Training ML models on tails

This page contains research and presentation material on the topic of instance filtering in machine learning.

---

Files

• Formal analysis & graphs: some plots and the simple gain contest analysis between linear and quadratic generators. (original Rmd source code)
• Toy model: A simple illustration of the impact of filtering. (original Rmd source code)
  
• Simulations: Simulations on the impact of filtering. (original Rmd source code)
  
• Portfolio backtesting: boosted tree-based portfolio construction (out-of-sample). (original Rmd source code)
  
• Data (In R format: 1,182 firms & 108 features over 162 months)
  
• Slides
• Working paper
  
• Published paper

---

---

DISCLAIMER: the data and code are meant for research and pedagogical use only.

---