RecNet: A Resource-Constraint Aware Neural Network for Used Car Recommendation
Abstract Resource constraints, e.g., limited product inventory or financial strength, may affect consumers’ choices or preferences in some recommendation tasks but are usually ignored in previous recommendation methods. In this paper, we aim to mine the cue of user preferences or intention in the ca...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer
2022-10-01
|
Series: | International Journal of Computational Intelligence Systems |
Subjects: | |
Online Access: | https://doi.org/10.1007/s44196-022-00155-9 |
_version_ | 1797984686561034240 |
---|---|
author | Haihua Shi Jianjun Qian Nengjun Zhu Tong Zhang Zhen Cui Qianliang Wu Shanshan Feng |
author_facet | Haihua Shi Jianjun Qian Nengjun Zhu Tong Zhang Zhen Cui Qianliang Wu Shanshan Feng |
author_sort | Haihua Shi |
collection | DOAJ |
description | Abstract Resource constraints, e.g., limited product inventory or financial strength, may affect consumers’ choices or preferences in some recommendation tasks but are usually ignored in previous recommendation methods. In this paper, we aim to mine the cue of user preferences or intention in the case of resource-constraint recommendation tasks. For this purpose, we specifically build a largely used car transaction dataset possessing resource-constraint characteristics. Accordingly, we propose a resource-constraint-aware network to predict the user’s future interaction based on dynamic connections between users and items. To describe the user-item connection dynamically, mutually recursive recurrent neural networks (MRRNNs) are introduced to capture long-term interactive dependencies, and effective representations of users and items are obtained. To further consider the resource constraint, a resource-constraint branch is built to explore resource variation’s influence on user preferences. Finally, mutual information is introduced to measure the similarity between the future user action and fused historical behavior features to predict future interaction. The fused features come from both MRRNNs and resource-constraint branches. We test the performance on the built used car transaction dataset and the Tmall dataset, and the experimental results verify the effectiveness of our framework. |
first_indexed | 2024-04-11T07:07:02Z |
format | Article |
id | doaj.art-9b9de3df81a648e282243845f002f3ad |
institution | Directory Open Access Journal |
issn | 1875-6883 |
language | English |
last_indexed | 2024-04-11T07:07:02Z |
publishDate | 2022-10-01 |
publisher | Springer |
record_format | Article |
series | International Journal of Computational Intelligence Systems |
spelling | doaj.art-9b9de3df81a648e282243845f002f3ad2022-12-22T04:38:22ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832022-10-0115111010.1007/s44196-022-00155-9RecNet: A Resource-Constraint Aware Neural Network for Used Car RecommendationHaihua Shi0Jianjun Qian1Nengjun Zhu2Tong Zhang3Zhen Cui4Qianliang Wu5Shanshan Feng6Jinling Institute of TechnologyKey Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing University of Science and TechnologySchool of Computer Engineering and Science, Shanghai UniversityKey Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing University of Science and TechnologyKey Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing University of Science and TechnologyKey Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing University of Science and TechnologySchool of Information Science and Engineering, Shandong Normal UniversityAbstract Resource constraints, e.g., limited product inventory or financial strength, may affect consumers’ choices or preferences in some recommendation tasks but are usually ignored in previous recommendation methods. In this paper, we aim to mine the cue of user preferences or intention in the case of resource-constraint recommendation tasks. For this purpose, we specifically build a largely used car transaction dataset possessing resource-constraint characteristics. Accordingly, we propose a resource-constraint-aware network to predict the user’s future interaction based on dynamic connections between users and items. To describe the user-item connection dynamically, mutually recursive recurrent neural networks (MRRNNs) are introduced to capture long-term interactive dependencies, and effective representations of users and items are obtained. To further consider the resource constraint, a resource-constraint branch is built to explore resource variation’s influence on user preferences. Finally, mutual information is introduced to measure the similarity between the future user action and fused historical behavior features to predict future interaction. The fused features come from both MRRNNs and resource-constraint branches. We test the performance on the built used car transaction dataset and the Tmall dataset, and the experimental results verify the effectiveness of our framework.https://doi.org/10.1007/s44196-022-00155-9Recommender systemResource constraintRecurrent neural networks(RNNs)Mutual information |
spellingShingle | Haihua Shi Jianjun Qian Nengjun Zhu Tong Zhang Zhen Cui Qianliang Wu Shanshan Feng RecNet: A Resource-Constraint Aware Neural Network for Used Car Recommendation International Journal of Computational Intelligence Systems Recommender system Resource constraint Recurrent neural networks(RNNs) Mutual information |
title | RecNet: A Resource-Constraint Aware Neural Network for Used Car Recommendation |
title_full | RecNet: A Resource-Constraint Aware Neural Network for Used Car Recommendation |
title_fullStr | RecNet: A Resource-Constraint Aware Neural Network for Used Car Recommendation |
title_full_unstemmed | RecNet: A Resource-Constraint Aware Neural Network for Used Car Recommendation |
title_short | RecNet: A Resource-Constraint Aware Neural Network for Used Car Recommendation |
title_sort | recnet a resource constraint aware neural network for used car recommendation |
topic | Recommender system Resource constraint Recurrent neural networks(RNNs) Mutual information |
url | https://doi.org/10.1007/s44196-022-00155-9 |
work_keys_str_mv | AT haihuashi recnetaresourceconstraintawareneuralnetworkforusedcarrecommendation AT jianjunqian recnetaresourceconstraintawareneuralnetworkforusedcarrecommendation AT nengjunzhu recnetaresourceconstraintawareneuralnetworkforusedcarrecommendation AT tongzhang recnetaresourceconstraintawareneuralnetworkforusedcarrecommendation AT zhencui recnetaresourceconstraintawareneuralnetworkforusedcarrecommendation AT qianliangwu recnetaresourceconstraintawareneuralnetworkforusedcarrecommendation AT shanshanfeng recnetaresourceconstraintawareneuralnetworkforusedcarrecommendation |