Journal Home > Volume 7 , Issue 2
Big Data Mining and Analytics 2024, 7(2): 294-314 https://doi.org/10.26599/BDMA.2023.9020041
Open Access | Issue | Published: 22 April 2024

Enhancing Telemarketing Success Using Ensemble-Based Online Machine Learning

Show Author's Information Shahriar Kaisar1( ),  Md Mamunur Rashid2,  Abdullahi Chowdhury3,  Sakib Shahriar Shafin4,  Joarder Kamruzzaman4,  Abebe Diro5
Department of Information Systems and Business Analytics, RMIT University, Melbourne 3000, Australia
School of Engineering and Technology, Central Queensland University, Rockhampton 4700, Australia
Faculty of Engineering, Computer and Mathematical Science, University of Adelaide, Adelaide 5005, Australia
Centre for Smart Analytics, Federation University Australia, Ballarat 3350, Australia
School of Accounting, Information Systems and Supply Chain, RMIT University, Melbourne 3000, Australia
Keywords:
machine learning, online learning, oversampling, telemarketing, imbalanced dataset, ensemble model
Cite this article:
Kaisar S, Rashid MM, Chowdhury A, et al. Enhancing Telemarketing Success Using Ensemble-Based Online Machine Learning. Big Data Mining and Analytics, 2024, 7(2): 294-314. https://doi.org/10.26599/BDMA.2023.9020041
Download citation
EndNote(RIS)
BibTeX

59

Views

8

Downloads

Citations

0

Crossref

0

WoS

0

Scopus

0

CSCD

Abstract Full text About this article

Telemarketing is a well-established marketing approach to offering products and services to prospective customers. The effectiveness of such an approach, however, is highly dependent on the selection of the appropriate consumer base, as reaching uninterested customers will induce annoyance and consume costly enterprise resources in vain while missing interested ones. The introduction of business intelligence and machine learning models can positively influence the decision-making process by predicting the potential customer base, and the existing literature in this direction shows promising results. However, the selection of influential features and the construction of effective learning models for improved performance remain a challenge. Furthermore, from the modelling perspective, the class imbalance nature of the training data, where samples with unsuccessful outcomes highly outnumber successful ones, further compounds the problem by creating biased and inaccurate models. Additionally, customer preferences are likely to change over time due to various reasons, and/or a fresh group of customers may be targeted for a new product or service, necessitating model retraining which is not addressed at all in existing works. A major challenge in model retraining is maintaining a balance between stability (retaining older knowledge) and plasticity (being receptive to new information). To address the above issues, this paper proposes an ensemble machine learning model with feature selection and oversampling techniques to identify potential customers more accurately. A novel online learning method is proposed for model retraining when new samples are available over time. This newly introduced method equips the proposed approach to deal with dynamic data, leading to improved readiness of the proposed model for practical adoption, and is a highly useful addition to the literature. Extensive experiments with real-world data show that the proposed approach achieves excellent results in all cases (e.g., 98.6% accuracy in classifying customers) and outperforms recent competing models in the literature by a considerable margin of 3% on a widely used dataset.


menu
Abstract
Full text
Outline
About this article

Enhancing Telemarketing Success Using Ensemble-Based Online Machine Learning

Show Author's information Shahriar Kaisar1( ), Md Mamunur Rashid2, Abdullahi Chowdhury3, Sakib Shahriar Shafin4, Joarder Kamruzzaman4, Abebe Diro5
Department of Information Systems and Business Analytics, RMIT University, Melbourne 3000, Australia
School of Engineering and Technology, Central Queensland University, Rockhampton 4700, Australia
Faculty of Engineering, Computer and Mathematical Science, University of Adelaide, Adelaide 5005, Australia
Centre for Smart Analytics, Federation University Australia, Ballarat 3350, Australia
School of Accounting, Information Systems and Supply Chain, RMIT University, Melbourne 3000, Australia

