Comparative Machine Learning Models for Predicting SME Business Performance

Authors

  • Azizah Diponegoro University, Indonesia
  • Rahmat Gernowo Diponegoro University, Indonesia
  • Budi Warsito Diponegoro University, Indonesia
  • Jumi Politeknik Negeri Semarang, Indonesia
Pages Icon

DOI:

https://doi.org/10.63158/journalisi.v8i4.1705

Keywords:

Small Medium Enterprises, Business Performance, Machine Learning, Random Forest, Prediction

Abstract

Small and Medium Enterprises (SMEs) play an essential role in supporting economic growth, employment creation, and innovation across developing and emerging economies. To maintain competitiveness, SMEs need to improve their business performance by understanding the factors that influence organizational success. Several factors, including risk-taking, open innovation, cost leadership, proactiveness, aggressiveness, and autonomy, contribute to SME performance improvement. This study aims to develop and compare machine learning models for predicting SME business performance using these influencing factors. A dataset containing 283 SME records obtained from the Mendeley Data Repository was used in this study. Four machine learning approaches were evaluated, including Random Forest (RF), XGBoost, Artificial Neural Network (ANN), and ANN optimized using Particle Swarm Optimization (PSO). The models were assessed using regression performance metrics, including the coefficient of determination (R²), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and computational execution time. The experimental results indicate that RF achieved the best prediction performance with an R² of 0.924, RMSE of 0.120, and MAE of 0.065, demonstrating high predictive accuracy and low error. XGBoost and ANN-PSO also showed competitive performance, while ANN achieved moderate results. Therefore, RF is recommended as an effective model for SME performance prediction. Future studies should employ larger datasets and external validation to improve model generalizability.

Downloads

Download data is not yet available.

References

[1] R. Rajnoha and P. Lesníková, “Strategic performance management system and corporate sustainability concept—Specific parameters in Slovak enterprises,” J. Compet., vol. 6, no. 3, pp. 107–124, Sep. 2016, doi: 10.7441/joc.2016.03.07.

[2] R. Alami and R. Sergio, “Future-proofing strategies: Machine learning models for organizational resilience in emerging markets,” in Navigating the Technological Tide: The Evolution and Challenges of Business Model Innovation, B. Alareeni and A. Hamdan, Eds., Lect. Notes Netw. Syst., vol. 1083. Cham, Switzerland: Springer, 2024, pp. 487–501, doi: 10.1007/978-3-031-67431-0_47.

[3] S. Chakravarty and P. K. Dash, “A PSO based integrated functional link net and interval type-2 fuzzy logic system for predicting stock market indices,” Appl. Soft Comput., vol. 12, no. 2, pp. 931–941, 2012, doi: 10.1016/j.asoc.2011.09.013.

[4] M. Wuest, D. Weimer, C. Irgens, and K.-D. Thoben, “Machine learning in manufacturing: Advantages, challenges, and applications,” Prod. Manuf. Res., vol. 4, no. 1, pp. 23–45, 2016, doi: 10.1080/21693277.2016.1192517.

[5] S. Balaji, M. Patil, and C. McGregor, “A cloud based big data based online health analytics for rural NICUs and PICUs in India: Opportunities and challenges,” in Proc. IEEE 30th Int. Symp. Comput.-Based Med. Syst. (CBMS), Thessaloniki, Greece, 2017, pp. 385–390, doi: 10.1109/CBMS.2017.112.

[6] M. A. Boyacioglu and D. Avci, “An adaptive network-based fuzzy inference system (ANFIS) for the prediction of stock market return: The case of the Istanbul Stock Exchange,” Expert Syst. Appl., vol. 37, no. 12, pp. 7908–7912, 2010, doi: 10.1016/j.eswa.2010.04.045.

[7] A. Carvalhal and B. V. De Melo Mendes, “Evaluating the forecast accuracy of emerging market stock returns,” Emerg. Mark. Finance. Trade, vol. 44, no. 1, pp. 21–40, 2008, doi: 10.2753/REE1540-496X440102.

[8] A. Abraham and B. Nath, “Hybrid intelligent systems for stock market analysis,” in Comput. Sci. ICCS 2001, Berlin, Germany: Springer, 2001, pp. 657–665.

[9] J. G. Covin and D. P. Slevin, “Strategic management of small firms in hostile and benign environments,” Strateg. Manage. J., vol. 10, no. 1, pp. 75–87, 1989, doi: 10.1002/smj.4250100107.

[10] H. Chesbrough, “The logic of open innovation: Managing intellectual property,” Calif. Manage. Rev., vol. 45, no. 3, pp. 33–58, 2003, doi: 10.1177/000812560304500301.

[11] M. E. Porter, Competitive Advantage: Creating and Sustaining Superior Performance. New York, NY, USA: Free Press, 1985.

[12] G. T. Lumpkin and G. G. Dess, “Clarifying the entrepreneurial orientation construct and linking it to performance,” Acad. Manage. Rev., vol. 21, no. 1, pp. 135–172, 1996, doi: 10.2307/258632.

[13] J. B. Santos and L. A. L. Brito, “Toward a subjective measurement model for firm performance,” BAR Braz. Adm. Rev., vol. 9, no. SI, pp. 95–117, 2012, doi: 10.1590/S1807-76922012000500007.

[14] P. M. Thi Pham and B. T. Thi Dao, “A meta-analysis of risk taking and corporate performance,” Cogent Bus. Manage., vol. 9, no. 1, Art. no. 2064263, 2022, doi: 10.1080/23311975.2022.2064263.

