Notebooks

This directory contains Jupyter notebooks demonstrating various aspects of CF-based ensemble learning, organized by topic.

Notebooks by Topic

01. Collaborative Filtering

• Demo-Part1-CF_with_ALS.ipynb: Introduction to collaborative filtering with Alternating Least Squares (ALS) optimization

02. Loss Functions

• Demo-Part2-The_Role_of_Loss_Function_in_CF_Ensemble.ipynb: Understanding the role of loss functions in CF ensemble learning

03. K-Nearest Neighbors Ensemble

• Demo-Part3-CF_Ensemble_with_kNNs.ipynb: CF ensemble with K-Nearest Neighbors

04. Stacking

• Demo-Part4-CF_Stacker.ipynb: CF ensemble for stacked generalization
• demo-stacking.ipynb: Additional stacking examples

05. Probability Filtering

• Demo-Part5-CF_Ensemble_via_Probability_Filtering.ipynb: CF ensemble with probability filtering
• Demo-Part5a-Alternative_Data_Representations_for_Probability_Filtering.ipynb: Alternative data representations
• Demo-Part5b-Probability_Filtering_via_Custom_Loss.ipynb: Probability filtering via custom loss functions

Getting Started

1. Set up the environment using environment.yml or environment-runpod.yml
2. Start with notebook 01 for an introduction to the core concepts
3. Progress through the numbered series to build understanding of the complete framework