Klasifikasi Perilaku Keuangan UMKM Medan dengan Machine Learning dan SHAP
Abstract
Good financial behavior is an important factor in sustaining micro, small, and medium enterprises (MSMEs), particularly in financial recording, debt management, and investment planning. Previous research using Structural Equation Modeling Partial Least Squares (SEM-PLS) identified financial attitude as the dominant factor influencing MSMEs’ financial behavior in Medan City. Based on these findings, this study develops a complementary machine learning-based approach to classify MSMEs’ financial behavior at the individual level and evaluate its consistency with SEM results through SHAP-based Explainable Artificial Intelligence (XAI). The dataset consists of 100 MSME respondents with seven main features, including three financial constructs and four demographic variables. Three ensemble algorithms, namely CatBoost, XGBoost, and Random Forest, were evaluated using hold-out and Stratified 5-Fold Cross-Validation. The results show that CatBoost achieved the best performance with 80.00% accuracy and 82.46% F1-score. SHAP analysis confirmed the dominance of attitude score and revealed the significant predictive contribution of demographic variables. Integrating machine learning and SHAP is an effective complementary approach to extend the understanding of MSMEs’ financial behavior comprehensively.
Downloads
References
S. Eriyanti, R. M. Dai, and D. Fordian, “The Influence of Financial Management Behavior On MSMES Sustainability of Tourist Attraction Services,” Islamic Banking : Jurnal Pemikiran dan Pengembangan Perbankan Syariah, vol. 11, no. 1, pp. 119–132, Aug. 2025, doi: 10.36908/isbank.v11i1.1530.
N. Perangin-Angin, L. T. B. Ginting, and S. O. Ginting, “Building the Foundation of Financial Behavior among MSMEs in Medan An Analysis of the Roles of Financial Literacy, Financial Attitude, and Financial Inclusion,” Jurnal Manajemen Motivasi, vol. 21, pp. 1344–1355, 2025.
P. E. Nopiyani and P. R. Indiani, “Pengaruh Sikap Keuangan, Perilaku Keuangan dan Literasi Keuangan terhadap Kinerja Keuangan UMKM pada Pemdes Ambengan,” Jurnal Akuntansi Kompetif, vol. 6, no. 3, pp. 411–418, Sep. 2023.
G. M. Putri, D. S. P. Koesoemasari, and I. Rokhayati, “Literasi, Sikap, Inklusi, Perencanaan Keuangan terhadap Perilaku Manajemen Keuangan UMKM Batik di Kabupaten Purbalingga,” Goodwood Akuntansi dan Auditing Reviu, vol. 3, no. 1, pp. 1–13, Nov. 2024, doi: 10.35912/gaar.v3i1.3344.
Z. Zhang, C. Wu, S. Qu, and X. Chen, “An explainable artificial intelligence approach for financial distress prediction,” Inf. Process. Manag., vol. 59, no. 4, p. 102988, 2022, doi: https://doi.org/10.1016/j.ipm.2022.102988.
K. Mandal, A. Ghosh, S. Gupta, S. Chowdhury, B. B. Dash, and S. S. Patra, “Redefining Crash Prediction with Interpretable Machine Intelligence,” in 2025 5th International Conference on Intelligent Technologies (CONIT), 2025, pp. 1–7. doi: 10.1109/CONIT65521.2025.11167794.
S. J. MacEachern and N. D. Forkert, “Machine learning for precision medicine,” Genome, vol. 64, no. 4, pp. 416–425, 2021, doi: 10.1139/gen-2020-0131.
C. Bentéjac, A. Csörgő, and G. Martínez-Muñoz, “A comparative analysis of gradient boosting algorithms,” Artif. Intell. Rev., vol. 54, no. 3, pp. 1937–1967, 2021, doi: 10.1007/s10462-020-09896-5.
T. R. Noviandy et al., “Ensemble Machine Learning Approach for Quantitative Structure Activity Relationship Based Drug Discovery: A Review,” Infolitika Journal of Data Science, vol. 1, no. 1, pp. 32–41, Sep. 2023, doi: 10.60084/ijds.v1i1.91.
R. Rivaldo, R. Taufik, I. S. Ilman, and O. D. E. Wulansari, “A Comparative Study of XGBoost, LightGBM, and CatBoost Models for Customer Churn Prediction in the Banking Industry,” Jurnal Pepadun, vol. 6, no. 2, pp. 178–187, 2025, doi: 10.23960/pepadun.v6i2.277.
E. R. Putri and D. B. Arianto, “Perbandingan Performa Algoritma Metode Bagging dan Boosting pada Prediksi Konsentrasi PM10 di Jakarta Utara,” Jurnal Nasional Teknologi dan Sistem Informasi, vol. 10, no. 1, pp. 72–81, May 2024, doi: 10.25077/TEKNOSI.v10i1.2024.72-81.
E. L. Crossesa and A. Sofro, “Application of XGBoost and CatBoost Algorithms for Elderly Hypertension Classification on IFLS 5 Data,” Leibniz: Jurnal Matematika, vol. 6, no. 1, pp. 1–14, Jan. 2026, doi: 10.59632/leibniz.v6i01.734.
T. Buyuktanir and K. Yildiz, “Improving Interpretability and Explainability in Financial Models through Ensemble Tree Simplification,” in 2025 10th International Conference on Computer Science and Engineering (UBMK), 2025, pp. 818–823. doi: 10.1109/UBMK67458.2025.11206812.
J. Černevičienė and A. Kabašinskas, “Explainable artificial intelligence (XAI) in finance: a systematic literature review,” Artif. Intell. Rev., vol. 57, no. 8, p. 216, 2024, doi: 10.1007/s10462-024-10854-8.
S. Darekar, P. Nilekar, S. Lilhare, A. Chaudhari, R. Narayan, and V. Borate, “A Machine Learning Approach for Bug or Error Prediction using Cat-Boost Algorithm,” in 2025 6th International Conference for Emerging Technology (INCET), 2025, pp. 1–5. doi: 10.1109/INCET64471.2025.11140996.
Z. Rais, M. F. S, S. Saida, and A. Triutomo, “Implementation of Machine Learning Algorithm with Extreme Gradient Boosting (XGBoost) Method in Hypertension Level Classification,” Journal of Applied Science, Engineering, Technology, and Education, vol. 7, no. 1, pp. 126–136, Apr. 2025, doi: 10.35877/454RI.asci4191.
W. Zhang and H. Zhang, “A Feature Extraction Method for Small Sample Data Based on Optimal Ensemble Random Forest,” Journal of Northwestern Polytechnical University, vol. 40, no. 6, pp. 1261–1268, Dec. 2022, doi: 10.1051/jnwpu/20224061261.
J. Bergstra and Y. Bengio, “Random search for hyper-parameter optimization,” J. Mach. Learn. Res., vol. 13, no. null, pp. 281–305, Feb. 2012.
A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, 2nd ed. Sebastopol, CA: O’Reilly Media, 2019.
J. Qiu, “An Analysis of Model Evaluation with Cross-Validation: Techniques, Applications, and Recent Advances,” in Proceedings of ICFTBA 2024 Workshop: Finance in the Age of Environmental Risks and Sustainability, 2024, pp. 69–72. doi: 10.54254/2754-1169/99/2024OX0213.
