Session-Based Recommendation Method Using Popularity-Stratified Preference Modeling

Large-scale offline evaluations of user–project interactions in recommendation systems are often biased due to inherent feedback loops. To address this, many studies have employed propensity scoring. In this work, we extend these methods to session-based recommendation tasks by refining propensity s...

Full description

Saved in:
Bibliographic Details
Main Authors: Yayelin Mo, Haowen Wang
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/6/960
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850091504742170624
author Yayelin Mo
Haowen Wang
author_facet Yayelin Mo
Haowen Wang
author_sort Yayelin Mo
collection DOAJ
description Large-scale offline evaluations of user–project interactions in recommendation systems are often biased due to inherent feedback loops. To address this, many studies have employed propensity scoring. In this work, we extend these methods to session-based recommendation tasks by refining propensity scoring calculations to reflect dataset-specific characteristics. We evaluate our approach using neural models, specifically GRU4REC, and K-Nearest Neighbors (KNN)-based models on music and e-commerce datasets. GRU4REC is selected for its proven sequential model and computational efficiency, serving as a robust baseline against which we compare traditional methods. Our analysis of trend distributions reveals significant variations across datasets, and based on these insights, we propose a hierarchical approach that enhances model performance. Experimental results demonstrate substantial improvements over baseline models, providing a clear pathway for mitigating biases in session-based recommendation systems.
format Article
id doaj-art-cfa71a9250c145b5808cfa26316aba03
institution DOAJ
issn 2227-7390
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-cfa71a9250c145b5808cfa26316aba032025-08-20T02:42:22ZengMDPI AGMathematics2227-73902025-03-0113696010.3390/math13060960Session-Based Recommendation Method Using Popularity-Stratified Preference ModelingYayelin Mo0Haowen Wang1School of Electronics and Information Engineering, Beijing Jiaotong University, Beijing 100444, ChinaDepartment of Energy Engineering, Zhejiang University, Hangzhou 310027, ChinaLarge-scale offline evaluations of user–project interactions in recommendation systems are often biased due to inherent feedback loops. To address this, many studies have employed propensity scoring. In this work, we extend these methods to session-based recommendation tasks by refining propensity scoring calculations to reflect dataset-specific characteristics. We evaluate our approach using neural models, specifically GRU4REC, and K-Nearest Neighbors (KNN)-based models on music and e-commerce datasets. GRU4REC is selected for its proven sequential model and computational efficiency, serving as a robust baseline against which we compare traditional methods. Our analysis of trend distributions reveals significant variations across datasets, and based on these insights, we propose a hierarchical approach that enhances model performance. Experimental results demonstrate substantial improvements over baseline models, providing a clear pathway for mitigating biases in session-based recommendation systems.https://www.mdpi.com/2227-7390/13/6/960recommender system biassession-based recommendationpropensity scoringpopularity stratified
spellingShingle Yayelin Mo
Haowen Wang
Session-Based Recommendation Method Using Popularity-Stratified Preference Modeling
Mathematics
recommender system bias
session-based recommendation
propensity scoring
popularity stratified
title Session-Based Recommendation Method Using Popularity-Stratified Preference Modeling
title_full Session-Based Recommendation Method Using Popularity-Stratified Preference Modeling
title_fullStr Session-Based Recommendation Method Using Popularity-Stratified Preference Modeling
title_full_unstemmed Session-Based Recommendation Method Using Popularity-Stratified Preference Modeling
title_short Session-Based Recommendation Method Using Popularity-Stratified Preference Modeling
title_sort session based recommendation method using popularity stratified preference modeling
topic recommender system bias
session-based recommendation
propensity scoring
popularity stratified
url https://www.mdpi.com/2227-7390/13/6/960
work_keys_str_mv AT yayelinmo sessionbasedrecommendationmethodusingpopularitystratifiedpreferencemodeling
AT haowenwang sessionbasedrecommendationmethodusingpopularitystratifiedpreferencemodeling