Debtor Eligibility Prediction Using Deep Learning with Chatbot-Based Testing

Reski Noviania; Enny Itje Sela; Luther Alexander Latumakulita; Steven R. Sentinuwo

doi:10.17977/um018v7i22024p128-138

Debtor Eligibility Prediction Using Deep Learning with Chatbot-Based Testing

Reski Noviania, Enny Itje Sela, Luther Alexander Latumakulita, Steven R. Sentinuwo

Abstract

Predicting debtor eligibility is essential for effective risk management and minimizing bad credit risks. However, financial institutions face challenges such as imbalanced data, inefficient feature selection, and limited user accessibility. This study combines Recursive Feature Elimination (RFE) and Deep Learning (DL) to improve prediction accuracy and integrates a chatbot interface for user-friendly testing. RFE effectively identifies critical features, while the DL model achieves a validation accuracy of 97.62%, surpassing previous studies with less comprehensive methodologies. The chatbot's novel design not only ensures accessibility but also enhances user engagement through flexible input options, such as approximate values, enabling non-experts to interact seamlessly with the system. For financial institutions, this chatbot-based testing approach offers practical benefits by streamlining debtor evaluation processes, reducing dependency on manual assessments, and providing consistent, scalable, and efficient solutions for credit risk management. It allows institutions to handle inquiries outside business hours, ensuring a continuous service flow. Furthermore, the system’s flexibility supports better customer interaction, increasing trust and transparency. By combining advanced machine learning with accessible interfaces, this study offers a scalable solution to improve the precision and practicality of debtor eligibility assessments, making it a valuable tool for modern financial institutions.

Full Text:

PDF

References

N. Kozodoi, J. Jacob, and S. Lessmann, “Fairness in credit scoring: Assessment, implementation and profit implications,” Eur. J. Oper. Res., vol. 297, no. 3, pp. 1083–1094, Mar. 2022.

S. Filomeni, G. F. Udell, and A. Zazzaro, “Communication frictions in banking organizations: Evidence from credit score lending,” Econ. Lett., vol. 195, no. 109412, p. 109412, Oct. 2020.

Y. Tan, M. C. K. Lau, and G. Gozgor, “Competition and Profitability: Impacts on Stability in Chinese Banking,” Int. J. Econ. Bus., vol. 28, no. 2, pp. 197–220, May 2021.

A. Bitetto, P. Cerchiello, S. Filomeni, A. Tanda, and B. Tarantino, “Machine learning and credit risk: Empirical evidence from small- and mid-sized businesses,” Socioecon. Plann. Sci., vol. 90, no. 101746, p. 101746, Dec. 2023.

R. M. Sum, W. Ismail, Z. H. Abdullah, N. F. M. N. Shah, and R. Hendradi, “A new efficient credit scoring model for personal loan using data mining technique for sustainability management,” J. Sustain. Sci. Manag., vol. 17, no. 5, pp. 2672–7226, 2022.

D. Kumar, R. Maddikunta, A. Chella, and R. Myadaraboina, “Machine learning approaches for predicting loan approval using chat bots,” Int. J. Progress. Res. Eng. Manag. Sci., vol. 04, no. 05, pp. 288–297, 2024.

B. Dushimimana, Y. Wambui, T. Lubega, and P. E. McSharry, “Use of machine learning techniques to create a credit score model for airtime loans,” J. Risk Financ. Manag., vol. 13, no. 8, 2020.

Y. Wu and Y. Pan, “Application analysis of credit scoring of financial institutions,” Complexity, vol. 2021, no. 9222617, 2021.

C. Wang, D. Han, Q. Liu, and S. Luo, “A deep learning approach for credit scoring of peer-to-peer lending using attention mechanism LSTM,” IEEE Access, vol. 7, pp. 2161–2168, 2019.

D. West, “Neural network credit scoring models,” Comput. Oper. Res., vol. 27, no. 11–12, pp. 1131–1152, Sep. 2000.

S. Prathipa, S. Haroon Prakash, D. Dinesh Kumar, and G. Tejesh Kumar, “Loan Management System Using Chatbot,” in 2024 International Conference on Communication, Computing and Internet of Things (IC3IoT), Apr. 2024, pp. 1–6.

I. Wickramasinghe and H. Kalutarage, “Naive Bayes: applications, variations and vulnerabilities: a review of literature with code snippets for implementation,” Soft Comput., vol. 25, no. 3, pp. 2277–2293, 2021.

J. Singh, M. H. Joesph, and K. B. A. Jabbar, “Rule-based chabot for student enquiries,” J. Phys. Conf. Ser., vol. 1228, no. 1, 2019.

C. Papakostas, C. Troussas, A. Krouska, and C. Sgouropoulou, “A Rule-Based Chatbot Offering Personalized Guidance in Computer Programming Education,” in Lecture Notes in Computer Science, vol. 14799, 2024, pp. 253–264.

D.-H. Kim, H.-S. Im, J.-H. Hyeon, and J.-W. Jwa, “Development of the rule-based smart tourism chatbot using Neo4J graph database,” Int. J. Internet, Broadcast. Commun., vol. 13, no. 2, pp. 179–186, 2021.

