A Systematic Literature Analysis On Cash Forecasting Problems In ATMs

Abstract

Automated Teller Machines, ATM’s, constitute one of the most important service branches of the banking sector. During COVID-19, banks shifted many in-branch transactions to these machines and encouraged the use of this contactless service point by increasing the deposit and withdrawal limits. Demand forecasts for cash flows in these machines create a challenging process with high added value as they target cash directly. The contradictory objectives of the problem are that if the cash is not available, the customer need cannot be met, but the stocked money may not evaluated in any investment instrument. Within the scope of this study, the studies on ATM demand forecasting are classified under various topics such as data structure, forecasting method, alternative models, forecasting horizon, and the backgrounds for future studies are prepared by stating untouched points. Especially, it has been observed that machine learning methods are widely used in the literature and their results are compared with the outcomes of the statistical forecasting techniques. Most of the studies employ a common public data set and provide comparable results. To the best of our knowledge, this study is the first literature review in this field, and also marks an area that has not been addressed yet in our country. Purpose: Review of the literature relevant to the ATMs forecasting studies, their classification and providing a roadmap for further studies in this area. Method: Systematic literature review, classification of the articles, selection of the criteria and analyze by the selected criteria. Findings: Presence of 32 papers on the ATM forecasting literature, employ of the common public data sets, widely utilization of the machine learning models, and detection of the use of statistical forecasting model results as the benchmark values. Originality: Being the first systematic review and analysis article on this area.

Keywords

• ATM Management
• Cash Management
• Demand Forecasting
• Financial Optimization

ATM’LERDEKİ NAKİTE YÖNELİK TALEP TAHMİNİ ÜZERİNE SİSTEMATİK YAZIN ANALİZİ

Abstract

Otomatik Vezne Makineleri, yaygın kullanılan ismi ile ATM’ler, bankacılık sektörünün en önemli servis kollarından birini oluşturmaktadır. Özellikle COVID-19 sürecinde, bankalar birçok şube içi işlemi bu makinelere kaydırmış, para çekme ve yatırma limitleri arttırılarak bu temassız servis noktasının kullanımını teşvik etmiştir. Bu makinelerde gerçekleşen nakit akışlarına yönelik yapılan talep tahminleri, herhangi bir üründen ziyade direk olarak nakit parayı hedef aldığından, katma değeri yüksek zorlu bir süreci oluşturmakla beraber; problemin karşıt amaçlarını ise, yeterli miktarda nakit bulunmaması durumunda müşteri ihtiyacının giderilememesi ve buna karşılık makine içerisindeki paranın banka tarafından herhangi bir yatırım aracında değerlendirilmemesi oluşturmaktadır. Bu çalışma kapsamında, günümüze kadar ATM talep tahmini üzerine yapılmış çalışmalar, veri yapısı, tahmin yöntemi, karşılaşılan sıkıntılar, alternatif modeller, tahmin dönemi gibi çeşitli başlıklarda sınıflandırılmakta, henüz değinilmemiş noktalar belirtilerek bundan sonraki çalışmalara zemin hazırlanmaktadır. Özellikle talep tahmininde makine öğrenmesi yöntemlerinin yaygın olarak kullanıldığı ve bu yöntemlerin sonuçlarının istatistiksel tahmin yöntemleri çıktıları ile karşılaştırıldığı tespit edilmiştir. Çalışmaların büyük bir çoğunluğu ortak bir açık veri seti kullanmakta ve karşılaştırılabilir sonuçlar sunmaktadır. Bildiğimiz kadarı ile bu çalışma, tasvir ettiğimiz alanda yapılan ilk yazın taraması olmakta, aynı zamanda ülkemizde henüz üzerinde durulmamış bir alanı işaret etmektedir. Amaç: ATM’lerle ilgili mevcut talep tahmini yazının taranması, sınıflandırılması ve bu alandaki çalışmalar için yol haritası oluşturması. Yöntem: Sistematik yayın taraması, makalelerin sınıflandırılması, kriterlerinin seçilmesi ve buna göre sınıflandırılıp analiz edilmesi. Bulgular: ATM talep tahmini alanında 32 çalışmanın varlığı, ortak açık veri setlerinin kullanıldığı, yaygın olarak makine öğrenme metotlarının uygulandığı ve istatistiksel talep tahmin modellerinin karşılaştırma ölçütü olarak sunulduğunun tespiti. Özgünlük: Bu alanda yapılan ilk sistematik yazın taraması ve analizi olması.

