DSpace
 

KNUSTSpace >
Research Articles >
College of Science >

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/14609

Title: Predicting Bank Operational Efficiency Using Machine Learning Algorithm: Comparative Study of Decision Tree, Random Forest, and Neural Networks
Authors: Appiahene, Peter
Missah, Yaw Marfo
Najim, Ussiph
Issue Date: 2020
Publisher: Hindawi Advances in Fuzzy Systems
Citation: Hindawi Advances in Fuzzy Systems
Abstract: ThefinancialcrisisthathitGhanafrom2015to2018hasraisedvariousissueswithrespecttotheefficiencyofbanksandthesafety ofdepositors’inthebankingindustry.Aspartofmeasurestoimprovethebankingsectorandalsorestorecustomers’confidence, efficiencyandperformanceanalysisinthebankingindustryhasbecomeahotissue.Thisisbecausestakeholdershavetodetectthe underlying causes of inefficiencies within the banking industry. Nonparametric methods such as Data Envelopment Analysis (DEA)havebeensuggestedintheliteratureasagoodmeasureofbanks’efficiencyandperformance.Machinelearningalgorithms havealsobeenviewedasagoodtooltoestimatevariousnonparametricandnonlinearproblems.Thispaperpresentsacombined DEAwiththreemachinelearningapproachesinevaluatingbankefficiencyandperformanceusing444Ghanaianbankbranches, Decision Making Units (DMUs). The results were compared with the corresponding efficiency ratings obtained from the DEA. Finally,thepredictionaccuraciesofthethreemachinelearningalgorithmmodelswerecompared.Theresultssuggestedthatthe decisiontree(DT)anditsC5.0algorithmprovidedthebestpredictivemodel.Ithad100%accuracyinpredictingthe134holdout sample dataset (30% banks) and a P value of 0.00. The DTwas followed closely by random forest algorithm with a predictive accuracyof98.5%anda P valueof0.00andfinallytheneuralnetwork(86.6%accuracy)witha P value0.66.Thestudyconcluded thatbanksinGhanacanusetheresultofthisstudytopredicttheirrespectiveefficiencies.Allexperimentswereperformedwithina simulation environment and conducted in R studio using R codes.
Description: This article is published at Hindawi Advances in Fuzzy Systems and also available at, https://doi.org/10.1155/2020/8581202
URI: doi.org/10.1155/2020/8581202
http://hdl.handle.net/123456789/14609
Appears in Collections:College of Science

Files in This Item:

File Description SizeFormat
Predicting Bank Operational Efficiency Using Machine Learning.pdf1.36 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback