Statistical and Artificial Intelligence Based Forecasting Approaches for Cash Demand Problem of Automated Teller Machines

Abstract

The efficient management of cash replenishment in Automated Teller Machines (ATMs) is a critical concern for banks and financial institutions. This paper explores the application of statistical and artificial intelligence (AI) forecasting methods to address the cash demand problem in ATMs. Recognizing the significance of accurate cash predictions for ensuring uninterrupted ATM services and minimizing operational costs, we investigate various forecasting approaches. Initially, statistical methodologies including Autoregressive Integrated Moving Average (ARIMA) and Seasonal ARIMA (SARIMA) are employed to model and forecast cash demand patterns. Subsequently, machine learning techniques such as Deep Neural Networks (DNN) and Prophet algorithm are leveraged to enhance prediction accuracy. We assess the performance of these methodologies through rigorous analysis and evaluation. Furthermore, the paper delves into the integration of these forecasting approaches within an overall decision support system for ATM cash management. By optimizing cash replenishment strategies based on accurate forecasts, financial institutions aim to simultaneously enhance customer satisfaction and reduce operational expenses. The findings of this study contribute to a comprehensive understanding of how statistical and AI-driven forecasting can revolutionize cash management in ATMs, offering insights for improving the efficiency and cost-effectiveness of ATM services in the banking sector.

Keywords

• Machine Learning
• Forecasting
• ARIMA
• Cash Demand
• Prophet

References

1. Baker, T., Jayaraman, V., Ashley, N. “A Data-Driven Inventory Control Policy for Cash Logistics Operations: An Exploratory Case Study Application at a Financial Institution,” 2013, pp. 205-226.
2. http://www.neural-forecasting-competition.com/NN5/ Retrieved October 19, 2023.
3. Catal, C., Fenerci, A., Ozdemir, B., & Gulmez, O. (2015). Improvement of demand forecasting models with special days. Procedia Computer Science, 59, 262-267.
4. Cedolin, M. and Erol Genevois, M. (2021), "An averaging approach to individual time series employing econometric models: a case study on NN5 ATM transactions data", Kybernetes, 51(9), 2673-2694.
5. Zapranis, A., & Alexandridis, A. (2009). Forecasting cash money withdrawals using wavelet analysis and wavelet neural networks. International Journal of Financial Economics and Econometrics.
6. Garcia-Pedrero, A., & Gomez-Gil, P. (2010, February). Time series forecasting using recurrent neural networks and wavelet reconstructed signals. In 2010 20th International Conference on Electronics Communications and Computers (CONIELECOMP) (pp. 169-173). IEEE.
7. Asad, M., Shahzaib, M., Abbasi, Y., and Rafi, M. “A Long-Short-Term-Memory Based Model for Predicting ATM Replenishment Amount,” in 2020 21st International Arab Conference on Information Technology (ACIT), Information Technology (ACIT), 2020 21st International Arab Conference On, 2020, 1–6. https://doi.org/10.1109/ACIT50332.2020.9300115
8. Serengil, S. I., Özpınar, A., “ATM Cash Flow Prediction and Replenishment Optimization with ANN,” 2019, pp. 402-408.

9. R. G. Anholt, L. C. Coelho, G. Laporte and I. F. A. Vis “An Inventory-Routing Problem with Pickups and Deliveries Aising in the Replenishment of Automated Teller Machines,” 2016, pp. 1077-1091.
10. Bolduc, M.-C., Laporte, G., Renaud, J., and Boctor, F. F. “A tabu search heuristic for the split delivery vehicle routing problem with production and demand calendars,” 2010, European Journal of Operational Research, 202(1), 122–130.
11. Simutis, R., Dilijonas, D., & Bastina, L. (2008). Cash demand forecasting for ATM using neural networks and support vector regression algorithms. 20th International Conference, Euro Mini Conference Continuous Optimization and Knowledge-Based Technologies, 416-421.
12. Simutis, R., Dilijonas, D., Bastina, L., & Friman, J. (2007). A flexible neural network for ATM cash demand forecasting. Cimmacs '07: WSEAS International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics, 163-168.
13. Brentnall, A. R., Crowder, M. J., & Hand, D. J. (2010a). Predicting the amount individuals withdraw at cash machines using a random effects multinomial model. Statistical Modelling, 10(2), 197-214.
14. Teddy, S. D., & Ng, S. K. (2011). Forecasting ATM cash demands using a local learning model of cerebellar associative memory network. International Journal of Forecasting, 27(3), 760-776.
15. Andrawis, R. R., Atiya, A. F., & El-Shishiny, H. (2011). Forecast combinations of computational intelligence and linear models for the NN5 time series forecasting competition. International Journal of Forecasting, 27(3), 672-688.
16. Venkatesh, K., Ravi, V., Prinzie, A., & Van den Poel, D. (2014). Cash demand forecasting in ATMs by clustering and neural networks. European Journal of Operational Research, 232(2), 383-392.
17. Fallahtafti, A., Aghaaminiha, M., Akbarghanadian, S., & Weckman, G. R. (2022). Forecasting ATM cash demand before and during the COVID-19 pandemic using an extensive evaluation of statistical and machine learning models. SN Computer Science, 3(2), 164.
18. Sarveswararao, V., Ravi, V., & Vivek, Y. (2023). ATM cash demand forecasting in an Indian bank with chaos and hybrid deep learning networks. Expert Systems with Applications, 211, 118645.
19. Box, G. E. P., Jenkins, G. M. and Reinsel, G. C. (1994). Time Series Analysis, Forecasting and Control, Prentice Hall, Englewood Cliffs, N.J.
20. Khanarsa, P., Sinapiromsaran, K. “Multiple ARIMA subsequences aggregate time series model to forecast cash in ATM. 9th International Conference on Knowledge and Smart Technology: Crunching Information of Everything,” 2017, 83–88. https://doi.org/10.1109/KST.2017.7886096
21. Gurgul, H., Suder, M. “Modeling of Withdrawals from Selected ATMs of the “Euronet” Network,” 2013, pp. 65-82.
22. Hyndman, R.J., Athanasopoulos, G. “Forecasting: principles and practice,” 2nd edition, 2018, OTexts: Melbourne, Australia. OTexts.com/fpp2. Accessed on 1.06.2022.
23. Venkatesh, K., Ravi, V., esd. “Cash Demand Forecasting in ATMs by Clustering and Neural Networks,” 2014, pp. 383-392.
24. Atsalaki, I. G., Atsalakis, G. S., and Zopounidis, C.D. “Cash withdrawals forecasting by neural networks,” Journal of Computational Optimization in Economics and Finance, 3(2), 2011, pp. 133-142.
25. Taylor, S. J., & Letham, B. “Prophet: Forecasting at scale,” 2017, pp. 37-45.
26. Wang, D., Meng, Y., Chen, S., Xie, C., and Liu, Z. “A Hybrid Model for Vessel Traffic Flow Prediction Based on Wavelet and Prophet,” 2021, pp. 1-16.