A field manual for making smarter decisions in real-world machine learning workflows.
Written by Thomas Rauter.
Most machine learning books focus on theory, implementation, or model performance.
This one is different.
Decision-Making in Machine Learning Projects is a concise, practical guide for navigating real ML projects — where trade-offs are constant, decisions are messy, and perfect data is rare.
This book focuses on:
- 🔍 What tools and techniques exist
- ⏱️ When to apply them
- 🧠 Why they help in context
You won’t find detailed math or tutorials — that’s what Google and docs are for.
Instead, this is the resource you keep open while working, to guide real decisions.
(or check the
releases/tab if hosted on GitHub or Bitbucket)
- Data-centric model development
- Exploratory data analysis (EDA)
- Feature transformations and encoding
- Dataset splitting and cross-validation
- Model selection and evaluation
- Common pitfalls in insight generation
- Interpreting and communicating model behavior
Everything is designed for clarity, conciseness, and direct applicability.
Thomas Rauter
PhD candidate in Bioinformatics (University of Salzburg)
Focus: Interpretable deep learning, CHO cell modeling, and statistical omics workflows.
📍 Salzburg, Austria
📧 rauterthomas0@gmail.com
This book will tell you what to do, when to do it, and why—
but if you want to know how, or dive into the details, you must consider additional resources.
This book is currently under active development.
All rights reserved. Please contact the author for permission to reuse or redistribute.