Takagi-Sugeno Neuro-Fuzzy Credit Risk Assessment for Micro, Small, and Medium Enterprises: Integration with Define-Measure-Analyze-Improve-Control-Based Quality Management

Credit scoring for Micro, Small, and Medium Enterprises (MSMEs) remains a critical challenge in emerging economies, where lending decisions must balance financial inclusion and risk mitigation. In practice, MSME credit evaluation relies heavily on structured expert judgment, which often leads to inconsistencies and limited auditability across decision processes. To address this issue, this study proposes an optimized Takagi-Sugeno Neuro-Fuzzy (NFTS) credit scoring model trained using an Accelerated Levenberg-Marquardt algorithm to approximate expert-based credit scores, rather than to predict loan default events. By focusing on expert score replication, the proposed approach aims to standardize and operationalize institutional credit assessment practices. The proposed model is evaluated using a dataset of 1,200 real-world MSME credit records collected from multiple provinces in Indonesia, with expert-assigned credit scores serving as the target variable. Model performance is benchmarked across eleven membership configurations and compared with conventional machine learning models, with additional validation conducted using k-fold cross-validation to ensure robustness and generalization stability. The optimal configuration (M10) achieves RMSE = 0.08, MAE = 0.04, MAPE = 0.05, and R2 = 1.00, indicating strong alignment with expert-assigned scores rather than perfect prediction of real-world default outcomes. Beyond algorithmic performance, the proposed NFTS model is embedded within a Total Quality Management (TQM) framework using the Define-Measure-Analyze-Improve-Control (DMAIC) cycle to support organizational integration, dashboard-based monitoring, and governance-oriented process control. The results demonstrate that Neuro-Fuzzy systems, when combined with quality management principles, can function as robust and explainable decision-support tools for standardized MSME credit evaluation.

Accelerated levenberg-marquardt algorithm; DMAIC; Expert-Based credit score; MSME credit scoring; Takagi-Sugeno neuro-fuzzy; Total quality management

Abbadi, S., & Karsh, S. M. A. (2013), ‘Methods of evaluating credit risk used by commercial banks’, International Research Journal of Finance and Economics, no. 111

Akay, B., Karaboga, D., & Akay, R. (2022), ‘A comprehensive survey on optimizing deep learning models by metaheuristics’, Artificial Intelligence Review, vol. 55, no. 2, pp. 829–894, https://doi.org/10.1007/s10462-021-09992-0

Alamsyah, A., Hafidh, A. A., & Mulya, A. D. (2025), ‘Innovative credit risk assessment: Leveraging social media data for inclusive credit scoring in Indonesia’s fintech sector’, Journal of Risk and Financial Management, vol. 18, no. 2, https://doi.org/10.3390/jrfm18020074

Asogbon, M. G., Olabode, O., Agbonifo, O. C., Samuel, O. W., & Yemi-Peters, V. I. (2016), ‘Adaptive neuro-fuzzy inference system for mortgage loan risk assessment’, International Journal of Intelligent Information Systems, vol. 5, no. 1, pp. 17–24, https://doi.org/10.11648/j.ijiis.20160501.13

Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., & Herrera, F. (2020), ‘Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI’, Information Fusion, vol. 58, https://doi.org/10.1016/j.inffus.2019.12.012

Billah, M., Waheed, S., & Hanifa, A. (2017), ‘Stock market prediction using an improved training algorithm of neural network’, ICECTE 2016 - 2nd International Conference on Electrical, Computer and Telecommunication Engineering, https://doi.org/10.1109/ICECTE.2016.7879611

Chen, S. (2023), ‘A novel ensemble machine learning model for credit risk prediction’, Advances in Economics, Management and Political Sciences, vol. 46, no. 1, https://doi.org/10.54254/2754-1169/46/20230356

Chen, X. Q., Ma, C. Q., Ren, Y. S., Lei, Y. T., Huynh, N. Q. A., & Narayan, S. (2023), ‘Explainable artificial intelligence in finance: A bibliometric review’, Finance Research Letters, vol. 56, https://doi.org/10.1016/j.frl.2023.104145

Djeundje, V. B., Crook, J., Calabrese, R., & Hamid, M. (2021), ‘Enhancing credit scoring with alternative data’, Expert Systems with Applications, vol. 163, https://doi.org/10.1016/j.eswa.2020.113766

