Effectiveness of ATM withdrawal forecasting methods under different market conditions

Bibliographic Data

ID21401474
AuthorsMarcin Suder (0000-0001-6279-7359, Jagiellonian University, corresponding author), Henryk Gurgul (0000-0002-6192-2995, Jagiellonian University), B Barbosa (0000-0002-4057-360X, Universidade do Porto), Artur Machno (0000-0002-6692-1385, Jagiellonian University), Łukasz Lach (0000-0001-8599-1162, Jagiellonian University)
Year2024
Volume200
Pages123089
Publication date2024-03-01
Open AccessYes
TypeARTICLE
VenueTechnological Forecasting and Social Change (JOURNAL)
Journal identifiersISSN: 0040-1625 • E-ISSN: 1873-5509
PublisherElsevier BV (PUBLISHER)
DOI10.1016/j.techfore.2023.123089
OpenAlexW4390428411
LanguageEN
References cited47

This study aims to test the forecasting accuracy of recently implemented econometric tools as compared to the forecasting accuracy of widely used traditional models when predicting cash demand at ATMs. It also aims to verify whether the pandemic-driven change in market conditions impacted the predictive power of the tested models. Our conclusions were derived based on a data set that consisted of daily withdrawals from 61 ATMs of one of the largest European ATM networks operating in Krakow, Poland, and covered the period between January 2017 and April 2021. The results proved that the recently implemented methods of forecasting ATM withdrawals were more accurate as compared to the traditional ones, with XGBoost providing the best forecasts in the majority of the tested cases. Moreover, it was found that the pandemic-driven change in market conditions affected the predictive power of the models. Both of these results seem particularly useful for improving the efficiency of ATM networks

Cash · Coronavirus disease 2019 (COVID-19) · Econometric model · Econometrics · Economics · Operations research · Predictive power · Complex Systems and Time Series Analysis · Computer Science · Engineering · Finance · Innovation Diffusion and Forecasting · Stock Market Forecasting Methods

Tools

Open DOIOpen Access