Machine Learning and Natural Language Processing for Predicting Islamic Fintech Adoption Intention: Evidence from Bangladesh – Comparison with Structural Equation Modeling
DOI:
https://doi.org/10.53799/df6bbs33Keywords:
Islamic Fintech, Machine Learning, Natural Language Processing, Technology Adoption, Trust, Bangladesh, Random Forest, Sentiment AnalysisAbstract
Islamic finance and digital financial technology have sparked academic and practical engagement, especially in Muslim nations of the developing world like Bangladesh. This study uses a dual approach of artificial intelligence (AI) techniques: supervised machine learning (ML) classification and lexicon-based natural language processing (NLP) sentiment analysis to analyze the determinants and public perception of the adoption of Islamic fintech. The survey data obtained from 301 respondents were trained with four ML algorithms: Logistic Regression, Support Vector Machine (SVM), Random Forest, and Gradient Boosting for the operationalization of intended Islamic fintech services as binary (median split). The feature importance analysis for the Random Forest gave the following results: most important features: Trust, Religiosity, Digital Literacy, Perceived Risk, Social Influence, and Facilitating Conditions. The test accuracy of Logistic Regression was the highest (83.61%), while the F1 score was 0.643 and the ROC-AUC value was 0.881, which indicates that the adoption decision is predominantly linear. A TextBlob NLP pipeline was run on a representative sample of social media text to classify public sentiment, yielding a polarity ratio of 2:1 positive to negative. The results contribute to the broader body of knowledge on utilizing AI tools for Islamic banking behavioral research and offer policy insights for fintech firms, Islamic financial institutions, regulators, and digital financial inclusion actors in Bangladesh.
References
[1] M. A. S. Shateri, A. Moustafa, W. Ismail, and M. Al-Emran, "Examining the impact of Islamic religiosity on students' intention to use online learning," Int. J. Emerg. Technol. Learn., vol. 15, no. 7, pp. 95–111, 2020.
[2] M. Aisyah, "Consumer demand on Islamic banking: The influence of halal/haram standards, quality of services, and attractiveness of products," Al-Iqtishad, vol. 10, no. 1, pp. 167–182, 2018.
[3] S. S. Alam, H. Janor, C. Zanariah, M. N. Ahsan, and C. A. C. Wel, "Isreligiosity an important determinant on Muslim consumer behaviour in Malaysia?" J. Islamic Mark., vol. 3, no. 1, pp. 83–96, 2012.
[4] A. A. Alalwan, Y. K. Dwivedi, and N. P. Rana, "Factors influencing adoption of mobile banking by Jordanian bank customers: Extending UTAUT2 with trust," Int. J. Inf. Manage., vol. 37, no. 3, pp. 99–110, 2017.
[5] D. G. Altman and P. Royston, "The cost of dichotomising continuous variables," BMJ, vol. 332, no. 7549, p. 1080, 2006.
[6] S. Akhter and A. S. Abbasi, "Islamic banking in Bangladesh: Prospects and challenges," J. Islamic Bank. Finance, vol. 34, no. 3, pp. 52–62, 2017.
[7] Bangladesh Bank, Annual Report on Mobile Financial Services. Dhaka:Bangladesh Bank Publications, 2023.
[8] G. Baptista and T. Oliveira, "Understanding mobile banking: The unified theory of acceptance and use of technology combined with culturalmoderators," Comput. Hum. Behav., vol. 50, pp. 418–430, 2015.
[9] L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001. [referred to as [10] in text]
[10] L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
[11] T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD, 2016, pp. 785–794.
[15] C. Cortes and V. Vapnik, "Support-vector networks," Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995.
[16] F. D. Davis, "Perceived usefulness, perceived ease of use, and useracceptance of information technology," MIS Q., vol. 13, no. 3, pp. 319–340, 1989.
[19] M. S. Featherman and P. A. Pavlou, "Predicting e-services adoption: A perceived risk facets perspective," Int. J. Hum.-Comput. Stud., vol. 59, no. 4, pp. 451–474, 2003.
[21] J. H. Friedman, "Greedy function approximation: A gradient boosting machine," Ann. Stat., vol. 29, no. 5, pp. 1189–1232, 2001.
[22] D. Gefen, E. Karahanna, and D. W. Straub, "Trust and TAM in online shopping: An integrated model," MIS Q., vol. 27, no. 1, pp. 51–90, 2003.
