lambdarank

Tensorflow implementations of various Learning to Rank (LTR) algorithms.

train models in pytorch, Learn to Rank, Collaborative Filter, Heterogeneous Treatment Effect, Uplift Modeling, etc

Implementation of RankNet to LambdaRank in TensorFlow 2.0

This module implements LambdaRank as a tensorflow OP in C++. As an example application, we use this OP as a loss function in our keras based deep ranking/recommendation engine. The ranking application embeds slide objects into d-dimensional space(slide2vec), such that we obtain best LambdaRank scores.

RocAuc Pairiwse objective for gradient boosting

ctr and rank model used by keras

Large-scale e-commerce recommendation engine with memory-efficient co-visitation, leakage-safe evaluation, feature engineering, and LightGBM LambdaRank reranking.

Intelligent candidate ranking system for the Redrob India Runs Data & AI Challenge. Ranks 100K profiles for a Senior AI Engineer JD in 52s on CPU using XGBoost LambdaRank with 43 engineered features + self-supervised pseudo-labels. 100% Precision@100.

Exploration of retrieval methods on the HotpotQA corpus, combining dense retrieval and feature-based reranking. Achieved a mean nDCG@10 of 0.9416 using LambdaRank with features such as cross-encoder score, LLM score, BM25 score, and token-based statistics—surpassing dense retriever + cross-encoder baselines.

Two-stage session-based recommender (LightGBM LambdaRank) for an Inditex hackathon. Cold-start focused, 93% of sessions have no user history. NDCG@5 = 0.377, Hit Rate@5 = 76%.