ATM cash stock prediction using different machine learning approaches

Gökçay, Dursun Ece and Coşkun, Furkan and Yanıkoğlu, Berrin and Turan, Ali and Ertem, Serkan (2020) ATM cash stock prediction using different machine learning approaches. In: 28. IEEE Sinyal İşleme ve İletişim Uygulamaları Kurultayı, Antep, Turkey (Accepted/In Press)

[thumbnail of Poster2050-ATM.pdf] PDF

Download (345kB)


One of the most common problems related to banking systems is the Automated Teller Machine (ATM) cash demand forecasting. Cash shortage adversely affects customer satisfaction, while too much cash reduces bank’s profitability. We have developed an ATM cash prediction system using different statistical and machine learning approaches, including linear regression, artificial neural networks, support vector machines, LSTMs and statistical analysis (ARIMA). We compare the results of these methods and show that machine learning methods in comparison with ARIMA have higher accuracy. Also it was shown that among the machine learning model LSTM gives the most accurate predictions and use less features compared to other models.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: ATM stock prediction, LSTM, regression, machine learning
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Computer Science & Eng.
Center of Excellence in Data Analytics
Faculty of Engineering and Natural Sciences
Depositing User: Berrin Yanıkoğlu
Date Deposited: 05 Oct 2020 16:34
Last Modified: 26 Apr 2022 09:37

Actions (login required)

View Item
View Item