Abstract

Telemarketing is a well-established marketing approach to offering products and services to prospective customers. The effectiveness of such an approach, however, is highly dependent on the selection of the appropriate consumer base, as reaching uninterested customers will induce annoyance and consume costly enterprise resources in vain while missing interested ones. The introduction of business intelligence and machine learning models can positively influence the decision-making process by predicting the potential customer base, and the existing literature in this direction shows promising results. However, the selection of influential features and the construction of effective learning models for improved performance remain a challenge. Furthermore, from the modelling perspective, the class imbalance nature of the training data, where samples with unsuccessful outcomes highly outnumber successful ones, further compounds the problem by creating biased and inaccurate models. Additionally, customer preferences are likely to change over time due to various reasons, and/or a fresh group of customers may be targeted for a new product or service, necessitating model retraining which is not addressed at all in existing works. A major challenge in model retraining is maintaining a balance between stability (retaining older knowledge) and plasticity (being receptive to new information). To address the above issues, this paper proposes an ensemble machine learning model with feature selection and oversampling techniques to identify potential customers more accurately. A novel online learning method is proposed for model retraining when new samples are available over time. This newly introduced method equips the proposed approach to deal with dynamic data, leading to improved readiness of the proposed model for practical adoption, and is a highly useful addition to the literature. Extensive experiments with real-world data show that the proposed approach achieves excellent results in all cases (e.g., 98.6% accuracy in classifying customers) and outperforms recent competing models in the literature by a considerable margin of 3% on a widely used dataset.

Keywords: machine learning, online learning, oversampling, telemarketing, imbalanced dataset, ensemble model

References(63)

[1]

S. Lahmiri, A two-step system for direct bank telemarketing outcome classification, Int. J. Intell. Syst. Account. Finance Manag., vol. 24, no. 1, pp. 49–55, 2017.
DOI Google Scholar
[2]

C. Page and L. Ye, Bank managers’ direct marketing dilemmas–customers’ attitudes and purchase intention, Int. J. Bank Mark., vol. 21, no. 3, pp. 147–163, 2003.
DOI Google Scholar
[3]

I. T. Javed, K. Toumi, F. Alharbi, T. Margaria, and N. Crespi, Detecting nuisance calls over internet telephony using caller reputation, Electronics, vol. 10, no. 3, p. 353, 2021.
DOI Google Scholar
[4]

N. T. Martin, Stop telephonin’ me: The problematically narrow conception of telemarketing abuse under the TCPA, Wisconsin Law Review, vol. 2022, no. 4, pp. 997–1026, 2022.
Google Scholar
[5]

F. T. Nobibon, R. Leus, and F. C. R. Spieksma, Optimization models for targeted offers in direct marketing: Exact and heuristic algorithms, Eur. J. Oper. Res., vol. 210, no. 3, pp. 670–683, 2011.
DOI Google Scholar
[6]
A. Chowdhury, S. Kaisar, M. M. Rashid, S. S. Shafin, and J. Kamruzzaman, Churn prediction in telecom industry using machine learning ensembles with class balancing, in Proc. 2021 IEEE Asia-Pacific Conf. Computer Science and Data Engineering (CSDE), Brisbane, Australia, 2021, pp. 1–6.
DOI
[7]

G. Tsoumakas, A survey of machine learning techniques for food sales prediction, Artif. Intell. Rev., vol. 52, no. 1, pp. 441–447, 2019.
DOI Google Scholar
[8]
J. H. Brito, J. M. Pereira, A. F. D. Silva, M. J. Angélico, A. Abreu, and S. Teixeira, Machine learning for prediction of business company failure in hospitality sector, in Advances in Tourism, Technology and Smart Systems, Á. Rocha, A. Abreu, J. V. D. Carvalho, D. Liberato, E. A. González, and P. Liberato, eds. Singapore: Springer, 2019, pp. 307–317.
DOI
[9]

Z. You, Y. W. Si, D. Zhang, X. Zeng, S. C. H. Leung, and T. Li, A decision-making framework for precision marketing, Expert Syst. Appl. Int. J., vol. 42, no. 7, pp. 3357–3367, 2015.
DOI Google Scholar
[10]

T. F. Bahari and M. S. Elayidom, An efficient CRM-data mining framework for the prediction of customer behaviour, Procedia Comput. Sci., vol. 46, pp. 725–731, 2015.
DOI Google Scholar
[11]

A. Intezari and S. Gressel, Information and reformation in KM systems: Big data and strategic decision-making, J. Knowl. Manag., vol. 21, no. 1, pp. 71–91, 2017.
DOI Google Scholar
[12]
S. Moro, R. M. S. Laureano, and P. Cortez, Using data mining for bank direct marketing: An application of the crisp-DM methodology, in Proc. 2011 European Simulation and Modelling Conf., Guimarães, Portugal, 2011, pp. 117–121.
[13]

