A Hybrid Decision Tree Deep Neural Network (DT-DNN) Model with Quadratic Activation Function for SME Credit Scoring
Received: 12 January 2026 | Revised: 14 February 2026 | Accepted: 20 February 2026 | Online: 4 April 2026
Corresponding author: F. M. R. Venusiana
Abstract
Small and Medium Enterprises (SMEs) often face limited access to formal credit due to incomplete financial records, motivating the use of alternative data sources for credit risk assessment. This study proposes a hybrid Decision Tree-Deep Neural Network (DT-DNN) model with a Quadratic Activation Function (QAF) for SME credit scoring using large-scale telecommunication data. Α Decision Tree performs embedded structural feature generation through leaf encoding, transforming original input variables into interpretable hierarchical representations that capture risk segmentation and class probability information. These leaf-encoding features are subsequently integrated into a Deep Neural Network (DNN), where the QAF enhances nonlinear interaction learning and improves class separability under severe class imbalance conditions. The experimental results demonstrate that the proposed hybrid DT-DNN with QAF achieved strong and consistent class-level discrimination. At the class level, and relative to the standalone DNN baseline, the proposed model improves the AUC of the On Time category from 0.831 to 0.873 (+5.05%) and the Late Payment category from 0.801 to 0.859 (+7.24%), indicating substantially enhanced separability for non-default customer segments. For the Default class, the model maintains meaningful predictive capability (AUC = 0.776) despite severe class imbalance and overlapping behavioral patterns. In addition, the proposed approach achieves a 1.41% improvement in weighted AUC compared to the Decision Tree baseline, confirming that the integration of decision tree-based leaf encoding with quadratic nonlinear learning enhances predictive accuracy while maintaining interpretability. Overall, these findings establish the proposed hybrid framework as a robust and explainable solution for SME credit scoring using alternative telecommunication data, particularly in imbalanced and data-scarce lending environments.
Keywords:
hybrid DT-DNN, quadratic activation function, SME credit scoring, decision tree, deep neural network, credit risk classificationDownloads
References
A. Gicić and D. Đonko, "Revolutionizing Credit Risk Management: Opportunities and Challenges in Credit Scoring with AI and Deep Learning," in Business, Management and Economics, vol. 42, A. Maček and M. Murg, Eds. IntechOpen, 2025. DOI: https://doi.org/10.5772/intechopen.1011543
L. Adam et al., "Driving Financial Inclusion in Indonesia with Innovative Credit Scoring," Journal of Risk and Financial Management, vol. 18, no. 8, Aug. 2025, Art. no. 442. DOI: https://doi.org/10.3390/jrfm18080442
E. Costa, E Silva, I. C. Lopes, A. Correia, and S. Faria, "A logistic regression model for consumer default risk," Journal of Applied Statistics, vol. 47, no. 13–15, pp. 2879–2894, Nov. 2020. DOI: https://doi.org/10.1080/02664763.2020.1759030
K. S. Ling, S. S. Jamaian, and S. Mansur, "Credit Scoring Model for Tenants Using Logistic Regression," in Proceedings of the 8th International Conference on the Applications of Science and Mathematics, vol. 294, A. Mustapha, N. Ibrahim, H. Basri, M. S. Rusiman, and S. Zuhaib Haider Rizvi, Eds. Springer Nature Singapore, 2023, pp. 213–227. DOI: https://doi.org/10.1007/978-981-99-2850-7_19
H. Wang, "Application of Decision Tree Model in Personal Credit Scoring and Its Fairness Optimization," Advances in Economics, Management and Political Sciences, vol. 176, no. 1, pp. 109–118, Apr. 2025. DOI: https://doi.org/10.54254/2754-1169/2025.22114
Y. Syahra, Y. F. Br. Tarigan, K. Andriani, H. W. Nazry, and R. Setik, "Decision Trees in Predicting Loan Default Risk in Customer Relationships within the Financial Sector," Sinkron, vol. 9, no. 2, pp. 734–745, Apr. 2025. DOI: https://doi.org/10.33395/sinkron.v9i2.14672
