The Evaluation of the Capability of the Regression & Neural Network Models in Predicting Future Cash Flows

Subject Areas : Financial Accounting

Bahman Talebi ¹ , Rasol Abdi ² , Zohreh Hajiha ³ , Nader Rezaei ⁴

1 - Department of Accounting, Bonab Branch, Islamic Azad university, Bonab, Iran
2 - Department of Accounting, Bonab Branch, Islamic Azad university, Bonab, Iran
3 - Department of Accounting,Tehran East Branch, Islamic Azad University, Tehran, Iran
4 - Department of Accounting, Bonab Branch, Islamic Azad university, Bonab, Iran

Received: 2019-08-18 Accepted : 2020-06-22 Published : 2022-04-01

Keywords: Accruals, Future Cash Flows, Neural Network Model,

Abstract :

Cash flow and profit are two important indicators for measuring the performance of a business unit. The future prediction was always a necessity in everyday life, and one of the subjects in which “The Prediction” has a great importance is economical and financial problems. The purpose of the present study is to predict future cash flows using regression and neural network models. Sub – separated variables of the accruals and operational cash flows were used to investigate this prediction. For this purpose, data of 137 accepted stock exchange companies in Tehran during 2009 to 2017 has been studied. In this study, Eviews9 software for regression model and Matlab13 software for Multi-Layer Artificial Neural Networks (MANN) with Error back propagation algorithm were used to test the hypotheses.The findings of the research show that both regression and neural network models within proposed variables in the present study have the capability of predicting future cash flows. Also, results of neural network models' processes show that a structure with 16 hidden neurons is the best model to predict future cash flows and this proposal neural network model compared with regression model in predicting future cash flows has a better and accurate function. Furthermore, in this study, it was noticed that accruals of assets compared with debt accrual and variables of operating cash flows with accrual components were more predictive for future cash flows.

References:

 References

[1] Aflatoni, A., Studying relationship between quality of accruals and profit stability regarding to the information reflection speed on share price, journal of Knowledge of accounting, 2013, 6(22), P.107-130, (in Persian).

 

[2] Al-Attar, A, M., Maali, B, M., The Effect of Earnings Quality On the Predictbaility of Accruals and Cash Flow Models in Forcasting Future Cash Flows, The Journal of Developing Areas, Tennessee State University College of Business, 2017, 51(2(, P. 45-58, ideas.repec.org/a/jda/journl/vol.51year2017issue2pp45-58.html.

 

[3] Arnedo, L., Lizarraga, F., and Sanchez, S., The role of accounting accruals for the prediction of future cash flows: evidence from Spain, journal of the spanish economic, springer, 2012, 3(4), P.499-520, Doi.org/10.1007/s13209-011-0070-7.

 

[4] Asadi, G, H., Nagdi, S., Planning and explanation of economic growth forecasting model with accounting approach, Journal of accounting, faculty of economic and management, 2018, 9, P.39-63 (in Persian).

 

[5] Audit organization, technical committee: audit standards, Tehran, P.160, 2002, (in Persian).

 

[6] Farshadfar, S., Monem, R., Further evidence of the relationship between accruals and future cash flows,

Accounting and Finance, 2017, 59(1), P.143–176, Doi.org/10,1111/acfi.12260.

 

[7] Etemadi, H., Azar, A., Bagaiee, V., Applying neural networks in predicting corporate profitability, Journal of Accounting Knowledge, 2012, 3(10), P. 51-70, (in Persian).

 

[8] Hamidian, M., Mohammadzadeh Mogaddam, M, b. Nagdi, S., Esmaili, J., Predicting dividened policy using Univariate and multi-variable neural network models, journal of knowledge of investement, 2018, 26, P.168-183, (in Persian).

 

[9] Heydar pour, F., Arabi, M., Ganad, M., effect of short time,middle time and longtime horizons on the future cash flows prediction, journal of strategy of financial management, 2016, 15, P.107-127(in Persian).

 

[10] Khashei, M., Bijari, M. and Mokhatab Rafiei, F. Variable Selection in Multilayer Perceptron Neural Networks for Prediction Using Self-Organized Mappings(SOM), Journal of Numerical Methods in Engineering, 2013, 33(1), P. 479– 489.

 

[11] Davoodi Kasbi, A., Dadashi, I., Azinfar, K., Stock price analysis using machine learning method(Non-sensory-parametric backup regression algorithm in linear and nonlinear mode). Advances in Mathematical Finance and Applications, 2021, 6(2), P. 285-301. Doi: 10.22034/amfa.2019.1869838.1232

 

[12] Doaei, M., Mirzaei, S., Rafigh, M., Hybrid Multilayer Perceptron Neural Network with Grey Wolf Optimization for Predicting Stock Market Index. Advances in Mathematical Finance and Applications, 2021, 6(4), P. 883-894. Doi: 10.22034/amfa.2021.1903474.1452

 

[13] Larson, C., Sloan, R., Zha Gied, J., Defining, measuring, and modeling accruals: a guide for researchers, Review of Accounting Studies, 2018, 23(3), P.827-871, Doi: 10.1007/s11142-018-9457-z.

 

[14] Li, Y., Mountinho, L, A., Opong, K., Pang, Y., Cash flow forecasting for South African firms, Review of Development Finance, 2015, 5, P.24-33, Doi: 10.1016/j.rdf.2014.11.001.

 

[15] Lorek, K., Willinger, G., Time-series properties and the predictive ability of quarterly cash-flows, Advances in Accounting, 2008, 24, P. 65–70.

 

[16] Orpurt, S., Zang, Y, Do direct cash flow disclosures help predict future cash flows and earnings? The Accounting Review, 2009, 84(3), P.893–935.

 

[17] Pang, Y., The design of dynamic and nonlinear models in cash flow prediction, PhD thesis, University of Glasgow, Scotland, 2015, https://eleanor.lib.gla.ac.uk/record=b3130051.

 

[18] Roozbacksh, N., Rezaiepajand, P., Najari, M., Prediction of the current cash flows using artificial neural network in Tehran Stock Exchange, the first international conference on political epic (with an approach to the middle east revolutions) and economic epic (with an approach to management and accounting), Rudehen, azad university of rudehen branch, 2013, (in Persian).

 

[19] Sagafi, A., Sarraf, F., Aghaballaiebacktiar, H., Application of artificial neural networks in predicting the future cash flows, journal of accounting studies, 2015, 3(9), P.63-80 (in Persian).

 

[20] Sarraf, F., SAgafi, A., A model for forecasting the cash flow in Iranian companies, researches of auditing and accounting, 2013, 31, P. 1-26(in Persian).

 

[21] Sarraf, F., Sagafi, A., Hassas Yeghane, y., and Amiri, M., Linear and nonlinear regression models to estimate cash flow, Journal of Management Accounting and Auditing Knowledge, 2013, 7, P. 141-155.

 

[22] Shubita, M, F., Accruals and Cash Flows- A Case of Jordan, Interdisciplinary Journal of Contemporary Research in Business, 2013, 5, P.428-441.

 

[23] Tavakoli, M., Doosti, H., Chesneau, C., Capsule Network Regression Using Information Measures: An Application in Bitcoin Market., Advances in Mathematical Finance and Applications, 2022, 7(1), P. 37-48. Doi: 10.22034/amfa.2021.1932547.1603

 

[24] Yarifard, R., Kermang, J., Nematjoo, H., Ebrahimi, M., Prediction of the cash flows in accepted companies of Tehran Stock Exchange, journal of management, 2016, 107, P.47-57 (in Persian).