papers of universal user representation learning for recommendation

DataSets links for recommender systems research, in particular for transfer learning, user representation, pre-training,lifelong learning, cold start recommendation

A smart fashion web app built with Python (Flask) that recommends personalized outfits based on user profiling and AI analysis. It includes features like real-time virtual try-on with OOTDiffusion, skin tone & demographic detection using DeepFace, and outfit recommendations powered by TensorFlow, Gemini API, and PyTorch.

6th Place Solution for SMP CUP 2017 (Third Prize)

JPIS: A Joint Model for Profile-Based Intent Detection and Slot Filling with Slot-to-Intent Attention (ICASSP 2024)

Source code for CIKM 2021 paper for Relation-aware Heterogeneous Graph for User Profiling

is a powerful tool designed to find a username across multiple social media platforms

基于地址探测与关联技术的IPv6地址分析平台

Python scripts that implement collaborative filtering using Matrix Factorization with Alternating Least Squares (MF-ALS) for hotels and restaurants, Restricted Boltzmann Machines (RBM) for attractions, and content-based filtering using cosine similarity for the "More Like This" feature.

User Profiling and Sentiment analysis of Twitter social network during the impeachment of Brazilian President

E-commerce pricing optimization & dynamic user profiling

Repository of the paper "Toward a Responsible Fairness Analysis: From Binary to Multiclass and Multigroup Assessment in Graph Neural Network-Based User Modeling Tasks"

Cluster Analysis of Personal IMDB Ratings to find insights and segment user preference.

Large Literature DB, ETL & AI: Multi-source Web Crawling/Scrapping, auto-load warehouse, Graph-based Recommenders, Big data tools, OLAP, GraphRAG AI, LLMops, market insights. Connects reader markets/communities. Millions of reviews. books,series,authors,reviews,genres,prices,trends,niche scores, influence networks

Source code for our paper at Re-coding Black Mirror workshop @ ISWC 2017

MemU is an agentic memory framework for LLM and AI agent backends: it ingests multi-modal data, extracts and organizes it into structured memory and supports both RAG and LLM-based retrieval.

Predict user who visits the domains.

This GitHub page presents the official code and resources for our research on LLM-Driven Temporal User Profiling (LLM-TP) for recommender systems. The project focuses on a modular framework that leverages Large Language Models (LLMs) to create rich, context-aware user profiles.

User profiling based on social media data is becoming an increasingly relevant task with applications in advertising, this is one of the top PAN2020 solutions!

SecureBank is a simulated banking platform using keystroke dynamics for continuous user authentication. It combines behavioral biometrics with Zero Trust security to detect anomalies and trigger real-time reauthentication for enhanced session security.