Predicting cash holdings using supervised machine learning algorithms in companies listed on the Tehran Stock Exchange (TSE)

Subject Areas : Financial engineering

Saeid Fallahpour ¹ , Reza Raei ² , Negar Tavakoli ³

1 - Associate Professor, Department of Finance, Faculty of Management, University of Tehran, Tehran, Iran
2 - Professor, Department of Finance, Faculty of Management, University of Tehran, Tehran, Iran
3 - MSc. Student, Department of Finance and Insurance, Faculty of Management, University of Tehran, Tehran, Iran

Received: 2023-07-12 Accepted : 2024-01-11 Published : 2024-09-22

Keywords: Machine Learning, Cash holdings, SVR, XGBoost, World Uncertainty Index,

Abstract :

According to the 22 selected features (which are checked during the research) with machine learning methods, this study predicts the cash holding of companies admitted to the Tehran Stock Exchange. 201 companies were investigated from 1396 to 1400. Multiple linear regression, K-nearest neighbor, support vector regression, decision tree, random forest, extreme gradient boosting algorithm and multilayer neural networks are used for prediction. The results show that the multiple linear regression methods provide the k-nearest neighbor of the root mean square error (RMSE) and the mean absolute error (MAE) of the high error. Meanwhile, more complex algorithms, especially support vector regression, achieve higher accuracy; The findings indicated that by reducing to 15 variables, machine learning methods, especially K-nearest neighbor, provided better results. Based on the paired sample t-test, support vector regression has a better performance than other supervised machine learning algorithms except decision tree. Also, the most important variables were company size and capital expenditures (CapEx). The World Uncertainty Index and inflation were also relatively important variables; Therefore, by using the support vector regression algorithm, we may predict the amount of cash to a significant extent.

References:

