# Pseudo-Implicit Feedback for Alleviating Data Sparsity in Top-K Recommendation

## TL;DR

PsiRec is a novel recommender system that uses pseudo-implicit feedback derived from user-item bipartite graphs and random walks to improve top-K recommendation accuracy in sparse data scenarios.

## Contribution

It introduces a graph-based approach with a Skip-gram inspired confidence measure to generate pseudo-implicit feedback, enhancing preference estimation in sparse datasets.

## Key findings

- Achieves 21.5% improvement in Precision@10
- Achieves 22.7% improvement in Recall@10
- Effective in alleviating data sparsity issues

## Abstract

We propose PsiRec, a novel user preference propagation recommender that incorporates pseudo-implicit feedback for enriching the original sparse implicit feedback dataset. Three of the unique characteristics of PsiRec are: (i) it views user-item interactions as a bipartite graph and models pseudo-implicit feedback from this perspective; (ii) its random walks-based approach extracts graph structure information from this bipartite graph, toward estimating pseudo-implicit feedback; and (iii) it adopts a Skip-gram inspired measure of confidence in pseudo-implicit feedback that captures the pointwise mutual information between users and items. This pseudo-implicit feedback is ultimately incorporated into a new latent factor model to estimate user preference in cases of extreme sparsity. PsiRec results in improvements of 21.5% and 22.7% in terms of Precision@10 and Recall@10 over state-of-the-art Collaborative Denoising Auto-Encoders. Our implementation is available at https://github.com/heyunh2015/PsiRecICDM2018.