I. Babu, R. V. S. Balan, and P. P. Mathai, "Machine Learning Approaches Used For Prediction In Diverse Fields," International Journal of Recent Technology and Engineering, vol. 8, no. 2S4, pp. 762–767, Aug. 2019. DOI: https://doi.org/10.35940/ijrte.B1154.0782S419
E. Afsaneh, A. Sharifdini, H. Ghazzaghi, and M. Z. Ghobadi, "Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: a comprehensive review," Diabetology & Metabolic Syndrome, vol. 14, no. 1, Dec. 2022, Art. no. 196. DOI: https://doi.org/10.1186/s13098-022-00969-9
S. A. Ajagbe and M. O. Adigun, "Deep learning techniques for detection and prediction of pandemic diseases: a systematic literature review," Multimedia Tools and Applications, vol. 83, no. 2, pp. 5893–5927, Jan. 2024. DOI: https://doi.org/10.1007/s11042-023-15805-z
I. D. Mienye and T. G. Swart, "A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications," Information, vol. 15, no. 12, Nov. 2024, Art. no. 755. DOI: https://doi.org/10.3390/info15120755
K. Ghosh, C. Bellinger, R. Corizzo, P. Branco, B. Krawczyk, and N. Japkowicz, "The class imbalance problem in deep learning," Machine Learning, vol. 113, no. 7, pp. 4845–4901, July 2024. DOI: https://doi.org/10.1007/s10994-022-06268-8
I. D. Mienye and N. Jere, "A Survey of Decision Trees: Concepts, Algorithms, and Applications," IEEE Access, vol. 12, pp. 86716–86727, 2024. DOI: https://doi.org/10.1109/ACCESS.2024.3416838
JiahaoLi-gdut, "JiahaoLi-gdut/CombRo." Apr. 14, 2025, [Online]. Available: https://github.com/JiahaoLi-gdut/CombRo.
R. Emekter, Y. Tu, B. Jirasakuldech, and M. Lu, "Evaluating credit risk and loan performance in online Peer-to-Peer (P2P) lending," Applied Economics, vol. 47, no. 1, pp. 54–70, Jan. 2015. DOI: https://doi.org/10.1080/00036846.2014.962222
A. A. Soltan and M. M. Mohammadi, "A hybrid model using decision tree and neural network for credit scoring problem," Management Science Letters, vol. 2, no. 5, pp. 1683–1688, July 2012. DOI: https://doi.org/10.5267/j.msl.2012.04.021
N. Frosst and G. Hinton, "Distilling a Neural Network Into a Soft Decision Tree." arXiv, 2017.
C. X. Pham, H. N. Trinh, and L. Q. Tran, "A Robust Approach to Credit Scoring with Deep Learning and Embedded Methods," Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 29284–29291, Dec. 2025. DOI: https://doi.org/10.48084/etasr.12649
J. Fan, "Predicting of Credit Default by SVM and Decision Tree Model Based on Credit Card Data," BCP Business & Management, vol. 38, pp. 28–33, Mar. 2023. DOI: https://doi.org/10.54691/bcpbm.v38i.3666
M. Óskarsdóttir, C. Bravo, C. Sarraute, J. Vanthienen, and B. Baesens, "The value of big data for credit scoring: Enhancing financial inclusion using mobile phone data and social network analytics," Applied Soft Computing, vol. 74, pp. 26–39, Jan. 2019. DOI: https://doi.org/10.1016/j.asoc.2018.10.004
R. Hlongwane, K. K. K. M. Ramaboa, and W. Mongwe, "Enhancing credit scoring accuracy with a comprehensive evaluation of alternative data," PLOS ONE, vol. 19, no. 5, May 2024, Art. no. e0303566. DOI: https://doi.org/10.1371/journal.pone.0303566
R. Bessi, "Approximation with activation functions and applications," Dec. 2021.
M. Kuhn and K. Johnson, Applied Predictive Modeling. Springer New York, 2013. DOI: https://doi.org/10.1007/978-1-4614-6849-3
M. Zhang, H. Peng, and X. Yan, "Improved algorithm of decision tree based on neural network," Journal of Physics: Conference Series, vol. 1693, no. 1, Dec. 2020, Art. no. 012081. DOI: https://doi.org/10.1088/1742-6596/1693/1/012081
P. Li, Z. Qin, X. Wang, and D. Metzler, "Combining Decision Trees and Neural Networks for Learning-to-Rank in Personal Search," in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, July 2019, pp. 2032–2040. DOI: https://doi.org/10.1145/3292500.3330676
S. O. Hasoon and M. M. Al-Hashimi, "Hybrid Deep Neural network and Long Short term Memory Network for Predicting of Sunspot Time Series," International Journal of Mathematics and Computer Science, vol. 17, no. 3, pp. 955–967, 2022.
Downloads
How to Cite
License
Copyright (c) 2026 F. M. R. Venusiana, Agung Wibowo, Aghus Sofwan
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
