LJSthu/Movie-Analysis
使用机器学习算法的电影推荐系统以及票房预测系统
Implements ensemble gradient boosting (CatBoost, XGBoost, LightGBM) for box office prediction and nine distinct recommendation algorithms spanning content-based similarity (TF-IDF on plot summaries), collaborative filtering (KNN on user-movie rating matrices), and matrix factorization (SVD with SGD/SGLD/SGHMC). The system integrates MovieLens and TMDB datasets with evaluation on 5-fold cross-validation, achieving top 6.8% on Kaggle's TMDB Box Office Prediction competition.
335 stars. No commits in the last 6 months.
Stars
335
Forks
55
Language
Python
License
—
Category
Last pushed
Feb 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LJSthu/Movie-Analysis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
MengtingWan/oscar
predicting oscars using machine learning methods
Vikranth3140/Movie-Revenue-Prediction
Movie Revenue Prediction System predicts the revenue of a movie with 14 parameters: name,...
devinw03/movie-genre-nlp
🎬 Classify movie genres from plot summaries using various models, including Transformers, with...
Zer0-Bug/IMDB_Prediction
End-to-End ML Pipeline for IMDB Rating Prediction w/ Advanced Feature Engineering.
nv2105/MovieIQ-Predictive-Analytics-on-Film-Success
MovieIQ is a Streamlit-based interactive dashboard that predicts movie success using data-driven...