criteo-research

reco-gym

Code for reco-gym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising

CausE

Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.

pytorch-ada

Another Domain Adaptation library, aimed at researchers.

bandit-reco

optimization-continuous-action-crm

iclr_analysis

paiss_deeprl

continuous-fairness

large-scale-ITE-UM-benchmark

blob

Source code for our paper "BLOB: a probabilistic model for recommendation that combines organic and bandit signals" published at KDD 2020.

tf-tile

TF-Tile: an efficient sparse representation for real-valued data

ad_click_prediction_from_aggregated_data

Efficient-Kernel-UCB

master-iasd

Resources for the IASD master from Criteo

logistic_bandit

Logistic Bandit experiments. Official code for the paper "Jointly Efficient and Optimal Algorithms for Logistic Bandits".

robust-label-attribution

sequential-conterfactual-risk-minimization

uplift_modeling_metric

criteo-privacy-preserving-ml-competition

success-proba-max

tensorflow_approximate_top_k

Custom Tensorflow operation to do approximate top-K

warhol

counterfactual_evaluation_and_recommendation

gennes

Generative Neural Networks for Differentiable Evolutionary Search.

Nested-Exponential-Weights