Keywords

• ATM Yönetimi
• Nakit Yönetimi
• Talep Tahmini
• Finansal Optimizasyon

References

1. Acuna, G., Ramirez, C., & Curilem, M. (2012). Comparing NARX and NARMAX models using ANN and SVM for cash demand forecasting for ATM. IEEE 2012 International Joint Conference on Neural Networks, 1-6.
2. 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.
3. Arabani, S. P., & Komleh, H. E. (2019). The Improvement of Forecasting ATMs Cash Demand of Iran Banking Network Using Convolutional Neural Network. Arabian Journal for Science and Engineering, 44(4), 3733-3743.
4. Arora, N., & Saini, J. K. R. (2014). Approximating methodology: Managing cash in automated teller machines using fuzzy ARTMAP network. International Journal of Enhanced Research in Science Technology & Engineering, 3(2), 318-326.
5. Aseev, M., Nemeshaev, S., & Nesterov, A. (2016). Forecasting cash withdrawals in the ATM network using a combined model based on the holt-winters method and markov chains. International Journal of Applied Engineering Research, 11(11), 7577-7582.
6. Atsalaki, I. G., Atsalakis, G. S., & Zopounidis, C.D. (2011). Cash withdrawals forecasting by neural networks. Journal of Computational Optimization in Economics and Finance, 3(2), 133-142.
7. Brentnall, A. R., Crowder, M. J., & Hand, D. J. (2008). A statistical model for the temporal pattern of individual automated teller machine withdrawals. Journal of the Royal Statistical Society Series C-Applied Statistics, 57, 43-59.
8. 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.

9. Brentnall, A. R., Crowder, M. J., & Hand, D. J. (2010b). Predictive-sequential forecasting system development for cash machine stocking. International Journal of Forecasting, 26(4), 764-776.
10. Catal, C., Fenerci, A., Ozdemir, B., & Gulmez, O. (2015). Improvement of demand forecasting models with special days. Procedia Computer Science, 59, 262-267.
11. Darwish, S.M. (2013). A Methodology to Improve Cash Demand Forecasting for ATM Network. International Journal of Computer and Electrical Engineering, 5(4), 405-409.
12. Dilijonas, D., & Sakalauskas, V. (2011). Self-service Systems Performance Evaluation and Improvement Model. Conference on e-Business, e-Services and e-Society, 87-98.
13. Garcia-Pedrero, A., & Gomez-Gil, P. (2010). Time series forecasting using recurrent neural networks and wavelet reconstructed signals. IEEE 2010 20th International Conference on Electronics Communications and Computers (CONIELECOMP), 169-173.
14. Gurgul, H., & Suder, M. (2013). Modeling of Withdrawals from Selected ATMs of the Euronet Network. AGH Managerial Economics, 13, 65–82.
15. Jadwal, P. K., Jain, S., Gupta, U., & Khanna, P. (2017). K-Means clustering with neural networks for ATM cash repository prediction. International Conference on Information and Communication Technology for Intelligent Systems, 588-596.
16. Kamini, V., Ravi, V., & Kumar, D. N. (2014). Chaotic time series analysis with neural networks to forecast cash demand in ATMs. 2014 IEEE International Conference on Computational Intelligence and Computing Research, 1-5.
17. Khanarsa, P., & Sinapiromsaran, K. (2017). Multiple ARIMA subsequences aggregate time series model to forecast cash in ATM. IEEE 9th International Conference on Knowledge and Smart Technology (KST), 83-88.
18. Kumar, P., & Walia, E. (2006). Cash Forecasting: An Application of Artificial Neural Networks in Finance. IJCSA, 3(1), 61-77.
19. Nemeshaev, S., & Tsyganov, A. (2016). Model of the forecasting cash withdrawals in the ATM network. Procedia Computer Science, 88, 463-468.
20. Paul, J., & Mukherjee, A. (2010). ATMs and cash demand forecasting: A study of two commercial banks. Journal of Regional Development, 2(2), 653-671.
21. Perera, K., & Hewage, U. (2018). Determinants of Automated Teller Machine Loading Demand Requirements in Sri Lankan Cash Supply Chains. IEEE International Conference on Production and Operations Management Society (POMS), 1-7.
22. Rajwanı, A., Syed, T., Khan, B., & Behlim, S. (2017). Regression analysis for ATM cash flow prediction. IEEE International Conference on in Frontiers of Information Technology (FIT), 212-217.
23. Ramírez C., & Acuña G. (2011). Forecasting Cash Demand in ATM Using Neural Networks and Least Square Support Vector Machine. In San Martin C., & Kim SW. (Eds.), Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25085-9_61
24. Rodrigues, P., & Esteves, P. (2010). Calendar effects in daily ATM withdrawals. Economics Bulletin, 30(4), 2587-2597.
25. Simutis, R., Dilijonas, D., Bastina, L., & Friman, J. (2007). A flexible neural network for ATM cash demand forecasting. International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics, 163-168.
26. Simutis, R., Dilijonas, D., & Bastina, L. (2008). Cash demand forecasting for ATM using neural networks and support vector regression algorithms. Euro Mini Conference Continuous Optimization and Knowledge-Based Technologies, 416-421.
27. 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
28. Van Anholt, R. G., & Vis, I. F. (2010). An integrative online ATM forecasting and replenishment model with a target fill rate. Proceedings of The International Conference on Logistics and Maritime Systems, 1-10.
29. 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.
30. Wagner, M. (2010). Forecasting daily demand in cash supply chains. American Journal of Economics and Business Administration, 2(4), 377-383.
31. Wichard, J. D. (2011). Forecasting the NN5 time series with hybrid models. International Journal of Forecasting, 27(3), 700-707.
32. Zapranis, A., & Alexandridis, A. (2009). Forecasting cash money withdrawals using wavelet analysis and wavelet neural networks. International Journal of Financial Economics and Econometrics. ISSN 0975-2072.