S. Moro, P. Cortez, and P. Rita, A data-driven approach to predict the success of bank telemarketing, Decis. Support. Syst., vol. 62, pp. 22–31, 2014.
DOI Google Scholar
[14]

U. Parlar and S. K. Acaravci, Using data mining techniques for detecting the important features of the bank direct marketing data, Int. J. Econ. Financ. News., vol. 7, no. 2, pp. 692–696, 2017.
Google Scholar
[15]

Y. Jiang, Using logistic regression model to predict the success of bank telemarketing, Int. J. Data Science and Technology, vol. 4, no. 1, pp. 35–41, 2018.
Google Scholar
[16]

M. L. McHugh, The Chi-square test of independence, Biochem. Med., vol. 23, no. 2, pp. 143–149, 2013.
DOI Google Scholar
[17]

R. Battiti, Using mutual information for selecting features in supervised neural net learning, IEEE Trans. Neural Netw., vol. 5, no. 4, pp. 537–550, 1994.
DOI Google Scholar
[18]

H. H. Hsu and C. W. Hsieh, Feature selection via correlation coefficient clustering, J. Softw., vol. 5, no. 12, pp. 1371–1377, 2010.
DOI Google Scholar
[19]

D. J. Hand and K. Yu, Idiot’s bayes—Not so stupid after all? Int. Stat. Rev., vol. 69, no. 3, pp. 385–398, 2001.
DOI Google Scholar
[20]

J. R. Quinlan, Induction of decision trees, Mach. Learn., vol. 1, no. 1, pp. 81–106, 1986.
DOI Google Scholar
[21]

G. De’ath and K. E. Fabricius, Classification and regression trees: A powerful yet simple technique for ecological data analysis, Ecology, vol. 81, no. 11, pp. 3178–3192, 2000.
DOI Google Scholar
[22]
J. Lawrence, Introduction to Neural Networks. Nevada City, CA, USA: California Scientific Software, 1993.
[23]

M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf, Support vector machines, IEEE Intell. Syst. Their Appl., vol. 13, no. 4, pp. 18–28, 1998.
DOI Google Scholar
[24]
L. Peterson, K-nearest neighbor, Scholarpedia, vol. 4, no. 2, p. 1883, 2009.
DOI
[25]
Y. Pan and Z. Tang, Ensemble methods in bank direct marketing, in Proc. 2014 11 th Int. Conf. Service Systems and Service Management (ICSSSM), Beijing, China, 2014, pp. 1–5.
[26]

O. Apampa, Evaluation of classification and ensemble algorithms for bank customer marketing response prediction, J. Int. Technol. Inf. Manag., vol. 25, no. 4, p. 6, 2016.
DOI Google Scholar
[27]
A. Lawi, A. A. Velayaty, and Z. Zainuddin, On identifying potential direct marketing consumers using adaptive boosted support vector machine, in Proc. 2017 4 th Int. Conf. Computer Applications and Information Processing Technology (CAIPT), Kuta Bali, Indonesia, 2017, pp. 1–4.
DOI
[28]
S. Kaisar and M. M. Rashid, Telemarketing outcome prediction using an ensemblebased machine learning technique, in Proc. Australasian Conf. Information Systems (ACIS), Wellington, New Zealand, 2020, p. 59.
[29]

V. L. Miguéis, A. S. Camanho, and J. Borges, Predicting direct marketing response in banking: Comparison of class imbalance methods, Serv. Bus., vol. 11, no. 4, pp. 831–849, 2017.
DOI Google Scholar
[30]
J. Asare-Frempong and M. Jayabalan, Predicting customer response to bank direct telemarketing campaign, in Proc. 2017 Int. Conf. Engineering Technology and Technopreneurship (ICE2T), Kuala Lumpur, Malaysia, 2017, pp. 1–4.
DOI
[31]

