Predicting Corporate Financial Performance Using an Adaptive Neuro-Fuzzy Inference System Algorithm

Saeid  Hooshmand; Morteza Bavaghar; Hamid Rostamijaaz; Mohammad Hossein Ranjbar; Hossein Kamrani

Authors

Saeid Hooshmand Department of Accounting, BA.C., Islamic Azad University, Bandar Abbas, Iran Author https://orcid.org/0009-0002-0149-3727
Morteza Bavaghar Department of Accounting, BA.C., Islamic Azad University, Bandar Abbas, Iran https://orcid.org/0000-0003-1559-6751
Hamid Rostamijaaz Department of Accounting, BA.C., Islamic Azad University, Bandar Abbas, Iran Author https://orcid.org/0000-0001-9735-1787
Mohammad Hossein Ranjbar Department of Accounting and Finance, BA.C., Islamic Azad University, Bandar Abbas, Iran Author https://orcid.org/0000-0003-3454-0200
Hossein Kamrani Department of Accounting, BA.C., Islamic Azad University, Bandar Abbas, Iran Author https://orcid.org/0000-0002-2257-6778

Keywords:

financial performance prediction, stock return, artificial intelligence, Adaptive Neuro-Fuzzy Inference System, Tehran Stock Exchange

Abstract

The present study aimed to predict financial performance using an Adaptive Neuro-Fuzzy Inference System (ANFIS) algorithm. The study was conducted using an exploratory mixed-methods approach (qualitative–quantitative). In the qualitative phase, the fuzzy Delphi technique was employed with the participation of 10 academic and executive experts in the capital market to identify, prioritize, and screen variables affecting financial performance from a large pool of potential indicators. In the quantitative phase, data from 160 companies listed on the Tehran Stock Exchange over the 2016–2024 period (1,440 firm-year observations) were extracted and analyzed using ANFIS to predict “stock price return.” The validity of the final model was assessed through two approaches: quantitatively, by evaluating its generalization accuracy using 421 test observations, and qualitatively, through expert judgment using a validation questionnaire. The fuzzy Delphi results led to the identification of 19 key variables in four categories: financial (7 indicators), economic (6 indicators), social (3 indicators), and macro-environmental (3 indicators). Furthermore, evaluation of the ANFIS model indicated that it explained 75.8% of the variance in stock price return. A comparison of actual and predicted values for 15 selected companies also confirmed that the model successfully tracked the overall trend in returns, although prediction errors increased slightly at extreme values. Accordingly, ANFIS demonstrated satisfactory and practically useful accuracy in predicting financial performance.

References

[1] E. Alizadeh, H. Vakilifard, and M. Hamidian, "Examining Micro- and Macro-Level Economic Policy Factors Affecting Firms' Financial Performance: A Fuzzy DEMATEL Approach," (in English), Scientific Research Quarterly of Investment Knowledge, pp. 11-41, 2022.

[2] C. A. Asamoah, K. N. Takyi, A. Klapalová, I. Agirre-Aramburu, and J. Matošková, "Dynamic managerial capabilities, digital innovation and perceived financial performance in the banking sector," Scientific African, vol. 31, 2026, doi: 10.1016/j.sciaf.2025.e03157.

[3] J. Yin and J. Xu, "Intellectual capital, digital transformation and firms’ financial performance: Evidence from ecological protection and environmental governance industry in China," PLoS ONE, vol. 20, no. 1, p. e0316724, 2025, doi: 10.1371/journal.pone.0316724.

[4] H. Khalouzadeh and N. Amiri, "Determining the Optimal Stock Portfolio in the Iranian Stock Market Based on Value-at-Risk Theory," (in English), Economic Research, no. 73, p. 231, 2020.

[5] H. Ghalibaf Asl, R. Tehrani, M. Rostami, and A. Siri, "Designing a Model for Predicting Long-Term Stock Returns Using Nonparametric Simulation of Bond Returns," (in English), Financial Management Perspective, vol. 8, no. 1, pp. 133-155, 2023.