[23] J. F. Hair, J. J. Risher, M. Sarstedt, and C. M. Ringle, "When to use and how to report the results of PLS-SEM," Eur. Bus. Rev., vol. 31, no. 1, pp. 2–24, 2019.
[25] J. A. Hanley and B. J. McNeil, "The meaning and use of the area under a receiver operating characteristic (ROC) curve," Radiology, vol. 143, no. 1, pp. 29–36, 1982.
[26] M. K. Hassan, M. R. Rabbani, and M. A. M. Ali, "Challenges for the Islamic finance and banking in post COVID era and the role of fintech," J. Econ. Coop. Dev., vol. 41, no. 3, pp. 93–116, 2020.
[28] D. W. Hosmer, S. Lemeshow, and R. X. Sturdivant, Applied Logistic Regression, 3rd ed. Hoboken, NJ: Wiley, 2013.
[29] C. W. Hsu, C. C. Chang, and C. J. Lin, "A practical guide to support vector classification," Tech. Rep., Nat. Taiwan Univ., 2003.
[31] D. Iacobucci, S. S. Posavac, F. R. Kardes, M. J. Schneider, and D. L. Popovich, "The median split: Robust, refined, and revived," J. Consum. Psychol., vol. 25, no. 4, pp. 690–704, 2015.
[32] Islamic Finance Development Report, Shifting Dynamics. Washington, DC: Refinitiv & ICD, 2023.
[33] O. Kaya, J. Schildbach, D. B. AG, and S. Schneider, "Artificial intelligence in banking," Deutsche Bank Research, 2019.
[34] A. Kesharwani and S. S. Bisht, "The impact of trust and perceived risk on internet banking adoption in India," Int. J. Bank Mark., vol. 30, no. 4, pp. 303–322, 2012.
[42] Y. Park, "The use of information and communication technology (ICT) in higher education," Innov. Educ. Teach. Int., vol. 46, no. 3, pp. 263–272, 2009.
[43] F. Pedregosa et al., "Scikit-learn: Machine learning in Python," J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.
[44] D. M. W. Powers, "Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation," J. Mach. Learn. Technol., vol. 2, no. 1, pp. 37–63, 2011.
[45] M. R. Rabbani et al., "Exploring the role of Islamic fintech in combating the aftershocks of COVID-19," J. Open Innov. Technol. Mark. Complex., vol. 7, no. 2, p. 136, 2021.
[47] H. S. Ryu, "What makes users willing or reluctant to use fintech?" Ind. Manage. Data Syst., vol. 118, no. 3, pp. 541–569, 2018.
[48] M. Sarstedt, J. F. Hair, C. M. Ringle, K. O. Thiele, and S. P. Gudergan, "Estimation issues with PLS and CBSEM: Where the bias lies!" J. Bus. Res., vol. 69, no. 10, pp. 3998–4010, 2019.
[50] M. A. Shareef, A. Baabdullah, S. Dewan, N. P. Rana, and Y. K. Dwivedi, "Consumer adoption of mobile banking services," J. Retail. Consum. Serv., vol. 43, pp. 54–67, 2018.
[51] G. Shmueli, S. Ray, J. M. Velasquez Estrada, and S. B. Chatla, "The elephant in the room: Predictive performance of PLS models," J. Bus. Res., vol. 69, no. 10, pp. 4552–4564, 2019.
[52] N. Souiden and M. Rani, "Consumer attitudes and purchase intentions toward Islamic banks: The influence of religiosity," Int. J. Bank Mark., vol. 33, no. 2, pp. 143–161, 2015.
[55] A. J. van Deursen and J. A. van Dijk, "The first-level digital divide shifts from inequalities in physical access to inequalities in material access," New Media Soc., vol. 21, no. 2, pp. 354–375, 2019.
[57] V. Venkatesh, M. G. Morris, G. B. Davis, and F. D. Davis, "Useracceptance of information technology: Toward a unified view," MIS Q., vol. 27, no. 3, pp. 425–478, 2003.
[58] V. Venkatesh, J. Y. Thong, and X. Xu, "Consumer acceptance and use of information technology: Extending UTAUT," MIS Q., vol. 36, no. 1, pp. 157–178, 2012.
[59] W. Verbeke et al., "New insights into churn prediction in the telecommunication sector," Eur. J. Oper. Res., vol. 218, no. 1, pp. 211–229, 2012.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 AIUB Journal of Science and Engineering
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
AJSE contents are under the terms of the Creative Commons Attribution License. This permits anyone to copy, distribute, transmit and adapt the work non-commercially provided the original work and source is appropriately cited.