[15] E. Moradi, S. M. Jafari, Z. M. Doorbash, and A. Mirzaei, “Impact of organizational inertia on business model innovation, open innovation and corporate performance,” Asia Pac. Manage. Rev., vol. 26, no. 4, pp. 171–179, 2021, doi: 10.1016/j.apmrv.2021.01.003.

[16] F. Moretti and D. Biancardi, “Inbound open innovation and firm performance,” J. Innov. Knowl., vol. 5, no. 1, pp. 1–19, 2020, doi: 10.1016/j.jik.2018.03.001.

[17] B. Bigliardi, G. Ferraro, S. Filippelli, and F. Galati, “The influence of open innovation on firm performance,” Int. J. Eng. Bus. Manag., vol. 12, Art. no. 184797902096954, 2020, doi: 10.1177/1847979020969545.

[18] H. Hilman and N. Kaliappen, “Do cost leadership strategy and process innovation influence the performance of Malaysia hotel industry?” Asian Soc. Sci., vol. 10, no. 10, pp. 134–141, 2014, doi: 10.5539/ass.v10n10p134.

[19] A. H. G. Dutse and M. S. Aliyu, “Cost leadership, market orientation and business performance: An empirical investigation,” J. Qual. Meas. Anal., vol. 2, no. 2, pp. 28–42, 2018.

[20] R. Sancho-Zamora, I. Peña-García, S. Gutiérrez-Broncano, and F. Hernández-Perlines, “Moderating effect of proactivity on firm absorptive capacity and performance: Empirical evidence from Spanish firms,” Mathematics, vol. 9, no. 17, Art. no. 2099, 2021, doi: 10.3390/math9172099.

[21] H. S. Bedi, “A contingency approach to proactiveness-business performance relationship,” Indian J. Mark., vol. 48, no. 12, pp. 34–45, 2018, doi: 10.17010/ijom/2018/v48/i12/139555.

[22] G. Andrevski and W. J. Ferrier, “Does it pay to compete aggressively? Contingent roles of internal and external resources,” J. Manage., vol. 45, no. 2, pp. 620–644, 2019, doi: 10.1177/0149206316673718.

[23] S. Nadkarni, T. Chen, and J. Chen, “The clock is ticking! Executive temporal depth, industry velocity, and competitive aggressiveness,” Strateg. Manage. J., vol. 37, no. 6, pp. 1132–1153, 2016, doi: 10.1002/smj.2376.

[24] T. L. Tufa, A. H. Belete, and A. A. Patel, “The autonomous side of EO and firm performance: The role of professional experience and entrepreneurial engagement,” Afr. J. Econ. Manag. Stud., vol. 12, no. 3, pp. 439–452, 2021, doi: 10.1108/AJEMS-09-2020-0445.

[25] E. Jang and Y. C. Kim, “Autonomy constrained: The dynamic interplay among job autonomy, work engagement, and innovative behavior under performance pressure,” Adm. Sci., vol. 15, no. 3, Art. no. 97, 2025, doi: 10.3390/admsci15030097.

[26] J. Bisbe and R. Malagueño, “Using strategic performance measurement systems for strategy formulation: Does it work in dynamic environments?” Manag. Account. Res., vol. 23, no. 4, pp. 296–311, 2012, doi: 10.1016/j.mar.2012.05.002.

[27] R. Rajnoha, R. Štefko, M. Merková, and J. Dobrovič, “Business intelligence as a key information and knowledge tool for strategic business performance management,” Econ. Manag., vol. 19, no. 1, pp. 183–203, 2016.

[28] M. Kumar, “Dataset of relationship of entrepreneurship orientation, open innovation and cost leadership towards firm performance among small medium enterprise (SME’s) in Malaysia,” Mendeley Data, 2022, doi: 10.17632/FNJ7TSWXVG.2.

[29] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.

[30] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York, NY, USA: Springer, 2009, doi: 10.1007/978-0-387-84858-7.

[31] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.

[32] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2016, pp. 785–794, doi: 10.1145/2939672.2939785.

[33] S. S. Haykin, Neural Networks and Learning Machines, 3rd ed. New York, NY, USA: Prentice Hall, 2009.

[34] J. Kennedy and R. Eberhart, “Particle swarm optimization,” in Proc. IEEE Int. Conf. Neural Networks (ICNN), Perth, Australia, 1995, pp. 1942–1948, doi: 10.1109/ICNN.1995.488968.

[35] R. Storn and K. Price, “Differential evolution—A simple and efficient heuristic for global optimization over continuous spaces,” J. Global Optim., vol. 11, pp. 341–359, 1997, doi: 10.1023/A:1008202821328.

[36] K. P. Murphy, Machine Learning: A Probabilistic Perspective. Cambridge, MA, USA: MIT Press, 2012.

[37] C. M. Bishop, Pattern Recognition and Machine Learning. New York, NY, USA: Springer, 2006.

[38] J. Friedman, “Greedy function approximation: A gradient boosting machine,” Ann. Stat., vol. 29, no. 5, pp. 1189–1232, 2001, doi: 10.1214/aos/1013203451.

Downloads

Published

2026-08-29

Issue

Vol. 8 No. 4 (2026): August

Section

Articles

License

Copyright (c) 2026 Journal of Information Systems and Informatics

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors Declaration

  1. The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
  2. The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
  3. The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
  4. The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
  5. The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
  6. The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
  7. If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
  8. The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights

Most read articles by the same author(s)