Research Article
BibTex RIS Cite

AN INTEGRATED MACHINE LEARNING BASED DECISION SUPPORT MODEL FOR PREDICTION OF BANK TELEMARKETING SUCCESS

Year 2022, Issue: 1, 94 - 109, 31.01.2022
https://doi.org/10.51551/verimlilik.748616

Abstract

Purpose: Today, electronic banking, which enables the capture of transaction data, has started to be adopted more and the amount of such data has increased significantly. Data mining-based techniques have been adopted to analyze this data. In this study, it is aimed to classify customers according to their time deposit eligibility status. The bank usually needs to make more than one phone connection to the same customer to understand whether a time deposit product can be offered.

Methodology: In this study, the data set used consists of the marketing campaigns data obtained by the Portuguese Banking Agency from its customers via telephone communication. Data is classified with C4.5, Naive Bayes, Bayes Networks, k-Nearest Neighbor and Sequential Minimal Optimization (SMO) classification algorithms. Classification models are compared according to synthesis index (SI) values.


Findings:
According to the results, simple C4.5 was found to be the best classification model. The proposed model was found to be superior to the methods applied by other studies in the literature on the same data set.

Originality: Different from the existing studies in the literature, in this study, different classification models were created with ensemble learning methods and a new performance criterion was developed as a synthesis index.

