In most of our data science teaching (including our book Practical Data Science with R) we emphasize the deliberately easy problem of “exchangeable prediction.” We define exchangeable prediction as: given a series of observations with two distinguished classes of variables/observations denoted “x”s (denoting control variables, independent variables, experimental variables, or predictor variables) and “y” (denoting an outcome variable, or dependent variable) then:
- Estimate an approximate functional relation
y ~ f(x).
- Apply that relation to new instances where
x is known and
y is not yet known.
An example of this would be to use measured characteristics of online shoppers to predict if they will purchase in the next month. Data more than a month old gives us a training set where both
y are known. Newer shoppers give us examples where only
x is currently known and it would presumably be of some value to estimate
y or estimate the probability of different
y values. The problem is philosophically “easy” in the sense we are not attempting inference (estimating unknown parameters that are not later exposed to us) and we are not extrapolating (making predictions about situations that are out of the range of our training data). All we are doing is essentially generalizing memorization: if somebody who shares characteristics of recent buyers shows up, predict they are likely to buy. We repeat: we are not forecasting or “predicting the future” as we are not modeling how many high-value prospects will show up, just assigning scores to the prospects that do show up.
The reliability of such a scheme rests on the concept of exchangeability. If the future individuals we are asked to score are exchangeable with those we had access to during model construction then we expect to be able to make useful predictions. How we construct the model (and how to ensure we indeed find a good one) is the core of machine learning. We can bring in any big name machine learning method (deep learning, support vector machines, random forests, decision trees, regression, nearest neighbors, conditional random fields, and so-on) but the legitimacy of the technique pretty much stands on some variation of the idea of exchangeability.
One effect antithetical to exchangeability is “concept drift.” Concept drift is when the meanings and distributions of variables or relations between variables changes over time. Concept drift is a killer: if the relations available to you during training are thought not to hold during later application then you should not expect to build a useful model. This one of the hard lessons that statistics tries so hard to quantify and teach.
We know that you should always prefer fixing your experimental design over trying a mechanical correction (which can go wrong). And there are no doubt “name brand” procedures for dealing with concept drift. However, data science and machine learning practitioners are at heart tinkerers. We ask: can we (to a limited extent) attempt to directly correct for concept drift? This article demonstrates a simple correction applied to a deliberately simple artificial example.
Image: Wikipedia: Elgin watchmaker
From time to time we are asked “what is the company name Win-Vector LLC referring to?” It is a cryptic pun trying to be an encoding of “we deliver victory.”
The story is an inside joke referring to something really only funny to one of the founders. But a joke that amuses the teller is always enjoyed by at least one person. Win-Vector LLC’s John Mount had the honor of co-authoring a 1997 paper titled “The Polytope of Win Vectors.” The paper title is obviously mathematical terms in an odd combination. However the telegraphic grammar is coincidentally similar to deliberately ungrammatical gamer slang such as “full of win” and “so much win.”
If we treat “win” as a concrete noun (say something you can put in a sack) and “vector” in its non-mathematical sense (as an entity of infectious transmission) we have “Win-Vector LLC is an infectious delivery of victory.” I.e.: we deliver success to our clients. Of course, we have now attempt to explain a weak joke. It is not as grand as “winged victory,” but it does encode a positive company value: Win-Vector LLC delivers successful data science projects and training to clients.
Winged Victory: from Wikipedia
Let’s take this as an opportunity to describe what a win vector is. Continue reading
Page 94 of Gelman, Carlin, Stern, Dunson, Vehtari, Rubin “Bayesian Data Analysis” 3rd Edition (which we will call BDA3) provides a great example of what happens when common broad frequentist bias criticisms are over-applied to predictions from ordinary linear regression: the predictions appear to fall apart. BDA3 goes on to exhibit what might be considered the kind of automatic/mechanical fix responding to such criticisms would entail (producing a bias corrected predictor), and rightly shows these adjusted predictions are far worse than the original ordinary linear regression predictions. BDA3 makes a number of interesting points and is worth studying closely. We work their example in a bit more detail for emphasis. Continue reading
What is meant by regression modeling?
Linear Regression is one of the most common statistical modeling techniques. It is very powerful, important, and (at first glance) easy to teach. However, because it is such a broad topic it can be a minefield for teaching and discussion. It is common for angry experts to accuse writers of carelessness, ignorance, malice and stupidity. If the type of regression the expert reader is expecting doesn’t match the one the writer is discussing then the writer is assumed to be ill-informed. The writer is especially vulnerable to experts when writing for non-experts. In such writing the expert finds nothing new (as they already know the topic) and is free to criticize any accommodation or adaption made for the intended non-expert audience. We argue that many of the corrections are not so much evidence of wrong ideas but more due a lack of empathy for the necessary informality necessary in concise writing. You can only define so much in a given space, and once you write too much you confuse and intimidate a beginning audience. Continue reading
Nassim Nicholas Taleb recently wrote an article advocating the abandonment of the use of standard deviation and advocating the use of mean absolute deviation. Mean absolute deviation is indeed an interesting and useful measure- but there is a reason that standard deviation is important even if you do not like it: it prefers models that get totals and averages correct. Absolute deviation measures do not prefer such models. So while MAD may be great for reporting, it can be a problem when used to optimize models. Continue reading
I was watching my cousins play Unspeakable Words over Christmas break and got interested in the end game. The game starts out as a spell a word from cards and then bet some points game, but in the end (when you are down to one marker) it becomes a pure betting game. In this article we analyze an idealized form of the pure betting end game. Continue reading
Elon Musk’s writing about a Tesla battery fire reminded me of some of the math related to trying to estimate the rate of a rare event from a single occurrence of the event (plus many non-event occurrences). In this article we work through some of the ideas. Continue reading
This article is a break from data-science, and is instead about the kind of problem you can try on the train. It is problem 70 in Bollobas’s “The art of mathematics” (though I forgot that and re-worked the problem crudely from memory when writing this article).
One of the many irritating things about airlines is the fact that the cary-on bag restrictions are often stated as “your maximum combined linear measurement (length + width + height) must not exceed 45 inches” when they really mean your bag must fit into a 14 inch by 9 inch by 22 inch box (so they actually may not accept a 43 inch by one inch by one inch pool spear as your carry-on). The “total linear measure” seems (at first glance) “gameable,” but can (through some hairy math) at least be seen to at least be self-consistent. It turns out you can’t put a box with longer total linear measurements into a box with smaller total linear measurements.
Let’s work out why this could be problem and then why the measure works. Continue reading
We share our opinion that
= should be preferred to the more standard
From time to time we work on projects that would benefit from a free lightweight pure Java linear programming library. That is a library unencumbered by a bad license, available cheaply, without an infinite amount of file format and interop cruft and available in Java (without binary blobs and JNI linkages). There are a few such libraries, but none have repeatably, efficiently and reliably met our needs. So we have re-packaged an older one of our own for release under the Apache 2.0 license. This code will have its own rough edges (not having been used widely in production), but I still feel fills an important gap. This article is brief introduction to our WVLPSolver Java library. Continue reading