inis 18(17): e4

Research Article

Improving Customer Behaviour Prediction with the Item2Item model in Recommender Systems

Download120 downloads
  • @ARTICLE{10.4108/eai.19-12-2018.156079,
        author={T. T. S. Nguyen and P. M. T. Do and T. T. Nguyen},
        title={Improving Customer Behaviour Prediction with the Item2Item model in Recommender Systems},
        journal={EAI Endorsed Transactions on Industrial Networks and Intelligent Systems},
        volume={5},
        number={17},
        publisher={EAI},
        journal_a={INIS},
        year={2018},
        month={12},
        keywords={recommender systems, sequence mining, item2item},
        doi={10.4108/eai.19-12-2018.156079}
    }
    
  • T. T. S. Nguyen
    P. M. T. Do
    T. T. Nguyen
    Year: 2018
    Improving Customer Behaviour Prediction with the Item2Item model in Recommender Systems
    INIS
    EAI
    DOI: 10.4108/eai.19-12-2018.156079
T. T. S. Nguyen1,*, P. M. T. Do1, T. T. Nguyen2
  • 1: School of Computer Science & Engineering, International University, VNU-HCMC, Ho Chi Minh City, Vietnam
  • 2: University of Buckingham, UK
*Contact email: nttsang@hcmiu.edu.vn

Abstract

Recommender Systems are the most well-known applications in E-commerce sites. However, the trade-off between runtime and the accuracy in making recommendations is a big challenge. This work combines several traditional techniques to reduce the limitation of each single technique and exploits the Item2Item model to improve the prediction accuracy. As a case study, this paper focuses on user behaviour prediction in restaurant recommender systems and uses a public dataset including restaurant information and user sessions. Within this dataset, user behaviour can be discovered for the collaborative filtering, and restaurant information is extracted for the content-based filtering. The idea of the pre-trained word embedding in Natural Language Processing is utilized in the item-based collaborative filtering to find the similarity between restaurants based on user sessions. Experimental results have shown that the combination of these techniques makes valuable recommendations.