_|1) اصولیان، محمد؛ تجویدی، الناز و پازوکی، یاسمن (1400). وجه نقد مازاد، ارزش شرکت و ریسک نقدشوندگی سهام در شرکت‌های دارای فرصت رشد یا محدودیت مالی. بررسی‌های حسابداری و حسابرسی،28(2): 248-273.
2) انورخطیبی، سعید؛ سیفی گواهر، لیلا و انصاری، فریبا (1400). توانایی سود و جریان نقد عملیاتی در توضیح ارزش ذاتی تحقق یافته شرکت. چشم‌انداز حسابداری و مدیریت، 4(45): 97-112.
3) تمری نیا، آیت اله؛ نظری، رضا و مرادزاده فرد، مهدی (1401). بررسی اعتبار جریان‌های نقد آزاد و کاربرد عملی آن در پیش‌بینی بحران‌های مالی بر پایه استانداردهای بین‌المللی حسابداری (IFRS): شواهدی از بازار سرمایه ایران. دانش حسابداری و حسابرسی مدیریت، 11(41): 259-270.
4) سلیمانی امیری، غلامرضا؛ جمشیدی، طیبه و عنبری، حمزه (1400). بررسی تأثیر محافظه‌کاری بر رابطه بین جریان نقد عملیاتی و ارزش وجه نقد. فصلنامه علمی کارافن، 2(18): 73-88.
5) صیدخانی، رضا؛ محمدی ملقرنی، عطا و امینی، پیمان (1400). بررسی توانمندی جریان‌های نقدی عملیاتی در ارزیابی عملکرد شرکت‌ها با تأکید بر کیفیت افشا در دوره‌های بحران مالی. پژوهش‌های حسابداری مالی و حسابرسی، 49(13): 147-176.
6) نصیرزاده، فرزانه و رستمی، امین (1391). بررسی رابطه‌ی بین شاخص‌های نقدینگی نوین و مبتنی بر صورت جریان وجه نقد با سودآوری شرکت‌ها (معیارهای مالی و مبتنی بر بازار). اقتصاد پولی، مالی، 3(19): 28-52.
7) Antunes, J. A. P. (2021). “To supervise or to self-supervise: A machine learning based comparison on credit supervision.” Financial Innovation, 7(1): 1-21.
8) Basak, S., Kar, S., Saha, S., Khaidem, L., & Dey, S. R. (2019). “Predicting the direction of stock market prices using tree-based classifiers.” The North American Journal of Economics and Finance, 47: 552-567.
9) Bates, T. W., Kahle, K. M., & Stulz, R. M. (2009). “Why do US firms hold so much more cash than they used to?.” The journal of finance, 64(5): 1985-2021.
10) Breiman, L. (1996). “Bagging predictors.” Machine learning, 24: 123-140.
11) Chen, T., & Guestrin, C. (2016). “Xgboost: A scalable tree boosting system.” In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785-794.
12) Ertel, W. (2018). “Introduction to artificial intelligence.” Springer.
13) Foley, C. F., Hartzell, J. C., Titman, S., & Twite, G. (2007). “Why do firms hold so much cash? A tax-based explanation.” Journal of financial economics, 86(3): 579-607.
14) Friedman, J.H. )2002(. “Stochastic gradient boosting.” Computational statistics & data analysis, 38(4): 367-378.
15) Gholamzadeh, M., Faghani, M., & Pifeh, A. (2021). “Implementing machine learning methods in the prediction of the financial constraints of the companies listed on Tehran’s stock exchange.” International Journal of Finance & Managerial Accounting, 6(20): 131-144.
16) Jensen, M. C. (1986). “Agency costs of free cash flow, corporate finance, and takeovers.” The American economic review, 76(2): 323-329.
17) Keynes, J. M. (1936). The general theory of unemployment. Interest and Money. Harcourt Brace, London.
18) Kim, C. S., Mauer, D. C., & Sherman, A. E. (1998). “The determinants of corporate liquidity: Theory and evidence.” Journal of financial and quantitative analysis, 33(3): 335-359.
19) Kou, G., Peng, Y., & Wang, G. (2014). “Evaluation of clustering algorithms for financial risk analysis using MCDM methods.” Information sciences, 275: 1-12.
20) Jensen, M. C., & Meckling, W. H. (2019). “Theory of the firm: Managerial behavior, agency costs and ownership structure.” In Corporate governance, 77-132.
21) Miller, M. H. and D. Orr (1966). “A model of the demand for money by firms.” The Quarterly journal of economics, 80(3): 413-435.
22) Mousa, G. A., Elamir, E. A., & Hussainey, K. (2022). “Using machine learning methods to predict financial performance: Does disclosure tone matter?.” International Journal of Disclosure and Governance, 1-20.
23) Opler, T., Pinkowitz, L., Stulz, R., & Williamson, R. (1999). “The determinants and implications of corporate cash holdings.” Journal of financial economics, 52(1): 3-46.
24) Polyzos, S., Samitas, A., & Kampouris, I. (2021). “Economic stimulus through bank regulation: Government responses to the COVID-19 crisis.” Journal of International Financial Markets, Institutions and Money, 75: 101444.
25) Popescu, M. E. and V. Dragotă (2018). “What do post-communist countries have in common when predicting financial distress?” Prague Economic Papers, 27(6): 637-653.
26) Rafi, M., Wahab, M. T., Khan, M. B., & Raza, H. (2020, January). “ATM cash prediction using time series approach.” In 2020 3rd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), 1-6
27) Rokach, L., & Maimon, O. (2005). “Top-down induction of decision trees classifiers-a survey.” IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 35(4): 476-487.
28) Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). “Learning representations by back-propagating errors.” nature, 323(6088): 533-536.
29) Sebastião, H., & Godinho, P. (2021). “Forecasting and trading cryptocurrencies with machine learning under changing market conditions.” Financial Innovation, 7(1): 1-30.
30) Vapnik, V. (1999). “The nature of statistical learning theory.” Springer science & business media.
31) Won, C., Kim, J., & Bae, J. K. (2012). “Using genetic algorithm based knowledge refinement model for dividend policy forecasting.” Expert Systems with Applications, 39(18): 13472-13479.
32) Wu, H. C., Chen, J. H., & Wang, P. W. (2021). “Cash holdings prediction using decision tree algorithms and comparison with logistic regression model..” Cybernetics and Systems, 52(8): 689-704.
33) Xiao, F., & Ke, J. (2021). “Pricing, management and decision-making of financial markets with artificial intelligence: introduction to the issue.” Financial Innovation, 7: 1-3.
34) Zhang, Z. (2016). “Introduction to machine learning: k-nearest neighbors.” Annals of translational medicine, 4(11).
|_