papers of universal user representation learning for 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.

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

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

Chrome extension + multi-agent LLM pipeline that bypasses Zhihu's anti-scraping defenses to profile any public user across PII leakage, content authenticity, and HEXACO personality. 绕过知乎反爬，浏览器扩展 + LLM 多智能体生成用户深度画像。

基于地址探测与关联技术的IPv6地址分析平台

E-commerce pricing optimization & dynamic user profiling

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

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.

River Algorithm memory consolidation SDK for Python — pip install riverse

AI-powered Xiaohongshu (小红书) user deep profiling & pursuit strategy engine. Multi-modal analysis with any LLM (GPT-4o/Claude/Gemini/local). 9-dimension psychological profiling based on 5 academic theories. Interactive HTML reports with ideal-type matching. 给我一个小红书链接，还你一份FBI级人物画像+量身定制追求路线图。

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

QuickSim — AI-powered life scenario prediction: Enter a multiple-choice question, and AI will deduce the chain of consequences for each path.

🧠 MindPeek | 让 AI 真正读懂人心 告别传统用户画像方法！ MindPeek 通过 LLM 深度解析，从每轮对话中自动提取性格、偏好、潜在需求——构建持续进化的个人画像。 ✨ 核心能力 • 多维度特征提取：性格特点 / 价值观 / 潜在想法 / 情感状态等 • 多 Agent 协作架构：自我进化，越用越懂你 懂用户的 AI，从这里开始。

An OSINT (Open-Source Intelligence) service that generates detailed factual and psychological profiles of Twitter users using an agentic AI model.