ATM Withdrawal Amount Forecasting Through Neural Architectures

Date

2019-12-12

Author

Baran, Orhun Bugra
Sunel, Saim
Karagöz, Pınar
Toroslu, İsmail Hakkı

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

193
views

0
downloads

Automated Telling Machines (ATM) are one of the prominent services of the banks, which facilitate daily banking operations. Among the offered services, money withdrawal is a very basic functionality of ATMs. For the banks, it is important to manage the amount of money to be loaded in ATMs. Hence, prediction of the withdrawal amount is an important step in the ATM management. In this work, we investigate the performance of deep learning techniques for ATM money withdrawal amount prediction problem. The problem is defined in two ways: predicting the amount of money to he withdrawn, and predicting the class label of the withdrawal amount. Our data set includes daily total withdrawal amounts together with the date information. In our experiments, we further analyzed the effect of additional information, such as size of history window, weather condition, currency rate and location. For numeric value prediction task, we compared the prediction performance with statistical models of ARIMA and SARIMA. The experiments show that the neural architectures are feasible for the task of withdrawal amount prediction. They can especially provide high accuracy results when the problem is modeled as a class label prediction task.

Subject Keywords

ATM, Prediction, Money withdrawal, Time series data, Neural networks, Banking, Deep learning, Spatial-temporal systems, Location based services

URI

https://hdl.handle.net/11511/46296

DOI

https://doi.org/10.1109/bigdata47090.2019.9006375

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Comparison of integer linear programming and dynamic programming approaches for ATM cash replenishment optimization problem Özer, FaziIle; Toroslu, İsmail Hakkı; Department of Computer Engineering (2019) In Automated Telling Machine (ATM) cash replenishment problem, banks aim to re-duce the number of out-of-cash ATMs and duration of out-of-cash status. On theother hand, they want to reduce the cost of cash replenishment, as well. The problemconventionally involves forecasting ATM cash withdrawals, and then cash replenish-ment optimization on the basis of the forecast. We assume that reliable forecasts arealready obtained for the amount of cash needed in ATMs. The focus of the thesisis cash replenishment opt...
Comparison of Integer Linear Programming and Dynamic Programming Approaches for ATM Cash Replenishment Optimization Problem Ozer, Fazilet; Toroslu, İsmail Hakkı; Karagöz, Pınar (2020-07-01) With the automated teller machine (ATM) cash replenishment problem, banks aim to reduce the number of out-of-cash ATMs and duration of out-of-cash status. On the other hand, they want to reduce the cost of cash replenishment, as well. The problem conventionally involves forecasting ATM cash withdrawals, and then cash replenishment optimization based on the forecast. The authors assume that reliable forecasts are already obtained for the amount of cash needed in ATMs. The focus of the article is cash repleni...
An empirical study on early warning systems for banking sector Boyraz, Mustafa Fatih; Gaygısız Lajunen, Esma; Department of Economics (2012) Early Warning Systems (EWSs) for banking sectors are used to measure occurrence risks of banking crises, generally observed with a rundown of bank deposits and widespread failures of financial institutions. In countries with a small number of banks, for example Turkey with 48 banks (BDDK, 2011), every bank may be considered to have a systematic importance since the failure of any individual bank may carry a potential threat to lead to a banking crisis. Taking into account this fact the present study focuses...
Empirical investigation of internet banking usage: The case of Turkey Daneshgadeh, Salva; Özkan Yıldırım, Sevgi (2014-10-17) This study empirically investigates the factors impacting internet banking (IB) usage by Turkish bank customers. A unique internet banking usage model (IBUM) was developed and validated. The initial proposed model incorporated 10 factors named usefulness, ease of use, control, social influence, compatibility, risk, website features, alliance service, awareness of service and personalization that affect internet banking usage. The initial model was tested against both measurement and structural models. The r...
Dynamic Programming Solution to ATM Cash Replenishment Optimization Problem Karagöz, Pınar; Toroslu, İsmail Hakkı (2018-10-05) Automated Telling Machine (ATM) replenishment is a wellknown problem in banking industry. Banks aim to improve customer satisfaction by reducing the number of out-of-cash ATMs and duration of out-of-cash status. On the other hand, they want to reduce the cost of cash replenishment, also. The problem conventionally has two components: forecasting ATM cash withdrawals, and then cash replenishment optimization on the basis of the forecast. In this work, for the first component, it is assumed that reliable fore...

Citation Formats

O. B. Baran, S. Sunel, P. Karagöz, and İ. H. Toroslu, “ATM Withdrawal Amount Forecasting Through Neural Architectures,” 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/46296.