Now Machine Learning (ML) is the new buzz word. It’s facinating to hear how ML is used to solve real world problems. It is not easy to apply machine learning to real world finance applications. Even though deep learning is good at classifying and predicting data they are not transparent. Financial system without complete transparency is never going to fly.
As an alternative I started looking into decision trees, a transparent ML. In my spare time I am working on decision tree algorithms and testing them. It’s fun!!
I found, “Tree-based Machine Learning Algorithms: Decision Trees, Random Forests, and Boosting” by Clinton Sheppard very useful. The book starts with a simple decision tree algorithm and slowly introduce one to it’s problems and show how to overcome them. This helped me understand the concept better. I would recommend this book to any one interested in tree-based Machine Learning.
So far all the examples that I works are using flat data. Still need to figure out how it can be applied on data with 1 to many relation.