A Long-Short-Term-Memory Based Model for Predicting ATM Replenishment Amount

Asad, Muhammad; Shahzaib, Muhammad; Abbasi, Yusra; Rafi, Muhammad

doi:10.1109/acit50332.2020.9300115

Cited by 9 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The specific stages described below that make up the predictive model production methodology were developed following the staging of typical machine learning projects designed to solve similar problems. Examples of describing the stages of data analysis for creating predictive models can be seen in previous studies (Morariu et al 2009;Bahrammirzaee 2010;Li and Ma 2010;Nair and Mohandas 2014;Katarya and Mahajan 2017;Sezer et al 2020;Asad et al 2020;Arabani and Komleh 2019;Kamini et al 2014). A universal pipeline for forecasting time series was developed to solve the problem of forecasting, consisting of the following steps:…”

Section: Methodsmentioning

confidence: 99%

“…However, this does not mean that this problem has not been considered in the literature (Ekinci et al 2019). We note, for example, the works of M. Rafi, which are devoted to modeling ATM loading using classical statistical methods such as moving average autoregression (Rafi et al 2020) and the use of recurrent neural networks based on LSTM cells (Asad et al 2020). LSTM can generally be considered a classical method since it was created specifically for modeling time series.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Machine Learning Pipeline for Forecasting Time Series in the Banking Sector

2021

View full text Add to dashboard Cite

The problem of forecasting time series is very widely debated. In recent years, machine learning algorithms have been very prolific in this area. This paper describes a systematic approach to building a machine learning predictive model for solving optimization problems in the banking sector. A literature analysis on applying such methods in this particular area is presented. As a direct result of the described research, a universal scenario for forecasting various non-stationary time series in automatic mode was developed. The developed scenario for solving specific banking tasks to improve business efficiency, including optimizing demand for ATMs, forecasting the load on the call center and cash center, is considered. A machine learning methodology in economics that can yield robust and reproducible results and can be reused in solving other similar tasks is described. The methodology described in the article was tested on three cases and showed the ability to generate models that are superior in accuracy to similar predictive models described in the literature by at least three percentage points. This article will be helpful to specialists dealing with the problem of forecasting economic time series and students and researchers due to a large number of links to systematic literature reviews on this topic.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A Machine Learning Pipeline for Forecasting Time Series in the Banking Sector

2021

View full text Add to dashboard Cite

show abstract

“…Forecasting the precise amount of cash required to meet daily customer demands, ensuring that a minimum cash level remains available until the next replenishment, presents a challenging issue. To address this problem, a data-driven machine learning technique has been employed for forecasting ATM replenishment quantities, offering a more accurate estimation of the optimal cash amount needed for ATM operations [7]. In recent years, machine learning techniques have become the predominant approach for resolving forecasting challenges.…”

Section: Literature Reviewmentioning

confidence: 99%

“…While the literature predominantly relies on conventional methods, the accuracy of predictions profoundly influences customer satisfaction with ATM services. Initially, diverse forecasting methodologies are applied to the NN5 dataset [2], encompassing statistical techniques like Exponential Smoothing, ARIMA and SARIMA [3] [4], alongside machine learning methods like neural networks [5] [6]. It is worth noting that Prophet has not been previously applied in the context of ATM cash replenishment policies, differentiating our approach.…”

Section: Introductionmentioning

confidence: 99%

Statistical and Artificial Intelligence Based Forecasting Approaches for Cash Demand Problem of Automated Teller Machines

CEDOLİN,

ORHAN,

GENEVOİS

2024

Academic Platform Journal of Engineering and Smart Systems

View full text Add to dashboard Cite

The efficient management of cash replenishment in Automated Teller Machines (ATMs) is a critical concern for banks and financial institutions. This paper explores the application of statistical and artificial intelligence (AI) forecasting methods to address the cash demand problem in ATMs. Recognizing the significance of accurate cash predictions for ensuring uninterrupted ATM services and minimizing operational costs, we investigate various forecasting approaches. Initially, statistical methodologies including Autoregressive Integrated Moving Average (ARIMA) and Seasonal ARIMA (SARIMA) are employed to model and forecast cash demand patterns. Subsequently, machine learning techniques such as Deep Neural Networks (DNN) and Prophet algorithm are leveraged to enhance prediction accuracy. We assess the performance of these methodologies through rigorous analysis and evaluation. Furthermore, the paper delves into the integration of these forecasting approaches within an overall decision support system for ATM cash management. By optimizing cash replenishment strategies based on accurate forecasts, financial institutions aim to simultaneously enhance customer satisfaction and reduce operational expenses. The findings of this study contribute to a comprehensive understanding of how statistical and AI-driven forecasting can revolutionize cash management in ATMs, offering insights for improving the efficiency and cost-effectiveness of ATM services in the banking sector.

show abstract

“…Rafi et al (2020) employed a vector auto regressive moving average with exogenous variable model (VAR-MAX) which is an extension of ARIMA model to forecast cash demand of 7 ATMs of Pakistan. Recently, Asad et al (2020) clustered 2,241 Pakistan ATMs employing density-based spatial clustering (DBSCAN) and employed ANN and long short-term memory (LSTM) models to forecast ATM replenishment amount. Vangala and Vadlamani (2020) proposed a two-stage forecasting model for daily cash demand of 100 Indian ATMs.…”

Section: Problem Backgroundmentioning

confidence: 99%

An averaging approach to individual time series employing econometric models: a case study on NN5 ATM transactions data

Cedolin

Genevois

2021

View full text Add to dashboard Cite

PurposeThe research objective is to increase the computational efficiency of the automated teller machine (ATM) cash demand forecasting problem. It proposes a practical decision-making process that uses aggregated time series of a bank's ATM network. The purpose is to decrease ATM numbers that will be forecasted by individual models, by finding the machines’ cluster where the forecasting results of the aggregated series are appropriate to use.Design/methodology/approachA comparative statistical forecasting approach is proposed in order to reduce the calculation complexity of an ATM network by using the NN5 competition data set. Integrated autoregressive moving average (ARIMA) and its seasonal version SARIMA are fitted to each time series. Then, averaged time series are introduced to simplify the forecasting process carried out for each ATM. The ATMs that are forecastable with the averaged series are identified by calculating the forecasting accuracy change in each machine.FindingsThe proposed approach is evaluated by different error metrics and is compared to the literature findings. The results show that the ATMs that have tolerable accuracy loss may be considered as a cluster and can be forecasted with a single model based on the aggregated series.Research limitations/implicationsThe research is based on the public data set. Financial institutions do not prefer to share their ATM transactions data, therefore accessible data are limited.Practical implicationsThe proposed practical approach will be beneficial for financial institutions to use, that hold an excessive number of ATMs because it reduces the computational time and resources allocated for the forecasting process.Originality/valueThis study offers an effective simplified methodology to the challenging cash demand forecasting process by introducing an aggregated time series approach.

show abstract

A Long-Short-Term-Memory Based Model for Predicting ATM Replenishment Amount

Cited by 9 publications

References 8 publications

A Machine Learning Pipeline for Forecasting Time Series in the Banking Sector

A Machine Learning Pipeline for Forecasting Time Series in the Banking Sector

Statistical and Artificial Intelligence Based Forecasting Approaches for Cash Demand Problem of Automated Teller Machines

An averaging approach to individual time series employing econometric models: a case study on NN5 ATM transactions data

Contact Info

Product

Resources

About