TY  - JOUR
T1  - Study Comparing the Performance of Linear and Non-linear Models in Recommendation Systems
AU  - Seong, Da-Hun 
AU  - Lim, Yujin 
JO  - The Transactions of the Korea Information Processing Society
PY  - 2024
DA  - 2024/2/28
DO  - https://doi.org/10.3745/TKIPS.2024.13.8.388
KW  - Recommendation System
KW  - Collaborative Filltering
KW  - Linear Model
KW  - Non-linear Model
KW  - Performance Evaluation
AB  - 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.