# FISM

**Repository Path**: Mrcc920/FISM

## Basic Information

- **Project Name**: FISM
- **Description**:  implementation for the paper "FISM: Factored Item Similarity Models for Top-N Recommender Systems" by Tensorflow 1.2
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2019-09-26
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# FISM
This repository contains an implementation for the paper "FISM: Factored Item Similarity Models for Top-N Recommender Systems" by Tensorflow 1.2.
# Requirement
Python 3.5

Tensorflow 1.2
# Dataset

This data set is extracted from movielens-1m by Dr. Xiangnan He. The data set is first proposed by the paper "Neural Collaborative Filtering".

# Evaluation
I use the hit ratio(aka HR) metric to evalute the model performance. I tune the hyperparameter carefully for the best performance. Specifically,
the best HR this code can achieve is 71.05%, after about 5 epoches training.

# Citation
If you use the codes for your paper as baseline implementation, please cite the link: "https://github.com/yushuai/FISM"

# Last update date
2018/1/15