Why Model Explainability is The Next Data Science Superpower

By Dan Becker

Model explainability techniques show you what your model is learning, and seeing inside your model is even more useful than most people expect.

I’ve interviewed many data scientists in the last 10 years, and model explainability techniques are my favorite topic to distinguish the very best data scientists from the average.

Some people think machine learning models are black boxes, useful for making predictions but otherwise unintelligible; but the best data scientists know techniques to extract real-world insights from any model. For any given model, these data scientists can easily answer questions like

  • What features in the data did the model think are most important?
  • For any single prediction from a model, how did each feature in the data affect that particular prediction
  • What interactions between features have the biggest effects on a model’s predictions

Answering these questions is more broadly useful than many people realize. This inspired me to create Kaggle’s model explainability micro-course. Whether you learn the techniques from Kaggle or from a comprehensive resource like Elements of Statistical Learning, these techniques will totally change how you build, validate and deploy machine learning models.

The five most important applications of model insights are

  • Debugging
  • Informing feature engineering
  • Directing future data collection
  • Informing human decision-making
  • Building Trust

The world has a lot of unreliable, disorganized and generally dirty data. You add a potential source of errors as you write preprocessing code. Add in the potential for target leakage and it is the norm rather than the exception to have errors at some point in a real data science projects.

Given the frequency and potentially disastrous consequences of bugs, debugging is one of the most valuable skills in data science. Understanding the patterns a model is finding will help you identify when those are at odds with your knowledge of the real world, and this is typically the first step in tracking down bugs.

Feature engineering is usually the most effective way to improve model accuracy. Feature engineering usually involves repeatedly creating new features using transformations of your raw data or features you have previously created.

Sometimes you can go through this process using nothing but intuition about the underlying topic. But you’ll need more direction when you have 100s of raw features or when you lack background knowledge about the topic you are working on.

A Kaggle competition to predict loan defaults gives an extreme example. This competition had 100s of raw features. For privacy reasons, the features had names like f1, f2, f3 rather than common English names. This simulated a scenario where you have little intuition about the raw data.

One competitor found that the difference between two of the features, specifically f527 — f528, created a very powerful new feature. Models including that difference as a feature were far better than models without it. But how might you think of creating this variable when you start with hundreds of variables?

The techniques you’ll learn in this course would make it transparent that f527 and f528 are important features, and that their role is tightly entangled. This will direct you to consider transformations of these two variables, and likely find the “golden feature” of f527 — f528.

As an increasing number of datasets start with 100s or 1000s of raw features, this approach is becoming increasingly important.

You have no control over datasets you download online. But many businesses and organizations using data science have opportunities to expand what types of data they collect. Collecting new types of data can be expensive or inconvenient, so they only want to do this if they know it will be worthwhile. Model-based insights give you a good understanding of the value of features you currently have, which will help you reason about what new values may be most helpful.

Some decisions are made automatically by models. Amazon doesn’t have humans (or elves) scurry to decide what to show you whenever you go to their website. But many important decisions are made by humans. For these decisions, insights can be more valuable than predictions.

Many people won’t assume they can trust your model for important decisions without verifying some basic facts. This is a smart precaution given the frequency of data errors. In practice, showing insights that fit their general understanding of the problem will help build trust, even among people with little deep knowledge of data science.

This essay is adapted from the model explainability micro-course on Kaggle Learn.