H. A. Elsalamony, Bank direct marketing analysis of data mining techniques, Int. J. Comput. Appl., vol. 85, no. 7, pp. 12–22, 2014.
DOI Google Scholar
[32]
A. G. K. Janecek, W. N. Gansterer, M. A. Demel, and G. F. Ecker, On the relationship between feature selection and classification accuracy, in Proc. 2008 Int. Conf. New Challenges for Feature Selection in Data Mining and Knowledge Discovery, Antwerp, Belgium, 2008, pp. 90–105.
[33]

S. C. K. Tékouabou, Ş. C. Gherghina, H. Toulni, P. N. Mata, M. N. Mata, and J. M. Martins, A machine learning framework towards bank telemarketing prediction, J. Risk Financ. Manag., vol. 15, no. 6, p. 269, 2022.
DOI Google Scholar
[34]
S. C. T. Koumétio and H. Toulni, Improving KNN model for direct marketing prediction in smart cities, in Machine Intelligence and Data Analytics for Sustainable Future Smart Cities, U. Ghosh, Y. Maleh, M. Alazab, and A. S. K. Pathan, eds. Cham, Switzerland: Springer, 2021, pp. 107–118.
DOI
[35]
B. A. Ram, D. J. S. Kumar, and A. Lakshmanarao, Improving efficiency of machine learning model for bank customer data using genetic algorithm approach, in Proc. Int. Conf. Innovative Computing and Communications, Delhi, India, 2021, pp. 649–657.
DOI
[36]

N. Ghatasheh, H. Faris, I. AlTaharwa, Y. Harb, and A. Harb, Business analytics in telemarketing: Cost-sensitive analysis of bank campaigns using artificial neural networks, Appl. Sci., vol. 10, no. 7, p. 2581, 2020.
DOI Google Scholar
[37]

M. Selma, Predicting the success of bank telemarketing using artificial neural network, Int. J. Economics and Management Engineering, vol. 14, no. 1, pp. 1–4, 2020.
Google Scholar
[38]
M. Singh, N. Dhanda, U. K. Farooqui, K. K. Gupta, and R. Verma, Prediction of client term deposit subscription using machine learning, in Proc. 4 th Int. Conf. Communication, Devices and Computing, Haldia, India, 2023, pp. 83–93.
DOI
[39]

S. Hou, Z. Cai, J. Wu, H. Du, and P. Xie, Applying machine learning to the development of prediction models for bank deposit subscription, Int. J. Bus. Anal., vol. 9, no. 1, pp. 1–14, 2022.
DOI Google Scholar
[40]

A. Abu-Srhan, B. Alhammad, S. A. Zghoul, and R. Al-Sayyed, Visualization and analysis in bank direct marketing prediction, Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 7, pp. 651–657, 2019.
DOI Google Scholar
[41]
A. Vitorio and G. Marques, Impact of imbalanced data on bank telemarketing calls outcome forecasting using machine learning, in Proc. 2021 Int. Conf. Data Analytics for Business and Industry (ICDABI), Sakheer, Bahrain, 2021, pp. 380–384.
DOI
[42]

F. Safarkhani and S. Moro, Improving the accuracy of predicting bank depositor’s behavior using a decision tree, Appl. Sci., vol. 11, no. 19, p. 9016, 2021.
DOI Google Scholar
[43]

Y. Feng, Y. Yin, D. Wang, and L. Dhamotharan, A dynamic ensemble selection method for bank telemarketing sales prediction, J. Bus. Res., vol. 139, pp. 368–382, 2022.
DOI Google Scholar
[44]
C. Muppala, S. Dandu, and A. Potluri, Efficient predictions on asymmetrical financial data using ensemble random forests, in Proc. Third Int. Conf. Computational Intelligence and Informatics, Hyderabad, India, 2018, pp. 361–372.
DOI
[45]
S. E. Saeed, M. Hammad, and A. Alqaddoumi, Predicting customer’s subscription response to bank telemarketing campaign based on machine learning algorithms, in Proc. 2022 Int. Conf. Decision Aid Sciences and Applications (DASA), Chiangrai, Thailand, 2022, pp. 1474–1478.
DOI
[46]

N. Ghatasheh, I. Altaharwa, and K. Aldebei, Modeling the telemarketing process using genetic algorithms and extreme boosting: Feature selection and cost-sensitive analytical approach, IEEE Access, vol. 11, pp. 67806–67824, 2023.
DOI Google Scholar
[47]

