{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T14:39:47Z","timestamp":1770043187565,"version":"3.49.0"},"reference-count":35,"publisher":"SAGE Publications","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2021,12,16]]},"abstract":"<jats:p>Automatic Teller Machine (ATM) are still largely used to dispense cash to the customers. ATM cash replenishment is a process of refilling ATM machine with a specific amount of cash. Due to vacillating users demands and seasonal patterns, it is a very challenging problem for the financial institutions to keep the optimal amount of cash for each ATM. In this paper, we present a time series model based on Auto Regressive Integrated Moving Average (ARIMA) technique called Time Series ARIMA Model for ATM (TASM4ATM). This study used ATM back-end refilling historical data from 6 different financial organizations in Pakistan. There are 2040 distinct ATMs and 18 month of replenishment data from these ATMs are used to train the proposed model. The model is compared with the state-of- the-art models like Recurrent Neural Network (RNN) and Amazon\u2019s DeepAR model. Two approaches are used for forecasting (i) Single ATM and (ii) clusters of ATMs (In which ATMs are clustered with similar cash-demands). The Mean Absolute Percentage Error (MAPE) and Symmetric Mean Absolute Percentage Error (SMAPE) are used to evaluate the models. The suggested model produces far better forecasting as compared to the models in comparison and produced an average of 7.86\/7.99 values for MAPE\/SMAPE errors on individual ATMs and average of 6.57\/6.64 values for MAPE\/SMAPE errors on clusters of ATMs.<\/jats:p>","DOI":"10.3233\/jifs-201953","type":"journal-article","created":{"date-parts":[[2021,10,7]],"date-time":"2021-10-07T18:40:18Z","timestamp":1633632018000},"page":"5915-5927","source":"Crossref","is-referenced-by-count":3,"title":["Towards optimal ATM cash replenishment using time series analysis"],"prefix":"10.1177","volume":"41","author":[{"given":"Muhammad","family":"Rafi","sequence":"first","affiliation":[{"name":"Computer Science Department, National University of Computer & Emerging Sciences, Shah Latif Town, Karachi, Pakistan"}]},{"given":"Mohammad Taha","family":"Wahab","sequence":"additional","affiliation":[{"name":"Computer Science Department, National University of Computer & Emerging Sciences, Shah Latif Town, Karachi, Pakistan"}]},{"given":"Muhammad Bilal","family":"Khan","sequence":"additional","affiliation":[{"name":"Computer Science Department, National University of Computer & Emerging Sciences, Shah Latif Town, Karachi, Pakistan"}]},{"given":"Hani","family":"Raza","sequence":"additional","affiliation":[{"name":"Computer Science Department, National University of Computer & Emerging Sciences, Shah Latif Town, Karachi, Pakistan"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-201953_ref1","doi-asserted-by":"crossref","unstructured":"Abbasimehr H. and Paki R. , Improving time series forecasting using lstm and attention models, Journal of Ambient Intelligence and Humanized Computing (2021).","DOI":"10.1007\/s12652-020-02761-x"},{"key":"10.3233\/JIFS-201953_ref2","unstructured":"Abbasimehr H. , Paki R. and Bahrini A. , Improving the performance of deep learning models using statistical features: The case study of covid-19 forecasting, Mathematical Methods in the Applied Sciences, n\/a(n\/a)."},{"key":"10.3233\/JIFS-201953_ref3","doi-asserted-by":"crossref","first-page":"106435","DOI":"10.1016\/j.cie.2020.106435","article-title":"An optimized model using lstm network for demand forecasting","volume":"143","author":"Abbasimehr","year":"2020","journal-title":"Computers & Industrial Engineering"},{"key":"10.3233\/JIFS-201953_ref4","unstructured":"Adhikari R. and Agrawal R. , An Introductory Study on Time series Modeling and Forecasting, (2013)."},{"key":"10.3233\/JIFS-201953_ref5","doi-asserted-by":"crossref","unstructured":"Agrawal R. , Faloutsos C. and Swami A. , Efficient similarity search in sequence databases. In Lomet,D. B., editor, Foundations of Data Organization and Algorithms, pages 69\u201384, Berlin, Heidelberg. Springer Heidelberg. (1993).","DOI":"10.1007\/3-540-57301-1_5"},{"key":"10.3233\/JIFS-201953_ref6","unstructured":"Agrawal S. and Carr M. , Cash demand forecasting for atms, (2013)."