@article{MF37E1600,
title = "Study Comparing the Performance of Linear and Non-linear Models in Recommendation Systems",
journal = "The Transactions of the Korea Information Processing Society",
year = "2024",
issn = "null",
doi = "https://doi.org/10.3745/TKIPS.2024.13.8.388",
author = "Da-Hun Seong, Yujin Lim",
keywords = "Recommendation System, Collaborative Filltering, Linear Model, Non-linear Model, Performance Evaluation",
abstract = "Since recommendation systems play a key role in increasing the revenue of companies, various approaches and models 
have been studied in the past. However, this diversity also leads to a complexity in the types of recommendation systems, 
which makes it difficult to select a recommendation model. Therefore, this study aims to solve the difficulty of selecting 
an appropriate recommendation model for recommendation systems by providing a unified criterion for categorizing various 
recommendation models and comparing their performance in a unified environment. The experiments utilized MovieLens 
and Coursera datasets, and the performance of linear models(ADMM-SLIM, EASER, LightGCN) and non-linear models(Caser, 
BERT4Rec) were evaluated using HR@10 and NDCG@10 metrics. This study will provide researchers and practitioners with 
useful information for selecting the best model based on dataset characteristics and recommendation context."
}