The modeling the fixed asset investing with a machine learning approach by emphasizing the role of regulatory criteria
Subject Areas : Financial EngineeringFarzaneh Shams Doost 1 , Omid Mahmoudi Khoshro 2 , Ataollah Mohammadi Malgharni 3 , Amir Sheikhahmadi 4
1 - Department of Finance, Sanandaj Branch, Islamic Azad University, Sanandaj, Iran.
2 - Department of Accounting, Sanandaj Branch, Islamic Azad University, Sanandaj, Iran.
3 - Department of Accounting, Sanandaj Branch, Islamic Azad University, Sanandaj, Iran.
4 - Department of Computer Engineering, Sanandaj Branch, Islamic Azad University, Sanandaj, Iran.
Keywords: Artificial Intelligence, Fixed asset invetment, Linear and non-linear models, Regulatory criteria,
Abstract :
Objective: Corporate governance mechanisms and ownership structure can directly impact investors' motivation to encourage management to use available resources efficiently within organizations. The aim of this study is to model fixed asset investment by examining the role of regulatory criteria and artificial intelligence approaches for companies listed on the Tehran Stock Exchange.
Research Methodology: In this research, samples were selected using the Relief-F regression variable selection method. Subsequently, the research data were divided into training, validation, and test sets using ten-fold cross-validation. Then, two parametric and non-parametric algorithms, namely, non-parallel support vector machine (NPSVM) and nonlinear kernel partial least squares (NKPLS), were applied to test the data. The statistical population of this study includes all companies listed on the Tehran Stock Exchange from 2011 to 2020, utilizing financial data from 101 companies.
Findings: The research findings indicate that variables such as board size, board independence, board financial expertise, audit committee size, audit committee independence, institutional ownership above 5%, CEO tenure, the presence of an internal auditor, the proportion of specialized members on the audit committee, and CEO duality have the most significant impact on predicting fixed asset investment in companies. Additionally, among artificial intelligence algorithms, linear algorithms demonstrated greater effectiveness than non-linear algorithms in predicting fixed asset investment.
Originality / Scientific Contribution: Given that unique market characteristics and limited investor awareness of the market, along with behavioral biases, have resulted in inefficiencies and reduced dynamism in the capital market — the core of the country's economy — investors often make erroneous decisions due to inadequate knowledge of these traps. This leads to their withdrawal from the capital market, producing negative consequences for the country. Therefore, by introducing investment opportunities, this study aims to encourage market participants to invest, mitigate financial crises, and prevent significant losses in the stock market.
Ahmed, B., Akbar, M., Sabahat, T., Ali, S., Hussain, A., Akbar, A., & Hongming, X. (2020). Does firm life cycle impact corporate investment efficiency? Sustainability, 13(1), 197-209.
Alipour, H., Tehrani, R., Alirezaei, A., & Abbaspour Esfndan, G. (2021). Providing a Model of the Effect of Uncertainty about the Inflation Rate and More Trust of Managers on the Increase in Investment (Case Study: Fellowship Affiliated Companies in Tehran Stock Exchange). Journal of Investment Knowledge, 10(38), 223-242. [In Persian]
Alpaydın, E. (2021). Machine learning. MIT Press.
Amiri, M., Raeesi Vanani, I., Razavi Hajiagha, S. H., & Jafari, T. (2021). Development of fuzzy Artificial Intelligence and Multi-Objective planning Model to Optimize the Portfolio of Investment Companies. Business Intelligence Management Studies, 9(36), 209-243. [In Persian]
Azad, A. & Pourzamani, Z. (2019). Providing a model for measuring the efficiency of companies with the role of regulatory criteria (cultural approach and Lasso). Financial Economics, 14(53), 65-96. [In Persian]
Azar, A., & Momeni, M. (2009). Statistics and its application in management volume two: statistical analysis. Samt. [In Persian]
Bahreini, A., Fard, M. A., & Khoshnood, M. (2023). Developing an LSTM neural network model for predicting blocktrade transaction valuation. Journal of Advances in Finance and Investment, 4(4), 145-176. [In Persian]
Dash, M., & Liu, H. (1997). Feature selection for classification. Intelligent data analysis, 1(1-4), 131-156.
De Vries, S., & Ter Braak, C. J. (1995). Prediction error in partial least squares regression: a critique on the deviation used in The Unscrambler. Chemometrics and intelligent laboratory systems, 30(2), 239-245.
Feridoni, M., Rezaei, N., Pakmaram, A., & Abdi, R. (2022). Improve Investment Efficiency Based on Cognitive Behavioral Biases CEO by Gray Vikor Analysis. Journal of Investment Knowledge, 11(42), 579-609. [In Persian]
Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. O'Reilly.
He, Y., Chen, C., & Hu, Y. (2019). Managerial overconfidence, internal financing, and investment efficiency: Evidence from China. Research in International Business and Finance, 47, 501-510.
