitter in the campaign so far came in a draw away at Manchester United.
I made what I think is a cool graph to put this performance in perspective. I looked at Liverpool’s points tally at the end of the first 19 match days through the length of the Premier League, and looked at “progress” (the data for last night’s win against Sheffield isn’t yet up on my dataset, which also doesn’t include data for the 1992-93 season, so those are left out).
Given the strength of this season’s performance, I don’t think there’s that much information in the graph, but here it goes in any case:
I’ve coloured all the seasons where Liverpool were the title contenders. A few things stand out:
This season, while great, isn’t that much better than the last one. Last season, Liverpool had three draws in the first half of the league (Man City at home, Chelsea away and Arsenal away). It was the first month of the second half where the campaign faltered (starting with the loss to Man City).
This possibly went under the radar, but Liverpool had a fantastic start to the 2016-17 season as well, with 43 points at the halfway stage. To put that in perspective, this was one more than the points total at that stage in the title-chasing 2008-9 season.
Liverpool went close in 2013-14, but in terms of points, the halfway performance wasn’t anything to write home about. That was also back in the time when teams didn’t dominate like nowadays, and eighty odd points was enough to win the league.
This is what Liverpool’s full season looked like (note that I’ve used a different kind of graph here. Not sure which one is better).
Finally, what’s the relationship between points at the end of the first half of the season (19 games) and the full season? Let’s run a regression across all teams, across all 38 game EPL seasons.
The regression doesn’t turn out to be THAT significant, with an R Squared of 41%. In other words, a team’s points tally at the halfway point in the season explains less than 50% of the variation in the points tally that the team will get in the second half of the season.
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 9.42967 0.97671 9.655 <2e-16 ***
Midway 0.64126 0.03549 18.070 <2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 6.992 on 478 degrees of freedom
(20 observations deleted due to missingness)
Multiple R-squared: 0.4059, Adjusted R-squared: 0.4046
F-statistic: 326.5 on 1 and 478 DF, p-value: < 2.2e-16
The interesting thing is that the coefficient of the midway score is less than 1, which implies that teams’ performances at the end of the season (literally) regress to the mean.
55 points at the end of the first 19 games is projected to translate to 100 at the end of the season. In fact, based on this regression model run on the first 19 games of the season, Liverpool should win the title by a canter.
PS: Look at the bottom of this projections table. It seems like for the first time in a very long time, the “magical” 40 points might be necessary to stave off relegation. Then again, it’s regression (pun intended).
I’m rather disappointed with my end-of-year Spotify report this year. I mean, I know it’s automated analytics, and no human has really verified it, etc. but there are some basics that the algorithm failed to cover.
The first few slides of my “annual report” told me that my listening changed by seasons. That in January to March, my favourite artists were Black Sabbath and Pink Floyd, and from April to June they were Becky Hill and Meduza. And that from July onwards it was Sigala.
Now, there was a life-changing event that happened in late March which Spotify knows about, but failed to acknowledge in the report – I moved from the UK to India. And in India, Spotify’s inventory is far smaller than it is in the UK. So some of the bands I used to listen to heavily in the UK, like Black Sabbath, went off my playlist in India. My daughter’s lullaby playlist, which is the most consumed music for me, moved from Spotify to Amazon Music (and more recently to Apple Music).
The other thing with my Spotify use-case is that it’s not just me who listens to it. I share the account with my wife and daughter, and while I know that Spotify has an algorithm for filtering out kid stuff, I’m surprised it didn’t figure out that two people are sharing this account (and pitched us a family subscription).
According to the report, these are the most listened to genres in 2019:
Now there are two clear classes of genres here. I’m surprised that Spotify failed to pick it out. Moreover, the devices associated with my account that play Rock or Power Metal are disjoint from the devices that play Pop, EDM or House. It’s almost like Spotify didn’t want to admit that people share accounts.
Then some three slides on my podcast listening for the year, when I’ve overall listened to five hours of podcasts using Spotify. If I, a human, were building this report, I would have dropped this section citing insufficient data, rather than wasting three slides with analytics that simply don’t make sense.
I see the importance of this segment in Spotify’s report, since they want to focus more on podcasts (being an “audio company” rather than a “music company”), but maybe something in the report to encourage me to use Spotify for more podcasts (maybe recommending Spotify’s exclusive podcasts that I might like, be it based on limited data?) might have helped.
Finally, take a look at my our most played songs in 2019.
It looks like my daughter’s sleeping playlist threaded with my wife’s favourite songs (after a point the latter dominate). “My songs” are nowhere to be found – I have to go all the way down to number 23 to find Judas Priest’s cover of Diamonds and Rust. I mean I know I’ve been diversifying the kind of music that I listen to, while my wife listens to pretty much the same stuff over and over again!
In any case, automated analytics is all fine, but there are some not-so-edge cases where the reports that it generates is obviously bad. Hopefully the people at Spotify will figure this out and use more intelligence in producing next year’s report!