References

  • Abbas, S. (2015). “Deposit Subscribe Prediction Using Data Mining Techniques Based Real Marketing Dataset”, arXiv preprint arXiv:1503.04344.
  • Bahari, T.F. ve Elayidom, M.S. (2015). “An Efficient CRM-Data Mining Framework for the Prediction of Customer Behaviour”, Procedia Computer Science, 46, 725-731.
  • Bermejo, P., Gámez, J.A. ve Puerta, J.M. (2014). “Speeding Up Incremental Wrapper Feature Subset Selection with Naive Bayes Classifier”, Knowledge-Based Systems, 55, 140-147.
  • Bilgen, Ö.B. ve Doğan, N. (2017). “Puanlayıcılar Arası Güvenirlik Belirleme Tekniklerinin Karşılaştırılması”, Journal of Measurement and Evaluation in Education and Psychology, 8(1), 63-78.
  • Catal, C. (2012). “Performance Evaluation Metrics for Software Fault Prediction Studies”, Acta Polytechnica Hungarica, 9(4), 193-206.
  • Chaurasia, V. ve Pal, S. (2017). “A Novel Approach for Breast Cancer Detection Using Data Mining Techniques”, International Journal of Innovative Research in Computer and Communication Engineering, 2(1), Ocak 2014.
  • Dai, W. ve Ji, W. (2014). “A Mapreduce Implementation of C4. 5 Decision Tree Algorithm”, International Journal of Database Theory and Application, 7(1), 49-60.
  • Deng, X., Liu, Q., Deng, Y. ve Mahadevan, S. (2016). “An Improved Method to Construct Basic Probability Assignment Based on the Confusion Matrix for Classification Problem”, Information Sciences, 340, 250-261.
  • Han, J., Pei, J. ve Kamber, M. (2011). Data Mining: Concepts and Techniques, Elsevier, DOI: 10.1016/B978-0-12-381479-1.00021-6.
  • Hubert, M. ve Vandervieren, E. (2008). “An Adjusted Boxplot for Skewed Distributions”, Computational Statistics and Data Analysis, 52(12), 5186-5201.
  • Keles, A. ve Keles, A. (2015). “IBMMS Decision Support Tool for Management of Bank Telemarketing Campaigns”, arXiv preprint arXiv:1511.03532.
  • Kim, K.H., Lee, C.S., Jo, S.M. ve Cho, S.B. (2015). “Predicting the Success of Bank Telemarketing Using Deep Convolutional Neural Network”, 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR), 314-317.
  • Koç, A.A. ve Yeniay, Ö. (2013). “A Comparative Study of Artificial Neural Networks and Logistic Regression for Classification of Marketing Campaign Results”, Mathematical and Computational Applications, 18(3), 392-398.
  • Kozak, J. ve Juszczuk, P. (2018). “Ant Colony Optimization Algorithms in the Problem of Predicting the Efficiency of the Bank Telemarketing Campaign”, International Conference on Computational Collective Intelligence, 335-344, Springer, Cham.
  • Ledezma, A., Aler, R., Sanchis, A. ve Borrajo, D, (2004). “Empirical Evaluation of Optimized Stacking Configurations”, 16th IEEE International Conference on Tools with Artificial Intelligence, 49-55.
  • Mašetic, Z., Subasi, A. ve Azemovic, J. (2016). “Malicious Web Sites Detection Using C4. 5 Decision Tree”, Southeast Europe Journal of Soft Computing, 5(1), 68-72.
  • Medina, J.L.V., Boqué, R. ve Ferré, J. (2009). “Bagged K-Nearest Neighbours Classification with Uncertainty in the Variables”, Analytica Chimica Acta, 646(1-2), 62-68.
  • Miguéis, V.L., Camanho, A.S. ve Borges, J. (2017). “Predicting Direct Marketing Response in Banking: Comparison of Class Imbalance Methods”, Service Business, 11(4), 831-849.
  • Narin, A., İşler, Y. ve Mahmut, Ö. (2014). “Konjestif Kalp Yetmezliği Teşhisinde Kullanılan Çapraz Doğrulama Yöntemlerinin Sınıflandırıcı Performanslarının Belirlenmesine Olan Etkilerinin Karşılaştırılması”, Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, 16(48), 1-8.
  • Narudin, F.A., Feizollah, A., Anuar, N.B. ve Gani, A. (2016). “Evaluation of Machine Learning Classifiers for Mobile Malware Detection”, Soft Computing, 20(1), 343-357.
  • Nizam, H. ve Akın, S.S. (2014). “Sosyal Medyada Makine Öğrenmesi ile Duygu Analizinde Dengeli ve Dengesiz Veri Setlerinin Performanslarının Karşılaştırılması”, XIX. Türkiye'de İnternet Konferansı, 1-6, İzmir.
  • Palaniappan, S., Mustapha, A., Foozy, C.F.M. ve Atan, R. (2017). “Customer Profiling Using Classification Approach for Bank Telemarketing”, JOIV: International Journal on Informatics Visualization, 1(4-2), 214-217.
  • Paris, I.H.M., Affendey, L.S. ve Mustapha, N. (2010). “Improving Academic Performance Prediction Using Voting Technique in Data Mining”, World Academy of Science, Engineering and Technology, 62, 820-823.
  • Patil, T.R. (2013). “MSSS Performance Analysis of Naive Bayes and J48 Classification Algorithm for Data Classification”, International Journal of Computer Science and Applications, 6(2), 256-261.
  • Popelka, O., Hrebicek, J., Stencl, M. ve Trenz, O. (2012). “Comparison of Different Non-Statistical Classification Methods”, 30th International Conference Mathematical Methods in Economics, 727-732.
  • Pradap, R. ve Kamaludeen, P. (2019). “Machine Learning Modelsfor Bank Telemarketing Classification and Prediction”, The International Journal of Analytical and Experimental Modal Analysis, 11(12), 962-967. Silahtaroğlu, G. (2008). “Veri Madenciliği”, Papatya Yayınları, İstanbul.
  • Türkmen, E. (2021). “Deep Learning Based Methods for Processing Data in Telemarketing-Success Prediction”, Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), 1161-1166.
  • Vajiramedhin, C. ve Suebsing, A. (2014). “Feature Selection with Data Balancing for Prediction of Bank Telemarketing”, Applied Mathematical Sciences, 8(114), 5667-5672.
  • Wang, Z., Wang, Z., He, S., Gu, X. ve Yan, Z.F. (2017). “Fault Detection and Diagnosis of Chillers Using Bayesian Network Merged Distance Rejection and Multi-Source Non-Sensor Information”, Applied Energy, 188, 200-214.
  • Zhang, Q., Wang, J., Lu, A., Wang, S. ve Ma, J. (2018). “An Improved SMO Algorithm for Financial Credit Risk Assessment-Evidence from China’s Banking”, Neurocomputing, 272, 314-325.

BANKA TELEPAZARLAMA BAŞARISININ TAHMİNİ İÇİN BİR BİRLEŞİK MAKİNE ÖĞRENME TABANLI KARAR DESTEK MODELİ

Year 2022, Issue: 1, 94 - 109, 31.01.2022
https://doi.org/10.51551/verimlilik.748616

Abstract

Amaç: Günümüzde bankacılık sektöründeişlem verilerinin yakalanmasını sağlayan elektronik bankacılık daha çok benimsenmeye başlanmış ve bu tür verilerin miktarı önemli ölçüde artmıştır. Bu verileri analiz etmek için veri madenciliğine dayalı teknikler benimsenmiştir. Bu çalışmada müşterilerin vadeli mevduat uygunluk durumlarına göre sınıflandırılması amaçlanmıştır.

