START HERE

Start here

The heart of this blog is the “Foundations of Finance Data Science” series. Like a book, it reads best in order, from Part 0.

Reading order

1. 0 7 ways finance data science differs from ordinary ML Published
2. 1 The card business and credit risk: where underwriting models begin Published
3. 2 Statistics first: how to read credit data Published
4. 3 Where deep learning doesn’t win: machine learning for scoring Published
5. 4 Building a credit model: scorecards and trees Published
6. 5 Ranking isn’t enough: three axes for evaluating a credit model Published
7. 6 Causal inference and experiments Upcoming
8. 7 Model validation, governance, and monitoring Upcoming
9. 8 Interpretability, fairness, and regulation Upcoming
10. 9 Data engineering and tooling Upcoming
11. 10 Connecting to the business, and communication Upcoming

※ The order and titles are provisional, and I refine them as the series goes.