Designing a Model for Improving Banking Recommender Systems Based on Predicting Customers’ Interests: Application of Data Mining Techniques

Nowadays, banks require new devices such as recommender systems to attract and preserve customers. Unlike most recommender systems in which the given recommendation is based on similarities between the preferences of users, this research has employed the classification techniques where customer’s pa...

Full description

Saved in:
Bibliographic Details
Main Authors: Maryam sadat Motaharinejad, Mohammad Mahdi Zolfagharzadeh, Ehsan Khadangi, Ali Asghar Sadabadi
Format: Article
Language:English
Published: University of Tehran 2016-07-01
Series:Journal of Information Technology Management
Subjects:
Online Access:https://jitm.ut.ac.ir/article_57230_10b61b9461be0adc2ebce9552302719a.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850159289999556608
author Maryam sadat Motaharinejad
Mohammad Mahdi Zolfagharzadeh
Ehsan Khadangi
Ali Asghar Sadabadi
author_facet Maryam sadat Motaharinejad
Mohammad Mahdi Zolfagharzadeh
Ehsan Khadangi
Ali Asghar Sadabadi
author_sort Maryam sadat Motaharinejad
collection DOAJ
description Nowadays, banks require new devices such as recommender systems to attract and preserve customers. Unlike most recommender systems in which the given recommendation is based on similarities between the preferences of users, this research has employed the classification techniques where customer’s past interests is considered as the most important feature to provide proper banking services for them. In this research, four classifiers including MLP, SVM, KNN, and Naïve Bayes have been used.  Firstly, the data set which was related to the services used by different bank customers was pre-processed and four different classification methods were trained by using it. Then, their validations were assessed by the 10-fold cross validation and the best method was selected. Lastly, the final recommender system which was a combination of four classification methods including Naïve Bayes with performance P=%85.4, 5-nn with P=%83.3, MLP with P=%81.4, and MLP with P=%92.6 respectively proposed for recommendation of four banking services including the internet, mobile, internet transfer and paying on the phone is.
format Article
id doaj-art-ae65b7f423ba449c8e415e755de10c31
institution OA Journals
issn 2008-5893
2423-5059
language English
publishDate 2016-07-01
publisher University of Tehran
record_format Article
series Journal of Information Technology Management
spelling doaj-art-ae65b7f423ba449c8e415e755de10c312025-08-20T02:23:35ZengUniversity of TehranJournal of Information Technology Management2008-58932423-50592016-07-018239331410.22059/jitm.2016.5723057230Designing a Model for Improving Banking Recommender Systems Based on Predicting Customers’ Interests: Application of Data Mining TechniquesMaryam sadat Motaharinejad0Mohammad Mahdi Zolfagharzadeh1Ehsan Khadangi2Ali Asghar Sadabadi3MSc in Information Technology Management, Islamic Azad University E-campus, Tehran, IranAssistant Prof., Faculty of New Sciences and Technologies, University of Tehran, IranPh.D. Student in Computer Engineering, Amirkabir University of Technology, Tehran, IranPhD student in science and technology policy, Faculty of New Sciences and Technologies, University of Tehran, TehranNowadays, banks require new devices such as recommender systems to attract and preserve customers. Unlike most recommender systems in which the given recommendation is based on similarities between the preferences of users, this research has employed the classification techniques where customer’s past interests is considered as the most important feature to provide proper banking services for them. In this research, four classifiers including MLP, SVM, KNN, and Naïve Bayes have been used.  Firstly, the data set which was related to the services used by different bank customers was pre-processed and four different classification methods were trained by using it. Then, their validations were assessed by the 10-fold cross validation and the best method was selected. Lastly, the final recommender system which was a combination of four classification methods including Naïve Bayes with performance P=%85.4, 5-nn with P=%83.3, MLP with P=%81.4, and MLP with P=%92.6 respectively proposed for recommendation of four banking services including the internet, mobile, internet transfer and paying on the phone is.https://jitm.ut.ac.ir/article_57230_10b61b9461be0adc2ebce9552302719a.pdfClassificationData MiningE-BankingRecommender System
spellingShingle Maryam sadat Motaharinejad
Mohammad Mahdi Zolfagharzadeh
Ehsan Khadangi
Ali Asghar Sadabadi
Designing a Model for Improving Banking Recommender Systems Based on Predicting Customers’ Interests: Application of Data Mining Techniques
Journal of Information Technology Management
Classification
Data Mining
E-Banking
Recommender System
title Designing a Model for Improving Banking Recommender Systems Based on Predicting Customers’ Interests: Application of Data Mining Techniques
title_full Designing a Model for Improving Banking Recommender Systems Based on Predicting Customers’ Interests: Application of Data Mining Techniques
title_fullStr Designing a Model for Improving Banking Recommender Systems Based on Predicting Customers’ Interests: Application of Data Mining Techniques
title_full_unstemmed Designing a Model for Improving Banking Recommender Systems Based on Predicting Customers’ Interests: Application of Data Mining Techniques
title_short Designing a Model for Improving Banking Recommender Systems Based on Predicting Customers’ Interests: Application of Data Mining Techniques
title_sort designing a model for improving banking recommender systems based on predicting customers interests application of data mining techniques
topic Classification
Data Mining
E-Banking
Recommender System
url https://jitm.ut.ac.ir/article_57230_10b61b9461be0adc2ebce9552302719a.pdf
work_keys_str_mv AT maryamsadatmotaharinejad designingamodelforimprovingbankingrecommendersystemsbasedonpredictingcustomersinterestsapplicationofdataminingtechniques
AT mohammadmahdizolfagharzadeh designingamodelforimprovingbankingrecommendersystemsbasedonpredictingcustomersinterestsapplicationofdataminingtechniques
AT ehsankhadangi designingamodelforimprovingbankingrecommendersystemsbasedonpredictingcustomersinterestsapplicationofdataminingtechniques
AT aliasgharsadabadi designingamodelforimprovingbankingrecommendersystemsbasedonpredictingcustomersinterestsapplicationofdataminingtechniques