Abstract
Studies of debit market clearly show the existence of different stages of debit card user experience. These stages are related not only to a frequency of transactions but also to a range of adopted purchase categories. Given the history of transactions, one can identify for a user to which cluster (in terms of similar purchase interests) he or she belongs, and, thus, to refine probabilities of purchases in different categories. Moreover, possible trajectories of a user in a state space may be additionally tuned using the information about his or her socioeconomic strata. In this study, we consider a problem of purchase categories prediction from the perspective of state-transition modeling. Being defined by fixed amount of transactions (n-grams) or fixed time period (vectors of frequencies), states of customers are represented as weighted directed graph with clusters corresponding to different patterns of spending behavior. The procedure of forecasting assigns the user to one of the identified clusters and simulates the continuation of spending as evolutionary process. The experimental study of proposed approach was performed on the anonymized dataset of expenses of clients of large regional Russian bank.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In frames of this study, we use amounts of payments only for dividing the users to groups with different levels of average monthly turnover.
- 2.
For example, there exist special-purpose cards for spending on children’s needs.
- 3.
94% of transactions of this category are cash withdrawal operations.
References
Bunn, M., Colvin, B., Pittier, C., Zanghi, A.: Understanding how consumers adopt a debit card payment preference (2012). https://www.mastercardadvisors.com
Oliver, R.L.: Whence consumer loyalty? J. Market. 63, 33–44 (1999)
Joshi, Y., Rahman, Z.: Factors affecting green purchase behaviour and future research directions. Int. Strat. Manag. Rev. 3(1–2), 128–143 (2015)
Westbrook, R.A., Oliver, R.L.: The dimensionality of consumption emotion patterns and consumer satisfaction. J. Consum. Res. 18(1), 84–91 (1991)
Wang, G., Dou, W., Zhou, N.: Consumption attitudes and adoption of new consumer products: a contingency approach. Eur. J. Market. 42(1/2), 238–254 (2008)
Lee, D., Park, J., Ahn, J.-H.: On the explanation of factors affecting e-commerce adoption. In: ICIS 2001 Proceedings, p. 14 (2001)
Leo, Y., Karsai, M., Sarraute, C., Fleury, E.: Correlations and dynamics of consumption patterns in social-economic networks. Soc. Netw. Anal. Min. 8(1), 9 (2018)
Cumby, C., Fano, A., Ghani, R., Krema, M.: Predicting customer shopping lists from point-of-sale purchase data. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 402–409 (2004)
Cadez, I.V., Smyth, P., Ip, E., Mannila, H.: Predictive profiles for transaction data using finite mixture models, Technical report. UCI-ICS 01–67 (2001)
Baldassini, L., Serrano, J.A.R.: client2vec: towards systematic baselines for banking applications, arXiv Preprint. arXiv:1802.04198 (2018)
Wen, Y.-T., Yeh, P.-W., Tsai, T.-H., Peng, W.-C., Shuai, H.-H.: Customer purchase behavior prediction from payment datasets. In: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 628–636 (2018)
Manzoor, E., Akoglu, L.: RUSH!: targeted time-limited coupons via purchase forecasts. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1923–1931 (2017)
Leo, Y., Karsai, M., Sarraute, C., Fleury, E.: Correlations of consumption patterns in social-economic networks. In: 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 493–500 (2016)
Milton, L., Robbins, B., Memon, A.: N-Gram-based user behavioral model for continuous user authentication, vol. c, pp. 43–49 (2014)
Volkovich, Z., Kirzhner, V., Bolshoy, A., Nevo, E., Korol, A.: The method of N-grams in large-scale clustering of DNA texts. Pattern Recognit 38(11), 1902–1912 (2005)
Damavandi, B., Kumar, S., Shazeer, N., Bruguier, A.: NN-grams: unifying neural network and n-gram language models for speech recognition. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2016, 08–12 September, pp. 3499–3503 (2016)
Miao, Y., Kešelj, V., Milios, E.: Document clustering using character N-grams: a comparative evaluation with term-based and word-based clustering. In: Proceedings of the 14th ACM International Conference on Information and Knowledge Management, pp. 357–358 (2005)
Ray, S., Turi, R.H.: Determination of number of clusters in k-means clustering and application in colour image segmentation. In: Proceedings of the 4th International Conference on Advances in Pattern Recognition and Digital Techniques, pp. 137–143 (1999)
Acknowledgements
This research is financially supported by The Russian Science Foundation, Agreement #17-71-30029 with co-financing of Bank Saint Petersburg.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Vaganov, D., Funkner, A., Kovalchuk, S., Guleva, V., Bochenina, K. (2018). Forecasting Purchase Categories with Transition Graphs Using Financial and Social Data. In: Staab, S., Koltsova, O., Ignatov, D. (eds) Social Informatics. SocInfo 2018. Lecture Notes in Computer Science(), vol 11185. Springer, Cham. https://doi.org/10.1007/978-3-030-01129-1_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-01129-1_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01128-4
Online ISBN: 978-3-030-01129-1
eBook Packages: Computer ScienceComputer Science (R0)