Yöntem: Bu çalışmada, kullanılan veri seti Portekiz Bankacılık Kurumu'nun müşterilerinden telefon ile iletişim yoluyla elde ettiği pazarlama kampanyaları verilerinden oluşmaktadır. Veriler C4.5, Naive Bayes, Bayes Ağları, k-En Yakın Komşu ve Sıralı Minimal Optimizasyon (SMO) sınıflandırma algoritmaları kullanılarak sınıflandırılmıştır. Sınıflandırma modelleri Sentez indeks (SI) değerlerine göre karşılaştırılmıştır.

Bulgular: Elde edilen sonuçlara göre basit C4.5, en iyi sınıflandırma modeli olarak bulunmuştur. Önerilen model, literatürdeki diğer çalışmaların aynı veri seti üzerinde uyguladığı yöntemlerden daha üstün bulunmuştur.


Özgünlük:
Literatürdeki mevcut çalışmalardan farklı olarak bu çalışmada, topluluk öğrenme yöntemleri ile farklı sınıflandırma modelleri oluşturulmuş ve sentez indeks olarak yeni bir performans ölçütü geliştirilmiştir.

References

  • Abbas, S. (2015). “Deposit Subscribe Prediction Using Data Mining Techniques Based Real Marketing Dataset”, arXiv preprint arXiv:1503.04344.
  • Bahari, T.F. ve Elayidom, M.S. (2015). “An Efficient CRM-Data Mining Framework for the Prediction of Customer Behaviour”, Procedia Computer Science, 46, 725-731.
  • Bermejo, P., Gámez, J.A. ve Puerta, J.M. (2014). “Speeding Up Incremental Wrapper Feature Subset Selection with Naive Bayes Classifier”, Knowledge-Based Systems, 55, 140-147.
  • Bilgen, Ö.B. ve Doğan, N. (2017). “Puanlayıcılar Arası Güvenirlik Belirleme Tekniklerinin Karşılaştırılması”, Journal of Measurement and Evaluation in Education and Psychology, 8(1), 63-78.
  • Catal, C. (2012). “Performance Evaluation Metrics for Software Fault Prediction Studies”, Acta Polytechnica Hungarica, 9(4), 193-206.
  • Chaurasia, V. ve Pal, S. (2017). “A Novel Approach for Breast Cancer Detection Using Data Mining Techniques”, International Journal of Innovative Research in Computer and Communication Engineering, 2(1), Ocak 2014.
  • Dai, W. ve Ji, W. (2014). “A Mapreduce Implementation of C4. 5 Decision Tree Algorithm”, International Journal of Database Theory and Application, 7(1), 49-60.
  • Deng, X., Liu, Q., Deng, Y. ve Mahadevan, S. (2016). “An Improved Method to Construct Basic Probability Assignment Based on the Confusion Matrix for Classification Problem”, Information Sciences, 340, 250-261.
  • Han, J., Pei, J. ve Kamber, M. (2011). Data Mining: Concepts and Techniques, Elsevier, DOI: 10.1016/B978-0-12-381479-1.00021-6.
  • Hubert, M. ve Vandervieren, E. (2008). “An Adjusted Boxplot for Skewed Distributions”, Computational Statistics and Data Analysis, 52(12), 5186-5201.
  • Keles, A. ve Keles, A. (2015). “IBMMS Decision Support Tool for Management of Bank Telemarketing Campaigns”, arXiv preprint arXiv:1511.03532.
  • Kim, K.H., Lee, C.S., Jo, S.M. ve Cho, S.B. (2015). “Predicting the Success of Bank Telemarketing Using Deep Convolutional Neural Network”, 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR), 314-317.
  • Koç, A.A. ve Yeniay, Ö. (2013). “A Comparative Study of Artificial Neural Networks and Logistic Regression for Classification of Marketing Campaign Results”, Mathematical and Computational Applications, 18(3), 392-398.
  • Kozak, J. ve Juszczuk, P. (2018). “Ant Colony Optimization Algorithms in the Problem of Predicting the Efficiency of the Bank Telemarketing Campaign”, International Conference on Computational Collective Intelligence, 335-344, Springer, Cham.
  • Ledezma, A., Aler, R., Sanchis, A. ve Borrajo, D, (2004). “Empirical Evaluation of Optimized Stacking Configurations”, 16th IEEE International Conference on Tools with Artificial Intelligence, 49-55.