Hubbard, R. G. (1998). Capital-market imperfections and investment. Journal of Economic Literature, 36(1), 193-225.
Huerta, R., Corbacho, F., & Elkan, C. (2013). Nonlinear support vector machines can systematically identify stocks with high and low future returns. Algorithmic Finance, 2(1), 45-58.
Jahanshad, A., & Khalili, S. A. (2013). The relationship between stock returns with fixed assets growth a wavelet analysis. Financial Engineering and Portfolio Management, 4(15), 1-15. [In Persian]
Khaleghi Zadeh Dehkordi, M., Sarraf, F., & Najafi Moghadam, A. (2022). Application of artificial intelligence algorithm in predicting investment efficiency Emphasizing the role of risk management criteria. Journal of Investment Knowledge, 11(42), 413-434. [In Persian]
Khoshkar, F., Safari Khah, M., & Ranjbari Share Jini, S. (2020). The effect of ownership structure on the relationship between financial information quality and investment efficiency. Journal of Accounting and Management Vision, 3(33), 162-175. [In Persian]
Kurani, A., Doshi, P., Vakharia, A., & Shah, M. (2023). A comprehensive comparative study of artificial neural network (ANN) and support vector machines (SVM) on stock forecasting. Annals of Data Science, 10(1), 183-208.
Lara, J. M. G., Osma, B. G., & Penalva, F. (2016). Accounting conservatism and firm investment efficiency. Journal of accounting and economics, 61(1), 221-238.
Lv, P., & Xiong, H. (2022). Can FinTech improve corporate investment efficiency? Evidence from China. Research in International Business and Finance, 60, 101571.
Mansourfar, G., Joudi, S., & Poursoleiman, E. (2020). Associate Prof., Department of Finance, Faculty of Management and Economics, Urmia University, West Azarbaijan, Urmia, Iran. Financial Research Journal, 22(2), 227-248. [In Persian]
Mello-Román, J. D., Hernández, A., & Mello-Román, J. C. (2021). Improved Predictive Ability of KPLS Regression with Memetic Algorithms. Mathematics, 9(5), 506-518.
Menshawy, I. M., Basiruddin, R., Mohd‐Zamil, N. A., & Hussainey, K. (2023). Strive towards investment efficiency among Egyptian companies: Do board characteristics and information asymmetry matter? International Journal of Finance & Economics, 28(3), 2382-2403.
Mohammadi, D., Mohammadi, E., Shokri, N., & Heidari, N. (2023). The use of support vector machine and Naive Bayes algorithms and its combination with risk measure and fuzzy theory in the selection of stock portfolio. Journal of Advances in Finance and Investment, 4(4), 177-206. [In Persian]
Naim, P., & Condamin, L. (2019). Operational risk modeling in financial services: The exposure, occurrence, impact method. John Wiley & Sons.
Robnik-Šikonja, M., & Kononenko, I. (1997). An adaptation of Relief for attribute estimation in regression. In Machine learning: Proceedings of the fourteenth international conference (ICML’97), 5, 296-304.
Rosipal, R., & Trejo, L. J. (2001). Kernel partial least squares regression in reproducing kernel hilbert space. Journal of machine learning research, 2(2001), 97-123.
Samet, M., & Jarboui, A. (2017). How does corporate social responsibility contribute to investment efficiency? Journal of multinational financial management, 40, 33-46.
Sayyadi, M., Dastgir, M., & Aliahmdi, S. (2019). Study on Enterprise Risk Management (ERM) effect on managerial ability in order to increasing investment efficiency. Financial Management Strategy, 7(1), 1-38. [In Persian]
Silverstein, B. (2020). Managerial opportunism and corporate investment efficiency. SSRN.
Taghizadeh Khanqah, V., Badavar Nahandi, Y., Mottagi, A., & Taghizadeh, H. (2021). Validation of Investment Efficiency Models Based on Agency Theory, Information Asymmetry, Managerial Entrenchment and Firm value maximization. Journal of Investment Knowledge, 10(38), 287-318. [In Persian]
Tahmooresi, Z., Talebnia, Q., Baradaran Hassanzadeh, R., Mousavi, N. A., & Vakilifard, H. (2024). Modeling The Effective variables on investment efficiency: evidence from Tehran Stock Exchange. Journal of Investment Knowledge, 13(51), 361-384. [In Persian]
Wang, J., Wang, H., & Wang, D. (2021). Equity concentration and investment efficiency of energy companies in China: Evidence based on the shock of deregulation of QFIIs. Energy Economics, 93, 105032.
Yang, Z. M., Hua, X. Y., Shao, Y. H., & Ye, Y. F. (2016). A novel parametric-insensitive nonparallel support vector machine for regression. Neurocomputing, 171, 649-663.
Zhang, X., Hu, Y., Xie, K., Wang, S., Ngai, E. W. T., & Liu, M. (2014). A causal feature selection algorithm for stock prediction modeling. Neurocomputing, 142, 48-59.
