The search functionality is under construction.
IEICE TRANSACTIONS on Information
Open Access
A Personalised Session-Based Recommender System with Sequential Updating Based on Aggregation of Item Embeddings
-
Full Text Views
96
- Cite this
- Free PDF (7MB)
Summary :
The study proposes a personalised session-based recommender system that embeds items by using Word2Vec and sequentially updates the session and user embeddings with the hierarchicalization and aggregation of item embeddings. To process a recommendation request, the system constructs a real-time user embedding that considers users’ general preferences and sequential behaviour to handle short-term changes in user preferences with a low computational cost. The system performance was experimentally evaluated in terms of the accuracy, diversity, and novelty of the ranking of recommended items and the training and prediction times of the system for three different datasets. The results of these evaluations were then compared with those of the five baseline systems. According to the evaluation experiment, the proposed system achieved a relatively high recommendation accuracy compared with baseline systems and the diversity and novelty scores of the proposed system did not fall below 90% for any dataset. Furthermore, the training times of the Word2Vec-based systems, including the proposed system, were shorter than those of FPMC and GRU4Rec. The evaluation results suggest that the proposed recommender system succeeds in keeping the computational cost for training low while maintaining high-level recommendation accuracy, diversity, and novelty.
- Publication
- IEICE TRANSACTIONS on Information Vol.E107-D No.5 pp.638-649
- Publication Date
- 2024/05/01
- Publicized
- 2024/01/09
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2023DAP0006
- Type of Manuscript
- Special Section PAPER (Special Section on Data Engineering and Information Management)
- Category
Authors
Yuma NAGI
UNICORN Inc.
Kazushi OKAMOTO
The University of Electro-Communications
Keyword
Latest Issue
Contents
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yuma NAGI, Kazushi OKAMOTO, "A Personalised Session-Based Recommender System with Sequential Updating Based on Aggregation of Item Embeddings" in IEICE TRANSACTIONS on Information,
vol. E107-D, no. 5, pp. 638-649, May 2024, doi: 10.1587/transinf.2023DAP0006.
Abstract: The study proposes a personalised session-based recommender system that embeds items by using Word2Vec and sequentially updates the session and user embeddings with the hierarchicalization and aggregation of item embeddings. To process a recommendation request, the system constructs a real-time user embedding that considers users’ general preferences and sequential behaviour to handle short-term changes in user preferences with a low computational cost. The system performance was experimentally evaluated in terms of the accuracy, diversity, and novelty of the ranking of recommended items and the training and prediction times of the system for three different datasets. The results of these evaluations were then compared with those of the five baseline systems. According to the evaluation experiment, the proposed system achieved a relatively high recommendation accuracy compared with baseline systems and the diversity and novelty scores of the proposed system did not fall below 90% for any dataset. Furthermore, the training times of the Word2Vec-based systems, including the proposed system, were shorter than those of FPMC and GRU4Rec. The evaluation results suggest that the proposed recommender system succeeds in keeping the computational cost for training low while maintaining high-level recommendation accuracy, diversity, and novelty.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023DAP0006/_f
Copy
@ARTICLE{e107-d_5_638,
author={Yuma NAGI, Kazushi OKAMOTO, },
journal={IEICE TRANSACTIONS on Information},
title={A Personalised Session-Based Recommender System with Sequential Updating Based on Aggregation of Item Embeddings},
year={2024},
volume={E107-D},
number={5},
pages={638-649},
abstract={The study proposes a personalised session-based recommender system that embeds items by using Word2Vec and sequentially updates the session and user embeddings with the hierarchicalization and aggregation of item embeddings. To process a recommendation request, the system constructs a real-time user embedding that considers users’ general preferences and sequential behaviour to handle short-term changes in user preferences with a low computational cost. The system performance was experimentally evaluated in terms of the accuracy, diversity, and novelty of the ranking of recommended items and the training and prediction times of the system for three different datasets. The results of these evaluations were then compared with those of the five baseline systems. According to the evaluation experiment, the proposed system achieved a relatively high recommendation accuracy compared with baseline systems and the diversity and novelty scores of the proposed system did not fall below 90% for any dataset. Furthermore, the training times of the Word2Vec-based systems, including the proposed system, were shorter than those of FPMC and GRU4Rec. The evaluation results suggest that the proposed recommender system succeeds in keeping the computational cost for training low while maintaining high-level recommendation accuracy, diversity, and novelty.},
keywords={},
doi={10.1587/transinf.2023DAP0006},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - A Personalised Session-Based Recommender System with Sequential Updating Based on Aggregation of Item Embeddings
T2 - IEICE TRANSACTIONS on Information
SP - 638
EP - 649
AU - Yuma NAGI
AU - Kazushi OKAMOTO
PY - 2024
DO - 10.1587/transinf.2023DAP0006
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E107-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2024
AB - The study proposes a personalised session-based recommender system that embeds items by using Word2Vec and sequentially updates the session and user embeddings with the hierarchicalization and aggregation of item embeddings. To process a recommendation request, the system constructs a real-time user embedding that considers users’ general preferences and sequential behaviour to handle short-term changes in user preferences with a low computational cost. The system performance was experimentally evaluated in terms of the accuracy, diversity, and novelty of the ranking of recommended items and the training and prediction times of the system for three different datasets. The results of these evaluations were then compared with those of the five baseline systems. According to the evaluation experiment, the proposed system achieved a relatively high recommendation accuracy compared with baseline systems and the diversity and novelty scores of the proposed system did not fall below 90% for any dataset. Furthermore, the training times of the Word2Vec-based systems, including the proposed system, were shorter than those of FPMC and GRU4Rec. The evaluation results suggest that the proposed recommender system succeeds in keeping the computational cost for training low while maintaining high-level recommendation accuracy, diversity, and novelty.
ER -
English
Sign In[Non-Member]