},{"key":"10.3233\/JIFS-201953_ref7","doi-asserted-by":"crossref","first-page":"309","DOI":"10.5539\/mas.v12n11p309","article-title":"Arima model in predicting banking stock market data","volume":"12","author":"Almasarweh","year":"2018","journal-title":"Modern Applied Science"},{"key":"10.3233\/JIFS-201953_ref8","doi-asserted-by":"crossref","unstructured":"Asad M. , Shahzaib M. , Abbasi Y. and Rafi M. , A long-short-term-memory based model for predicting atm replenishment amount, The 21st International Arab Conference on Information Technology 2020 (2020), (ACIT).","DOI":"10.1109\/ACIT50332.2020.9300115"},{"key":"10.3233\/JIFS-201953_ref9","doi-asserted-by":"crossref","unstructured":"Chase C.W. , Demand-driven forecasting: a structured approach to forecasting, John Wiley & Sons (2013).","DOI":"10.1002\/9781118691861"},{"issue":"4","key":"10.3233\/JIFS-201953_ref10","doi-asserted-by":"crossref","first-page":"2534","DOI":"10.1007\/s10489-020-02031-5","article-title":"Selection of key features for pm2.5 prediction using a wavelet model and rbf-lstm","volume":"51","author":"Chen","year":"2021","journal-title":"Applied Intelligence"},{"key":"10.3233\/JIFS-201953_ref11","first-page":"343","article-title":"Atm cash flow management. International Journal of Innovation","volume":"6","author":"Dandekar","year":"2015","journal-title":"Management and Technology"},{"key":"10.3233\/JIFS-201953_ref12","doi-asserted-by":"crossref","first-page":"405","DOI":"10.7763\/IJCEE.2013.V5.741","article-title":"A methodology to improve cash demand forecasting for atm network","volume":"5","author":"Darwish","year":"2013","journal-title":"International Journal of Computer and Electrical Engineering"},{"key":"10.3233\/JIFS-201953_ref13","unstructured":"Donepudi P. , Banu M. , Bangladesh W. , Khan A.l. , Ahmed A. , Khan W. , Neogy T. and Asadullah A.B.M. , Intelligence and machine learning in treasury management: A systematic literature review, 11 (2020), 13\u201322."},{"key":"10.3233\/JIFS-201953_ref14","first-page":"42","article-title":"Optimization of atm cash replenishment with group-demand forecast","author":"Ekinci","year":"2015","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/JIFS-201953_ref15","unstructured":"Gobindgarh M. , An artificial intelligence atm forecasting system for hybrid neural networks, (2016)."},{"key":"10.3233\/JIFS-201953_ref16","first-page":"65","article-title":"Modeling of withdrawals from selected atms of the \u201ceuronet\u201d network","volume":"13","author":"Gurgul","year":"2015","journal-title":"Managerial Economics"},{"key":"10.3233\/JIFS-201953_ref17","doi-asserted-by":"crossref","first-page":"491","DOI":"10.7763\/IJMLC.2014.V6.460","article-title":"Predicting time series using integration of moving average and support vector regression","volume":"4","author":"Hung","year":"2014","journal-title":"International Journal of Machine Learning and Computing"},{"key":"10.3233\/JIFS-201953_ref18","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1016\/j.ejor.2013.07.027","article-title":"Cash demand forecasting in atms by clustering and neural networks","volume":"232","author":"Kamini","year":"2014","journal-title":"European Journal of Operational Research"},{"issue":"3","key":"10.3233\/JIFS-201953_ref19","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1007\/s10115-004-0154-9","article-title":"Exact indexing of dynamic time warping","volume":"7","author":"Keogh","year":"2005","journal-title":"Knowledge and Information Systems"},{"key":"10.3233\/JIFS-201953_ref20","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.ijpe.2015.09.011","article-title":"Forecasting with multivariate temporal aggregation: The case of promotional modelling","volume":"181","author":"Kourentzes","year":"2016","journal-title":"International Journal of Production Economics"},{"issue":"4","key":"10.3233\/JIFS-201953_ref21","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1016\/0169-2070(89)90017-4","article-title":"Why combining works?","volume":"5","author":"Makridakis","year":"1989","journal-title":"International Journal of Forecasting"},{"key":"10.3233\/JIFS-201953_ref22","doi-asserted-by":"crossref","unstructured":"Marikkar