Forecasting of bank sales with Sberbank as a case study

Abstract

Introduction. This scientific study highlights the relevance of modeling and forecasting sales of Sberbank in terms of effective business management. Sales forecast is an important tool for predicting the demand for goods and services, as well as determining the adequate strategies and tactics to achieve the company’s goals. The research is distinguished by its reference to artificial intelligence methods in the field of marketing. Forecasting methods applied to a proprietary data sample of Sberbank’s daily sales give novel results, which reliably supports the development of adequate strategies and tactics for successful business management. The key hypothesis of the study is to check the prognostic potential of machine learning methods against the traditional econometric approaches to modeling Sberbank’s sales.

The purpose of the study is to develop sales forecasting models for multifunctional products and their practical instruments for Sberbank’s Sales Network Block.

Materials and Methods. The study relies on the methods of system-oriented analysis, statistical and economic mathematical methods of data analysis and their processing. Collected and pre-processed sales data for Sberbank’s phantom products reflecting the dynamics of bank sales were used for computational experiments to build a few forecasting models and justify the choice of the best model among those built.

Results. Random Forest and Gradient Busting (XGBRegressor) Models used training and test samples to give the forecasts with the accuracy significantly higher than the accuracy of forecasts by ARIMA-model and linear regression.

Conclusions. The results of the analysis reliably confirm that machine learning methods are currently promising methods for forecasting bank sales and can be the subject of further research in this area. Machine learning techniques introduced into banking practices have the potential to significantly improve the effectiveness of existing sales and risk management.

Keywords: forecasting, sales volume, financial reporting, econometric models, machine learning, statistical methods

For citation

Ermakova A. R., Vasyova G. S. Forecasting of bank sales with Sberbank as a case study. Perm University Herald. Economy, 2024, vol. 19, no. 2, pp. 145–163. DOI 10.17072/1994-9960-2024-2-145-163. EDN UBQMXB.

REFERENCES

1. Bondareva K. I. Ponyatie i sushchnost' prodazhi tovarov v sovremennykh usloviyakh. Ekonomika i sotsium, 2016, no. 6-3 (25), pp. 9–12. (In Russ.). EDN WMTGLJ
2. Zverev O. A. Sistema prodazh bankovskikh produktov kak neot"emlemyi element rynochnogo mekhanizma v bankovskoi sfere. Finance and Credit, 2004, no. 14 (152), pp. 3–9. (In Russ.). EDN HVQOPL
3. Chernov M. V. Ponyatie i sushchnost' protsessa prodazh. Ekonomika i upravlenie: analiz tendentsii i perspektiv razvitiya, 2016, no. 26, pp. 76–79. (In Russ.). EDN VWSGTD
4. Plotnikova A. V., Khashova V. V., Vishnyakova A. B. Prognozirovanie kak element prinyatiya upravlencheskikh reshenii v deyatel'nosti PAO «Sberbank Rossii». Vestnik molodykh uchenykh Samarskogo gosudarstvennogo ekonomicheskogo universiteta, 2018, no. 2 (38), pp. 123–127. (In Russ.). EDN VMOAHK
5. Rudenko I. V. Sales management: Origins, essence, approaches. Herald of Omsk University. Series: Economics, 2012, no. 4, pp. 21–25. (In Russ.). EDN QJCIOZ
6. Mifodovskaya Yu. S. Analiz i prognozirovanie prodazh i zakupok na osnove matematicheskikh modelei dlya torgovykh kompanii. Innovatsii. Nauka. Obrazovanie, 2021, no. 34, pp. 2710–2713. (In Russ.). EDN EEMBSQ
7. Khorzova Ya. A. Primenenie razlichnykh metodov prognozirovaniya ob"ema prodazh. Elektronnyi nauchnyi zhurnal, 2016, no. 4 (7), pp. 596–603. (In Russ.). DOI 10.18534/enj.2016.04.596. EDN WAQCOF
8. Afanas'ev G. I., Afanas'ev A. G., Burmistro-va M. V., Tet V. Ya. S. Issledovanie metodov mashinnogo obucheniya dlya prognozirovaniya effektivnykh biznes-reshenii v sistemakh elektronnoi kommertsii. E-Scio, 2022, no. 11 (74), pp. 1–14. (In Russ.). EDN KCTBIG
9. Valiakhmetova Yu. I., Idrisova E. I. Primenenie metodov mashinnogo obucheniya v oblasti prognozirovaniya ob"ema prodazh s uchetom dinamicheski izmenyayushchikhsya priznakov. StudNet, 2020, vol. 3, no. 10, pp. 98. (In Russ.). EDN GRCMQK
10. Antonov G. V., Ivanov S. I. Linear regression as a method statistical research. Izvestiya Velikolukskoi gosudarstvennoi sel'skokhozyaistvennoi akademii, 2021, no. 2 (35), pp. 64–75. (In Russ.). EDN UNIRWN
11. Ge H., Fang L. Prediction Model of Physical Goods Sales based on Time Series Analysis. Frontiers in Business, Economics and Management, 2022, vol. 5, no. 2, pp. 90–97.
12. Zhang Z. Sales prediction based on ARIMA time series and multifactorial linear model. Highlights in Science, Engineering and Technology, 2023, vol. 38, pp. 1–8. DOI 10.54097/hset.v38i.5680
13. Serdinskaya Yu. A., Mokshin V. V. Ispol'zovanie metodov mashinnogo obucheniya dlya otsenki prognozirovaniya prodazh tovara. Informatika: problemy, metody, tekhnologii (IPMT-2022), Voronezh, 2022, pp. 1062–1068. (In Russ.). EDN NXQUYK
14. Pavlyshenko B. M. Machine-learning models for sales time series forecasting. Data, 2019, vol. 4, no. 1, Article 15. DOI 10.3390/data4010015
15. Zilrahmi M. A. Yu., Putra A. A., Fitri F. Comparison fuzzy time series Cheng and Ruey Chyn Tsaur Model for Forecasting Sales at Empat Saudara Store. UNP Journal of Statistics and Data Science, 2023, vol. 1, no. 3, pp. 218–225. DOI 10.24036/ujsds%2Fvol1-iss3%2F56

Show full text