[6] S. Akbari Emami, M. Jamipour, and S. Fathi, "Designing a Framework for the Application of Artificial Intelligence in Human Resource Management," (in English), Biannual Scientific Journal of Sustainable Human Resource Management, vol. 5, no. 9, pp. 263-284, 2023.

[7] B. Trenerry et al., "Preparing Workplaces for Digital Transformation: An Integrative Review and Framework of Multi-Level Factors," Frontiers in Psychology, vol. 12, p. 620766, 2021.

[8] Y. Wang and F. Liu, "Impact of artificial intelligence innovation on food company performance," International Review of Financial Analysis, vol. 103, no. 5, pp. 1115-1145, 2025, doi: 10.1016/j.irfa.2025.104219.

[9] S. H. Hosseini and S. Abbasi, "Comparing the Efficiency of Artificial Intelligence Models Based on Deep Neural Networks and Logistic Regression in Predicting Corporate Profitability," (in English), Accounting and Auditing Review, vol. 30, no. 2, pp. 221-245, 2024.

[10] F. Barboza, H. Kimura, and E. I. Altman, "Machine learning models and bankruptcy prediction," Expert Systems with Applications, vol. 83, pp. 405-417, 2017, doi: 10.1016/j.eswa.2017.04.006.

[11] F. M. Richardson and L. F. Davidson, "An exploration into bankruptcy Discriminant model sensitivity," Journal of Business Finance & Accounting, vol. 10, no. 2, pp. 195-207, 2020.

[12] M. Ansari and R. Rahimi, "Predicting Financial Performance and the Probability of Distress in Companies Listed on the Tehran Stock Exchange Using Gradient Boosting Algorithms," (in English), Financial Accounting and Auditing Research, vol. 15, no. 58, pp. 85-112, 2023.

[13] N. Arora and J. R. Saini, "Time series model for bankruptcy prediction via adaptive neuro-fuzzy inference system," International Journal of Hybrid Information Technology, vol. 6, no. 2, pp. 51-63, 2013.

[14] W. Choensawat and P. Polsiri, "Financial institution failure prediction using adaptive neuro-fuzzy inference systems: Evidence from the East Asian economic crisis," Journal of Advanced Computational Intelligence and Intelligent Informatics, vol. 17, no. 1, pp. 83-91, 2013, doi: 10.20965/jaciii.2013.p0083.

[15] T. Buisui, "Adaptive Kalman filter optimization," Journal of International Money and Finance, vol. 42, no. 3, pp. 311-331, 2022.

[16] D. Liong, R. Honka, and J. H. Chintagunta, "Estimates of the return on the Taiwan Stock Exchange using different neural networks," Applied Intelligence, vol. 22, no. 1, pp. 47-60, 2023.

[17] A. Raoofi and T. Mohammadi, "Predicting Tehran Stock Market Returns Using a Combination of Wavelet Decomposition and Adaptive Neuro-Fuzzy Network," (in English), Iranian Economic Research, vol. 23, no. 76, pp. 107-136, 2023.

[18] R. Triankel, "Application of Neural Fuzzy System and Neural Network for predicting annual returns of construction companies," IEEE Transactions on Knowledge and Data Engineering, no. 26, pp. 866-883, 2023.

[19] Z. Wu and Y. Dai, "Signal of Financial or Performance Transparency? The Impact and Mechanisms of Nonprofit Transparency on Donation Willingness," Public Performance & Management Review, vol. 48, no. 3, pp. 675-704, 2025, doi: 10.1080/15309576.2025.2465750.

[20] R. Jain et al., "Explaining sentiment analysis results on social media texts through visualization," Multimedia Tools and Applications, vol. 82, no. 15, pp. 22613-22629, 2023.

[21] D. GorsenT, L. Kauf, and D. J. Hand, Application of artificial neural network model in predicting the time of construction projects. UK: John Wiley and Sons, 2024.