S. Hosseini, A decision support system based on machined learned Bayesian network for predicting successful direct sales marketing, J. Manag. Anal., vol. 8, no. 2, pp. 295–315, 2021.
DOI Google Scholar
[48]
M. Mitik, O. Korkmaz, P. Karagoz, I. H. Toroslu, and F. Yucel, Data mining based product marketing technique for banking products, in Proc. 2016 IEEE 16 th Int. Conf. Data Mining Workshops (ICDMW), Barcelona, Spain, 2016, pp. 552–559.
DOI
[49]
D. W. Tan, S. Y. Liew, and W. Yeoh, Improving telemarketing intelligence through significant proportion of target instances, in Proc. 2014 Pacific Asia Conf. Information Systems (PACIS), Chengdu, China, 2014, p. 368.
[50]

S. B. Kotsiantis, D. Kanellopoulos, and P. E. Pintelas, Data preprocessing for supervised leaning, Int. J. Computer Science, vol. 1, no. 1, pp. 111–117, 2006.
Google Scholar
[51]
T. M. Cover and J. A. Thomas, Elements of Information Theory. Hoboken, NJ, USA: Wiley-Interscience, 2006.
[52]
M. M. Ulkhaq, A. T. Wibowo, M. R. Tribosnia, R. Putawara, and A. B. Firdauz, Predicting customer churn: A comparison of eight machine learning techniques: A case study in an Indonesian telecommunication company, in Proc. 2021 Int. Conf. Data Analytics for Business and Industry (ICDABI), Sakheer, Bahrain, 2021, pp. 42–46.
DOI
[53]
M. M. Khaled and Z. A. Aghbari, ccfDetector: Utilizing GAN and deep learning for credit card fraud detection, in Proc. 2023 Advances in Science and Engineering Technology Int. Conf. (ASET), Dubai, United Arab Emirates, 2023, pp. 1–6.
DOI
[54]

C. N. Nwafor and O. Z. Nwafor, Determinants of non-performing loans: An explainable ensemble and deep neural network approach, Finance Res. Lett., vol. 56, p. 104084, 2023.
DOI Google Scholar
[55]
S. Ruiz, P. Gomes, L. Rodrigues, and J. Gama, Assembled feature selection for credit scoring in microfinance with non-traditional features, in Proc. 23 rd Int. Conf. Discovery Science, Thessaloniki, Greece, 2020, pp. 207–216.
DOI
[56]

G. Kumar and N. Parimala, A weighted sum method MCDM approach for recommending product using sentiment analysis, Int. J. Bus. Inf. Syst., vol. 35, no. 2, pp. 185–203, 2020.
DOI Google Scholar
[57]

N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, SMOTE: Synthetic minority over-sampling technique, J. Artif. Intell. Res., vol. 16, pp. 321–357, 2002.
DOI Google Scholar
[58]
H. Han, W. Y. Wang, and B. H. Mao, Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning, in Proc. Int. Conf. Intelligent Computing, Hefei, China, 2005, pp. 878–887.
DOI
[59]
H. He, Y. Bai, E. A. Garcia, and S. Li, ADASYN: Adaptive synthetic sampling approach for imbalanced learning, in Proc. 2008 IEEE Int. Joint Conf. Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China, 2008, pp. 1322–1328.
[60]

L. Breiman, Random forests, Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
DOI Google Scholar
[61]
Q. Wang and X. Wei, The detection of network intrusion based on improved adaboost algorithm, in Proc. 2020 4 th Int. Conf. Cryptography, Security and Privacy, Nanjing, China, 2020, pp. 84–88.
DOI
[62]

J. H. Friedman, Greedy function approximation: A gradient boosting machine, Ann. Statist., vol. 29, no. 5, pp. 1189–1232, 2001.
DOI Google Scholar
[63]

D. Upadhyay, J. Manero, M. Zaman, and S. Sampalli, Gradient boosting feature selection with machine learning classifiers for intrusion detection on power grids, IEEE Trans. Netw. Serv. Manag., vol. 18, no. 1, pp. 1104–1116, 2021.
DOI Google Scholar
Publication history
Copyright
Rights and permissions

Publication history

Received: 08 May 2023
Revised: 02 November 2023
Accepted: 26 December 2023
Published: 22 April 2024
Issue date: June 2024

Copyright

© The author(s) 2023.

Rights and permissions

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return