This book is for anyone who wants to understand machine learning at a conceptual level, without writing code and without working through the mathematics.
Starting from first principles, the book builds a complete picture of how machine learning works: what it is, how models learn from data, and where the approach succeeds and where it fails. You will develop the mental models needed to evaluate ML systems, ask better questions, and make more informed decisions when machine learning is involved in your work.
What You Will Learn
- Explain what machine learning is and how it differs from traditional rule-based software
- Describe the main types of ML problems: supervised, unsupervised, and reinforcement learning
- Interpret model performance metrics and explain why a 95% accurate model can still be useless
- Describe overfitting, underfitting, and how regularization addresses them
- Identify the major families of ML algorithms and when each is appropriate
- Walk through the end-to-end ML workflow, from problem definition to deployment
Every concept is grounded in finance, with examples drawn from credit risk, fraud detection, and the kinds of problems that arise in banks, asset managers, and fintech companies.