面向大连理工大学学者，基于大连理工大学机构知识库，推荐潜在主题词，优化科研方向，促进跨学部、学科、领域科研合作。

Zee Recommender Systems is a personalized movie recommendation project built using the MovieLens dataset. It implements collaborative filtering, similarity-based models, and matrix factorization to enhance user experience by suggesting movies tailored to individual preferences. Includes EDA, evaluation (RMSE & MAPE) and visualization of embeddings.

System is going to filter out the best possible movies basis on some criteria in recommendation area even after analyzing and previewing the reviews of the particular movie using sentiment analysis theory.

Shopper Spectrum: Streamlit app for customer segmentation (RFM + KMeans) and product recommendations (collaborative filtering) using e-commerce data.

The Movie Recommendation System is a Python application that provides personalized movie suggestions using collaborative and content-based filtering techniques. Utilizing the MovieLens 25M dataset, it offers customizable recommendations based on user ID, movie title, and desired suggestion count, creating an engaging and tailored movie discovery.

Survey on Similarity Measures for Collaborative Filtering

android 屏幕适配方案，app module是利用反射做的代码适配； precentscreen是利用自定义view和attrs来做到屏幕适配

HCP Hybrid Recommender System v0.1: A healthcare marketing recommendation engine using LSTM, topic modeling, and collaborative/content-based filtering to predict personalized content and channel engagement for HCPs. Includes data preprocessing, model training, and a Streamlit dashboard for interactive visualization.