Grishunin, S., Suloeva, S., Egorova, A., & Burova, E. (2020), ‘Comparison of empirical methods for the reproduction of global manufacturing companies’ credit ratings’, International Journal of Technology, vol. 11, no. 6, pp. 1223–1232, https://doi.org/10.14716/ijtech.v11i6.4424

Grishunin, S., Suloeva, S., Shiryakina, V., & Burova, E. (2021), ‘Analyzing insolvency drivers and developing credit rating system for small and medium-sized enterprises in Russia’, International Journal of Technology, vol. 12, no. 7, pp. 1479–1487, https://doi.org/10.14716/ijtech.v12i7.5349

Gupta, A. (2007), ‘Computational intelligence in time series forecasting: Theory and engineering applications’, International Journal of Robust and Nonlinear Control, vol. 17, no. 4, https://doi.org/10.1002/rnc.1153

Hintze, A. (2016), ‘Understanding the four types of artificial intelligence, from reactive robots to self-aware beings’, https://theconversation.com/understanding-the-four-types-of-ai-from-reactive-robots-to-self-aware-beings-67616

Hlongwane, R., Ramaboa, K. K. K. M., & Mongwe, W. (2024), ‘Enhancing credit scoring accuracy with a comprehensive evaluation of alternative data’, PLoS ONE, vol. 19, no. 5, https://doi.org/10.1371/journal.pone.0303566

Hyndman, R. J., & Koehler, A. B. (2006), ‘Another look at measures of forecast accuracy’, International Journal of Forecasting, vol. 22, no. 4, https://doi.org/10.1016/j.ijforecast.2006.03.001

Ikasari (2014), ‘Credit decision support methodology for micro, small and medium enterprises (MSMEs): Indonesian cases’

Jang, J. S. R. (1993), ‘ANFIS: Adaptive-network-based fuzzy inference system’, IEEE Transactions on Systems, Man and Cybernetics, vol. 23, no. 3, https://doi.org/10.1109/21.256541

Kalra, S., & Prasad, J. S. (2019), ‘Efficacy of news sentiment for stock market prediction’, Proceedings of the International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon 2019), https://doi.org/10.1109/COMITCon.2019.8862265

Kim, S., & Kim, H. (2016), ‘A new metric of absolute percentage error for intermittent demand forecasts’, International Journal of Forecasting, vol. 32, no. 3, pp. 669–679, https://doi.org/10.1016/j.ijforecast.2015.12.003

Liu, Y., Liu, Y., Shao, Q., Wang, R., & Lv, Y. (2024), ‘A novel neuro-fuzzy learning algorithm for first-order Takagi–Sugeno fuzzy model: Caputo fractional-order gradient descent method’, International Journal of Fuzzy Systems, vol. 26, no. 8, https://doi.org/10.1007/s40815-024-01750-y

Majumder, M. M. R., Hossain, M. I., & Hasan, M. K. (2019), ‘Indices prediction of Bangladeshi stock by using time series forecasting and performance analysis’, 2nd International Conference on Electrical, Computer and Communication Engineering (ECCE 2019), https://doi.org/10.1109/ECACE.2019.8679480

Malhotra, R., & Malhotra, D. K. (2015), ‘Evaluating loans using a combination of data envelopment and neuro-fuzzy systems’, 6th International Multi-Conference on Complexity, Informatics and Cybernetics (IMCIC 2015) and 6th International Conference on Society and Information Technologies (ICSIT 2015)

Mohammadi, N., & Zangeneh, M. (2016), ‘Customer credit risk assessment using artificial neural networks’, International Journal of Information Technology and Computer Science, vol. 8, no. 3, pp. 58–66, https://doi.org/10.5815/ijitcs.2016.03.07

Mokoginta, H., Paputungan, Y. S., Yusniar, Harsono, I., & Ramadhani, H. (2024), ‘The effect of macroeconomic factors on banking credit risk study on commercial banks in Indonesia’, Jurnal Aktiva: Riset Akuntansi dan Keuangan, vol. 6, no. 1, https://doi.org/10.52005/aktiva.v6i1.224

Ouifak, H., & Idri, A. (2023), ‘On the performance and interpretability of Mamdani and Takagi–Sugeno–Kang based neuro-fuzzy systems for medical diagnosis’, Scientific African, vol. 20, https://doi.org/10.1016/j.sciaf.2023.e01610