U. , Jameel Hassan A.S. , MaithripalaM.S., GodaliyaddaR.I., EkanayakeP.B. and EkanayakeJ.B., Modified Auto Regressive Technique for Univariate Time Series Prediction of Solar Irradiance. arXiv e-prints, (2020) arXiv:2012.03215.","DOI":"10.1109\/ICIIS51140.2020.9342694"},{"issue":"2","key":"10.3233\/JIFS-201953_ref23","first-page":"347","article-title":"A multivariate analysis approach to forecasts combination. application to foreign exchange (fx) markets","volume":"34","author":"Mat\u00e9","year":"2011","journal-title":"Revista Colombiana de Estad\u00edstica"},{"key":"10.3233\/JIFS-201953_ref24","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.cie.2018.02.007","article-title":"Forecast of individual customer\u2019s demand from a large and noisy dataset","volume":"118","author":"Murray","year":"2018","journal-title":"Computers & Industrial Engineering"},{"key":"10.3233\/JIFS-201953_ref25","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1016\/j.ins.2019.01.076","article-title":"Evaluation of statistical and machine learning models for time series prediction: Identifying the state-of-the-art and the best conditions for the use of each model","volume":"484","author":"Parmezan","year":"2019","journal-title":"Information Sciences"},{"issue":"4","key":"10.3233\/JIFS-201953_ref26","doi-asserted-by":"crossref","first-page":"473","DOI":"10.2307\/2297602","article-title":"Multiple Time Series Regression with Integrated Processes","volume":"53","author":"Phillips","year":"1986","journal-title":"The Review of Economic Studies"},{"key":"10.3233\/JIFS-201953_ref27","doi-asserted-by":"crossref","unstructured":"Ram\u00edrez C. and Acu\u00f1a G. , Forecasting cash demand in atm using neural networks and least square support vector machine, 7042 (2011), 515\u2013522.","DOI":"10.1007\/978-3-642-25085-9_61"},{"key":"10.3233\/JIFS-201953_ref28","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.neucom.2007.07.018","article-title":"Soft-computing techniques and arma model for time series prediction","volume":"71","author":"Rojas","year":"2008","journal-title":"Neurocomputing"},{"key":"10.3233\/JIFS-201953_ref29","unstructured":"Salinas D. , Flunkert V. and Gasthaus J. , Deepar: Probabilistic forecasting with autoregressive recurrent networks, (2017)."},{"key":"10.3233\/JIFS-201953_ref30","first-page":"28","article-title":"Arima: The models of box and jenkins","author":"Stellwagen","year":"2013","journal-title":"Foresight: Int J Appl Forecast"},{"key":"10.3233\/JIFS-201953_ref31","doi-asserted-by":"crossref","first-page":"121261","DOI":"10.1016\/j.physa.2019.121261","article-title":"Modeling financial time-series with generative adversarial networks","volume":"527","author":"Takahashi","year":"2019","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"10.3233\/JIFS-201953_ref32","unstructured":"Vangala S. and Ravi V. , ATM cash demand forecasting in an indian bank with chaos and deep learning, CoRR, abs\/2008.10365. (2020)."},{"key":"10.3233\/JIFS-201953_ref33","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.1016\/j.eswa.2009.06.106","article-title":"Application of fuzzy time series models for forecasting the amount of taiwan export","volume":"37","author":"Wong","year":"2010","journal-title":"Expert Syst Appl"},{"key":"10.3233\/JIFS-201953_ref34","doi-asserted-by":"crossref","first-page":"114209","DOI":"10.1016\/j.eswa.2020.114209","article-title":"Air compressor load forecasting using artificial neural network","volume":"168","author":"Wu","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/JIFS-201953_ref35","first-page":"4907423","article-title":"Stock market prediction on high-frequency data using generative adversarial nets","volume":"2018","author":"Zhou","year":"2018","journal-title":"Mathematical Problems in Engineering"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-201953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T02:50:21Z","timestamp":1770000621000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-201953"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,16]]},"references-count":35,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.3233\/jifs-201953","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,16]]}}}