Abstract
Over the last few decades, consumers’ preferences and lifestyles have changed significantly. In such market, the number of products and services aims to mass marketing have become less effective. Therefore, personalization tailored to individual characteristics, certain segments, and one-to-one marketing focusing on individuals are becoming important. Therefore, customer relationship management, retaining existing customers and costs for acquiring new customers are important for both of academic and business field. However, for that purpose, it is essential to grasp customer behavior in more detail and use it for analysis. Therefore, in this study, we estimate the potential clusters of customers and customers’ purchase behavior. Concretely, we use pLSA and XGBoost which become popular machine learning methodologies. In this study, we set the number of store visits per month for objective variable and show a prediction model of it. Then we compare the model that incorporates the result of predicting the probability of the latent cluster as an explanatory variable with the model that incorporates a general explanatory variable.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bucklin, R.E., et al.: Choice and the internet: from clickstream to research stream. Mark. Lett. 13(3), 245–258 (2002). https://doi.org/10.1023/A:1020231107662
Davis, P., Garcés, E.: Quantitative Techniques for Competition and Antitrust Analysis. Princeton University Press, Princeton (2009)
Niimi, J., Hoshino, T.: Predicting the consumers behavior with using the variety of user access patterns. Jpn. J. Appl. Stat. 44(3), 121–143 (2015). (in Japanese)
Niimi, J., Hoshino, T.: Predicting purchases with using the variety of customer behaviors, analysis of the purchase history and the browsing history by deep learning. Trans. Jpn. Soc. Artif. Intell. 32(2B), 1–9 (2017). (in Japanese)
Matsumura, N., Izumi, K., Yamada, K.: A marketing simulation of a retail store with the consumer reactions to out-of-shelf based on a POS data. Jpn. Soc. Artif. Intell. 31(2F), 1–8 (2016). (in Japanese)
Ishigaki, T., Takenaka, T., Motomura, Y.: Customer behavior prediction system by large scale data fusion in a retail service. Jpn. Soc. Artif. Intell. 26(6D), 1–9 (2011). (in Japanese)
Tsukasa, T., Takenaka, T., Motomura, Y.: Improvement of prediction accuracy of the number of customers by latent class model. Jpn. Soc. Artif.Intell. 25(1B3-2), 1–4 (2011). (in Japanese)
Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794 (2016)
Hofmann, T.: Probabilistic latent semantic indexing. In: Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence, pp. 289–296 (1999)
Acknowledgement
This work was supported by JSPS KAKENHI Grant Number 19K01945.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Saito, R., Otake, K., Namatame, T. (2021). Customer Visit Prediction Using Purchase Behavior and Tendency. In: Meiselwitz, G. (eds) Social Computing and Social Media: Applications in Marketing, Learning, and Health. HCII 2021. Lecture Notes in Computer Science(), vol 12775. Springer, Cham. https://doi.org/10.1007/978-3-030-77685-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-77685-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77684-8
Online ISBN: 978-3-030-77685-5
eBook Packages: Computer ScienceComputer Science (R0)