  • Mašetic, Z., Subasi, A. ve Azemovic, J. (2016). “Malicious Web Sites Detection Using C4. 5 Decision Tree”, Southeast Europe Journal of Soft Computing, 5(1), 68-72.
  • Medina, J.L.V., Boqué, R. ve Ferré, J. (2009). “Bagged K-Nearest Neighbours Classification with Uncertainty in the Variables”, Analytica Chimica Acta, 646(1-2), 62-68.
  • Miguéis, V.L., Camanho, A.S. ve Borges, J. (2017). “Predicting Direct Marketing Response in Banking: Comparison of Class Imbalance Methods”, Service Business, 11(4), 831-849.
  • Narin, A., İşler, Y. ve Mahmut, Ö. (2014). “Konjestif Kalp Yetmezliği Teşhisinde Kullanılan Çapraz Doğrulama Yöntemlerinin Sınıflandırıcı Performanslarının Belirlenmesine Olan Etkilerinin Karşılaştırılması”, Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, 16(48), 1-8.
  • Narudin, F.A., Feizollah, A., Anuar, N.B. ve Gani, A. (2016). “Evaluation of Machine Learning Classifiers for Mobile Malware Detection”, Soft Computing, 20(1), 343-357.
  • Nizam, H. ve Akın, S.S. (2014). “Sosyal Medyada Makine Öğrenmesi ile Duygu Analizinde Dengeli ve Dengesiz Veri Setlerinin Performanslarının Karşılaştırılması”, XIX. Türkiye'de İnternet Konferansı, 1-6, İzmir.
  • Palaniappan, S., Mustapha, A., Foozy, C.F.M. ve Atan, R. (2017). “Customer Profiling Using Classification Approach for Bank Telemarketing”, JOIV: International Journal on Informatics Visualization, 1(4-2), 214-217.
  • Paris, I.H.M., Affendey, L.S. ve Mustapha, N. (2010). “Improving Academic Performance Prediction Using Voting Technique in Data Mining”, World Academy of Science, Engineering and Technology, 62, 820-823.
  • Patil, T.R. (2013). “MSSS Performance Analysis of Naive Bayes and J48 Classification Algorithm for Data Classification”, International Journal of Computer Science and Applications, 6(2), 256-261.
  • Popelka, O., Hrebicek, J., Stencl, M. ve Trenz, O. (2012). “Comparison of Different Non-Statistical Classification Methods”, 30th International Conference Mathematical Methods in Economics, 727-732.
  • Pradap, R. ve Kamaludeen, P. (2019). “Machine Learning Modelsfor Bank Telemarketing Classification and Prediction”, The International Journal of Analytical and Experimental Modal Analysis, 11(12), 962-967. Silahtaroğlu, G. (2008). “Veri Madenciliği”, Papatya Yayınları, İstanbul.
  • Türkmen, E. (2021). “Deep Learning Based Methods for Processing Data in Telemarketing-Success Prediction”, Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), 1161-1166.
  • Vajiramedhin, C. ve Suebsing, A. (2014). “Feature Selection with Data Balancing for Prediction of Bank Telemarketing”, Applied Mathematical Sciences, 8(114), 5667-5672.
  • Wang, Z., Wang, Z., He, S., Gu, X. ve Yan, Z.F. (2017). “Fault Detection and Diagnosis of Chillers Using Bayesian Network Merged Distance Rejection and Multi-Source Non-Sensor Information”, Applied Energy, 188, 200-214.
  • Zhang, Q., Wang, J., Lu, A., Wang, S. ve Ma, J. (2018). “An Improved SMO Algorithm for Financial Credit Risk Assessment-Evidence from China’s Banking”, Neurocomputing, 272, 314-325.
There are 30 citations in total.

Details

Primary Language Turkish
Journal Section Articles
Authors

Ömer Algorabi

Ersin Namlı 0000-0001-5980-9152

Publication Date January 31, 2022
Submission Date June 5, 2020
Published in Issue Year 2022 Issue: 1

Cite

APA Algorabi, Ö., & Namlı, E. (2022). BANKA TELEPAZARLAMA BAŞARISININ TAHMİNİ İÇİN BİR BİRLEŞİK MAKİNE ÖĞRENME TABANLI KARAR DESTEK MODELİ. Verimlilik Dergisi(1), 94-109. https://doi.org/10.51551/verimlilik.748616

23139       23140          29293

22408 Journal of Productivity is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0)