Abstract
Nowadays, the task of forecasting the client’s behavior using his/her digital footprints is highly demanded. There are many approaches to predict the client’s next purchase or the next location visited that focus on achieving the best possible prediction quality in terms of different quality metrics. Within such approaches, the quality is however usually evaluated on the entire set of clients, without dividing them into classes with a different predictability rate of client’s behavior. In contrast to the approaches of this type, we propose a method for the identification of the client’s behaviour predictability class by means of a foreign trip in the next month by using only client’s historical transactional data. In a sense, this allows us to estimate the quality of forecasting the client’s foreign trip before the actual prediction procedure. Our experiments show that the approach is rather efficient and that the predictability classes obtained quite agree with the prediction quality classes found within the actual forecasting.
This research was financially supported by the Russian Science Foundation, Agreement 17-71-30029 with co-financing of Bank Saint Petersburg.
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
Similar content being viewed by others
Change history
09 June 2021
The chapter was inadvertently published with incomplete funding information in the acknowledgment. The missing funding information is now added and the chapter has been updated with the changes.
References
Chen, S.H., Navet, N.: Failure of genetic-programming induced trading strategies: Distinguishing between efficient markets and inefficient algorithms. In: Chen, S.H., Wang, P.P., Kuo, T.W. (eds.) Computational Intelligence in Economics and Finance, pp. 169–182. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-72821-4_11
Clements, M., Hendry, D.: Forecasting Economic Time Series. Cambridge University Press (1998)
Duan, M.: Time series predictability. Ph.D. thesis, Marquette University (2002)
Gama, J.a., Žliobaitundefined, I., Bifet, A., Pechenizkiy, M., Bouchachia, A.: A survey on concept drift adaptation. ACM Comput. Surv. 46(4) (2014). https://doi.org/10.1145/2523813
Gers, F.A., Schraudolph, N.N., Schmidhuber, J.: Learning precise timing with LSTM recurrent networks. J. Mach. Learn. Res. 3, 115–143 (2002)
Goerg, G.: Forecastable component analysis. In: International Conference on Machine Learning, pp. 64–72 (2013)
Janardan, Mehta, S.: Concept drift in streaming data classification: algorithms, platforms and issues. Procedia Comput. Sci. 122, 804–811 (2017). 5th International Conference on Information Technology and Quantitative Management, ITQM 2017
Javed, K., Gouriveau, R., Zemouri, R., Zerhouni, N.: Features selection procedure for prognostics: an approach based on predictability. IFAC Proc. Vol. 45(20), 25–30 (2012)
Kaboudan, M.: A measure of time series’ predictability using genetic programming applied to stock returns. J. Forecast. 18(5), 345–357 (1999)
Krawczyk, B., Minku, L.L., Gama, J., Stefanowski, J., Woźniak, M.: Ensemble learning for data stream analysis: a survey. Inf. Fusion 37, 132–156 (2017)
Mehmood, H., Kostakos, P., Cortes, M., Anagnostopoulos, T., Pirttikangas, S., Gilman, E.: Concept drift adaptation techniques in distributed environment for real-world data streams. Smart Cities 4(1), 349–371 (2021)
Moon, G., Hamm, J.: A large-scale study in predictability of daily activities and places. In: MobiCASE, pp. 86–97 (2016)
Peña, D., Sánchez, I.: Measuring the advantages of multivariate vs. univariate forecasts. J. Time Ser. Anal. 28(6), 886–909 (2007)
Prelipcean, G., Popoviciu, N., Boscoianu, M.: The role of predictability of financial series in emerging market applications. In: Proceedings of the 9th WSEAS International Conference on Mathematics & Computers in Business and Economics, MCBE 2008, pp. 203–208 (2008)
Richthofer, S., Wiskott, L.: Predictable feature analysis. In: 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), pp. 190–196. IEEE (2015)
Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673–2681 (1997)
Stavinova, E., Bochenina, K.: Forecasting of foreign trips by transactional data: a comparative study. Procedia Comput, Sci. 156, 225–234 (2019)
Teodorescu, H.N., Fira, L.I.: Analysis of the predictability of time series obtained from genomic sequences by using several predictors. J. Intelli. Fuzzy Syst. 19(1), 51–63 (2008)
Vaganov, D., Funkner, A., Kovalchuk, S., Guleva, V., Bochenina, K.: Forecasting purchase categories with transition graphs using financial and social data. In: Staab, S., Koltsova, O., Ignatov, D.I. (eds.) SocInfo 2018. LNCS, vol. 11185, pp. 439–454. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01129-1_27
Wang, W., Van Gelder, P.H., Vrijling, J.: Measuring predictability of daily streamflow processes based on univariate time series model. In: Proceedings of the iEMSs 4th Biennial Meeting - International Congress on Environmental Modelling and Software: Integrating Sciences and Information Technology for Environmental Assessment and Decision Making, iEMSs 2008, pp. 1378–1385 (2008)
Wilson, G., Banzhaf, W.: Fast and effective predictability filters for stock price series using linear genetic programming. In: IEEE Congress on Evolutionary Computation. pp, 1–8. IEEE (2010)
Wiskott, L., Sejnowski, T.J.: Slow feature analysis: Unsupervised learning of invariances. Neural Comput. 14(4), 715–770 (2002)
Yeo, I.K., Johnson, R.A.: A new family of power transformations to improve normality or symmetry. Biometrika 87(4), 954–959 (2000)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Stavinova, E., Bochenina, K., Chunaev, P. (2021). Predictability Classes for Forecasting Clients Behavior by Transactional Data. In: Paszynski, M., Kranzlmüller, D., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M. (eds) Computational Science – ICCS 2021. ICCS 2021. Lecture Notes in Computer Science(), vol 12744. Springer, Cham. https://doi.org/10.1007/978-3-030-77967-2_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-77967-2_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77966-5
Online ISBN: 978-3-030-77967-2
eBook Packages: Computer ScienceComputer Science (R0)