Introduction

Here are some in-depth examples to help you with mastering Choice-Learn. In particular you will find notebooks to handle:

DATA - An introduction to data handling with Choice-Learn - More in-depth examples to instantiate a ChoiceDataset - Explanations and examples on how to use Features by IDs if you have RAM usage issues

MODELS

• Linear Models :

  • MNL: An introduction to choice modeling with the Multi Nomial Logit model
  • cLogit: Tutorials on how to parametrize and fit a Conditional Logit model
  • nLogit: How to parametrize and fit a Nested Logit model
  • Latent Class: A basic examples on how to estimate several Latent Class models

• Non-Linear Models :

  • RUMnet: Representing Random Utility Choice Models with Neural Networks (Aouad and Désir, 2023).
  • TasteNet-MNL: A neural-embedded discrete choice model: Learning taste representation with strengthened interpretability (Han, Pereira, Ben-Akiva and Zegras, 2022)

• Diverse :

  • Logistic Regression: A reproduction of the logistic regression tutorial by scikit-learn
  • On model finetuning: Hyperparameters and learning tools

AUXILIARY TOOLS

We currently handle two types of post-processing that leverage choice models:

• Assortment Optimization: How to best select a subset of alternatives to sell to a customer.
• Pricing: How to best select alternative prices - can be combined with assortment optimization.

If you feel like adding adding a dataset, a model, a tool or a usecase algorithm would bring value to the package, feel free to reach out !