Skip to content

Latest commit

 

History

History
24 lines (19 loc) · 832 Bytes

README.md

File metadata and controls

24 lines (19 loc) · 832 Bytes

goodbooks-10k-recommender

Description

XGBoost Book Recommender system using goodbooks-10k dataset (binary ratings ver.)
This recommender system provides the top 10 recommended books by the user. If recommender system doesn't have any information about the user, recommend 10 of the most popular books (books with high ratings).

Usage

  1. Download dataset
    You can download dataset here : https://www.kaggle.com/zygmunt/goodbooks-10k

  2. Run Train / Predict / Recommend
    mode : train, predict, recommend
    user_id : user_id (only for recommend mode)

./run.sh {mode} {user_id}
  • train : train xgboost model
  • predict : evaluate xgboost model performance(rmse, accuracy)
  • recommend : recommend top 10 books for user(user_id)

Performance

RMSE : 0.36416453186682807
Accuray Score : 0.7875972342264477