allRank is a framework for training learning-to-rank neural models based on PyTorch.

LibAUC: A Deep Learning Library for X-Risk Optimization

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

machine learning framework for node.js

Official codebase for the ACL 2025 Findings paper: Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval.

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.

Pairwise t-test on TREC run files

normalized discounted cumulative gain

Movie recommendation system with Python. Implements content-based filtering (TF-IDF + cosine similarity), collaborative filtering with matrix factorization (TruncatedSVD), and a hybrid approach. Evaluates with Precision@K, Recall@K, and NDCG. Includes rating distribution plots, top movies, and sample recommendations.

bert-ndcg for LP(Link Prediction)，链接预测

Re-ranking documents optimising NDCG measure with XGBRanker model

🔝 HW1 of Intelligent Information Retrieval MSc Course ECE@UT

🔍 A Python Search Engine with building index using TF-IDF and NDCG, also include a Flask web app. UCI Information Retrieval Project.

Structured approach in AI and ML. Fundamentals and Advanced topics. RAG, Scoring & Profiling, LangChain & LangGraph, Certified Azure AI Engineer materials.

Plots for search metrics nDCG and ERR

Machine learning competition on kaggle

A port of gdeval.pl to Rust

Korean-optimized RAG evaluation toolkit with Kiwi tokenizer, ROUGE metrics, and IR evaluation for retrieval systems (Hit@K, NDCG@K, MRR, etc.)

Delve into the exciting world of Applied Machine Learning to deliver personalized anime recommendations! This project is designed to help anime enthusiasts discover new series tailored to their unique preferences, enhancing their viewing experience.