Palit, A. K., & Babuška, R. (2001), ‘Efficient training algorithm for Takagi–Sugeno type neuro-fuzzy network’, IEEE International Conference on Fuzzy Systems, vol. 3, https://doi.org/10.1109/FUZZ.2001.1008912

Pasila, F. (2008), ‘Multivariate inputs for electrical load forecasting on hybrid neuro-fuzzy and fuzzy c-means forecaster’, IEEE International Conference on Fuzzy Systems, https://doi.org/10.1109/FUZZY.2008.4630690

Pasila, F., & Alimin, R. (2016), ‘Applications of artificial intelligence control for parallel discrete-manipulators’, 4th IGNITE Conference and International Conference on Advanced Informatics: Concepts, Theory and Application (ICAICTA 2016), https://doi.org/10.1109/ICAICTA.2016.7803114

Pasila, F., Palit, A. K., & Thiele, G. (2008), ‘Neuro-fuzzy approaches for forecasting electrical load using additional moving average window data filter on Takagi–Sugeno type MISO networks’, Journal of Advanced Computational Intelligence and Intelligent Informatics, vol. 12, no. 4, https://doi.org/10.20965/jaciii.2008.p0361

Pasila, F., Ronni, S., Thiang, & Wijaya, L. H. (2008), ‘Long-term forecasting in financial stock market using accelerated LMA on neuro-fuzzy structure and additional fuzzy c-means clustering for optimizing the GMFs’, Proceedings of the International Joint Conference on Neural Networks, https://doi.org/10.1109/IJCNN.2008.4634367

Russell, S., & Norvig, P. (2021), Artificial intelligence: A modern approach, 4th edn, Pearson

Russell, S., & Norvig, P. (2022), Artificial intelligence: A modern approach, 4th edn, Pearson

Sujatha, R., Kavitha, D., Maheswari, B. U., & Ajay, K. G. (2025), ‘Ensemble machine learning models for corporate credit risk prediction: A comparative study’, SN Computer Science, vol. 6, no. 5, https://doi.org/10.1007/s42979-025-04053-7

Surjaningsih, N., Kurniati, I. N., & Indriani, R. (2018), ‘Credit risk models for five major sectors in Indonesia’, Buletin Ekonomi Moneter dan Perbankan, vol. 20, no. 4, https://doi.org/10.21098/bemp.v20i4.900

Tantisripreecha, T., & Soonthomphisaj, N. (2018), ‘Stock market movement prediction using LDA-online learning model’, 2018 IEEE/ACIS 19th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD 2018), https://doi.org/10.1109/SNPD.2018.8441038

Weber, P., Carl, K. V., & Hinz, O. (2024), ‘Applications of explainable artificial intelligence in finance: A systematic review of finance, information systems, and computer science literature’, Management Review Quarterly, vol. 74, no. 2, https://doi.org/10.1007/s11301-023-00320-0

Willmott, C. J., & Matsuura, K. (2005), ‘Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance’, Climate Research, vol. 30, no. 1, https://doi.org/10.3354/cr030079

Xu, Q., Xie, W., Liao, B., Hu, C., Qin, L., Yang, Z., Xiong, H., Lyu, Y., Zhou, Y., & Luo, A. (2023), ‘Interpretability of clinical decision support systems based on artificial intelligence from technological and medical perspective: A systematic review’, Journal of Healthcare Engineering, vol. 2023, https://doi.org/10.1155/2023/9919269

Zander, E., van Oostendorp, B., & Bede, B. (2023), ‘Reinforcement learning with Takagi–Sugeno–Kang fuzzy systems’, Complex Engineering Systems, vol. 3, no. 2, https://doi.org/10.20517/ces.2023.11

Zhang, L., & Wang, L. (2024), ‘An ensemble learning-enhanced smart prediction model for financial credit risks’, Journal of Circuits, Systems and Computers, vol. 33, no. 7, https://doi.org/10.1142/S0218126624501299

Zhang, Z., Shen, Y., Zhang, G., Song, Y., & Zhu, Y. (2017), ‘Short-term prediction for opening price of stock market based on self-adapting variant PSO-Elman neural network’, Proceedings of the IEEE International Conference on Software Engineering and Service Sciences (ICSESS 2017), https://doi.org/10.1109/ICSESS.2017.8342901