M. Jang, Y. Jung, and S. Kim, “Investigating managers’ understanding of chatbots in the Korean financial industry,” Comput. Human Behav., vol. 120, p. 106747, Jul. 2021.

S. A. Thorat and V. Jadhav, “A review on implementation issues of rule-based chatbot systems,” SSRN Electron. J., no. Icicc, pp. 1–6, 2020.

Y. Kwon et al., “Osteoporosis pre-screening using ensemble machine learning in postmenopausal Korean women,” Healthc., vol. 10, no. 6, 2022.

W. Lian, G. Nie, B. Jia, D. Shi, Q. Fan, and Y. Liang, “An intrusion detection method based on decision tree-recursive feature elimination in ensemble learning,” Math. Probl. Eng., vol. 2020, 2020.

E. A. Kadasah, “Artificial Intelligence Powered Chatbot for Business,” Int. J. Inf. Technol. Bus., vol. 4, no. 2, pp. 61–66, May 2023.

F. Safarkhani and S. Moro, “Improving the accuracy of predicting bank depositor’s behavior using a decision tree,” Appl. Sci., vol. 11, no. 19, 2021.

V. K. Zhirov, N. A. Staroverova, M. L. Shustrova, and M. N. Tomilova, “Neural network as a tool to solve the problem of credit scoring,” J. Phys. Conf. Ser., vol. 2032, no. 1, 2021.

Y. Li and W. Chen, “A comparative performance assessment of ensemble learning for credit scoring,” Mathematics, vol. 8, no. 10, pp. 1–19, 2020.

Y. Wang, Y. Zhang, Y. Lu, and X. Yu, “A comparative assessment of credit risk model based on machine learning a case study of bank loan data,” Procedia Comput. Sci., vol. 174, pp. 141–149, 2020.

C. Yu, Y. Jin, Q. Xing, Y. Zhang, S. Guo, and S. Meng, “Advanced User Credit Risk Prediction Model Using LightGBM, XGBoost and Tabnet with SMOTEENN,” in 2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems (ICPICS), Jul. 2024, pp. 876–883.

M. K. Nallakaruppan, B. Balusamy, M. L. Shri, V. Malathi, and S. Bhattacharyya, “An Explainable AI framework for credit evaluation and analysis,” Appl. Soft Comput., vol. 153, no. 111307, p. 111307, Mar. 2024.

X. Luo, S. Tong, Z. Fang, and Z. Qu, “Frontiers: Machines vs. humans: The impact of artificial intelligence chatbot disclosure on customer purchases,” Mark. Sci., vol. 38, no. 6, pp. 937–947, 2019.

M. A. Muslim, Y. Dasril, A. Alamsyah, and T. Mustaqim, “Bank predictions for prospective long-term deposit investors using machine learning LightGBM and SMOTE,” J. Phys. Conf. Ser., vol. 1918, no. 4, 2021.

E. Ileberi, Y. Sun, and Z. Wang, “Performance Evaluation of Machine Learning Methods for Credit Card Fraud Detection Using SMOTE and AdaBoost,” IEEE Access, vol. 9, no. 165286, pp. 165286–165294, 2021.

A. Fernández, S. García, F. Herrera, and N. V. Chawla, “SMOTE for Learning from Imbalanced Data: Progress and Challenges, Marking the 15-year Anniversary,” J. Artif. Intell. Res., vol. 61, pp. 863–905, 2018.

Y. Li, Y. Fan, S. Wang, J. Bai, and K. Li, “Application of YOLOv5 based on attention mechanism and receptive field in identifying defects of thangka images,” IEEE Access, vol. 10, no. July, pp. 81597–81611, 2022.

P. Giudici, B. Hadji-Misheva, and A. Spelta, “Network based credit risk models,” Qual. Eng., vol. 32, no. 2, pp. 199–211, 2020.

M. A. Muslim, A. Nurzahputra, and B. Prasetiyo, “Improving accuracy of c4.5 algorithm using split feature reduction model and bagging ensemble for credit card risk prediction,” Int. Conf. Inf. Commun. Technol., pp. 141–145, 2018.

E. Priyanto, E. I. Sela, L. A. Latumakulita, and N. Islam, “Decision Tree C4.5 Performance Improvement using Synthetic Minority Oversampling Technique (SMOTE) and K-Nearest Neighbor for Debtor Eligibility Evaluation,” Ilk. J. Ilm., vol. 15, no. 2, pp. 373–381, Aug. 2023.

M. Ghaleb et al., “Mining the chatbot brain to improve COVID-19 bot response accuracy,” Comput. Mater. Contin., vol. 70, no. 2, pp. 2619–2638, 2022.

S. Zhang and J. Song, “A chatbot based question and answer system for the auxiliary diagnosis of chronic diseases based on large language model,” Sci. Rep., vol. 14, no. 1, p. 17118, Jul. 2024.

DOI: http://dx.doi.org/10.17977/um018v7i22024p128-138