Chapter 7. Traffic Stops and Crash Locations – When Two Datasets Are Better Than One

If you remember from Chapter 4, Traffic Stops – Barking Up the Wrong Tree?, we used a decision tree to help us determine if a person received a ticket or a warning based on several seasonality factors like time of day, day of the week, and the like. Ultimately, we could not find a relationship. Your first inclination might be to throw out the dataset, which I think is a mistake because there might be data gold in them thar hills, but we are just using the wrong model. Also, if a single dataset is not profitable, I typically start augmenting that set with others to see if the combination of features will provide a more satisfactory answer. In this chapter, let's ...

Get Mastering .NET Machine Learning now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.