Comparing the Efficiency of Statistical Models and Machine-Learning Models and Choosing the Optimal Model for Predicting Net Profit and Operating Cash Flows

Aug 4, 2026

Upload by Ivy

The study compares machine-learning and statistical models for forecasting net profit and operating cash flows using both accrual and cash variables. The research proceeds in three stages: dataset and variable selection, model building, and estimation, focusing on Tehran Stock Exchange firms observed from 2012 to 2021. Results show accrual variables provide stronger explanatory power than cash variables for net profit and future operating cash flows. Machine-learning methods generally outperform statistical approaches, with symbolic regression excelling among machine-learning models and the probit model leading among statistical models, while some individual models vary in relative performance.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages22

Reading Time55 min

AccessFree to download

Introduction

Research objectives and hypotheses

Materials & Methods

Data sources and modeling tools

Findings

Vuong test and comparative performance

[https://amf.ui.ac.ir](https://amf.ui.ac.ir) Journal of Asset Management and Financing E-ISSN: 2383-1189 Vol. 11, Issue 2, No. 41, Summer 2023, p 53-74 Received: 05.02.2023 Accepted: 04.10.2023 Research Paper Comparing the Efficiency of Statistical Models and Machine-Learning Models and Choosing the Optimal Model for Predicting Net Profit and Operating Cash Flows Sajjad Mirzaei MSc. of Financial Management, Faculty of Economics and Management, Urmia University, Urmia, Iran [st_s.mirzaei@urmia.ac.ir](st_s.mirzaei@urmia.ac.ir) Ali Ashtab * Assistant Professor, Department of Accounting, Faculty of Economics and Management, Urmia University, Urmia, Iran [a.ashtab@urmia.ac.ir](a.ashtab@urmia.ac.ir) Akbar Zavari Rezaei Assistant Professor, Department of Accounting, Faculty of Economics and Management, Urmia University, Urmia, Iran [a.zavarirezaei@urmia.ac.ir](a.zavarirezaei@urmia.ac.ir) Abstract The present study compared the predictive performance of machine-learning models and statistical models for forecasting profit and operational cash flow by using a combination of accrual and cash variables. The research method encompassed 3 main stages: data set and variable selection, modeling, and estimation. The study focused on companies listed on the Tehran Stock Exchange (TSE), analyzing data from 184 companies over the period of 2012-2021. The findings indicated that accrual variables exhibited greater explanatory power than cash variables in predicting net profit and future operating cash flow. Furthermore, the comparison of machine-learning and statistical models for forecasting net profit and future operating cash flow revealed that the artificial intelligence approach exhibited superior capability. Specifically, symbolic regression among the machine-learning models and the probit model among the statistical models demonstrated higher performance. Additionally, the results indicated that certain statistical models outperformed some machine-learning models while, on average, machinelearning models outperformed statistical models. Keywords: Classification, Data Mining, Machine Learning, Net Profit Forecasting, Operating Cash Flow Forecasting. Introduction In the current intensely competitive business environment, precise prediction of financial outcomes has emerged as a pivotal element in organizational triumph. Projecting crucial financial indicators, such as net profit and operating cash flows, equips businesses with the insight needed to make well-informed choices regarding investment strategies, resource distribution, and comprehensive financial strategizing. The capacity to anticipate future financial performance enables organizations to streamline operations and mitigate risks. Consequently, there is an escalating need for effective forecasting models. This study had two primary objectives: firstly, assessing the predictive capability of accrual and cash variables for forecasting profit and future cash flows and secondly, comparing the efficacy of statistical models and machine-learning models in predicting net profit and operating cash flows. Statistical models seek to scrutinize historical data patterns and underlying relationships to anticipate future financial outcomes. Conversely, machine-learning models have emerged as a potent alternative, employing advanced computational techniques to glean insights from data and make predictions without explicit programming. This research was guided by four hypotheses: First hypothesis: The predictive capability of accrual variables for future net profit significantly exceeds that of cash variables. Second hypothesis: The predictive capacity of accrual variables for future operational cash flow significantly surpasses that of cash variables. Third hypothesis: Machine-learning models outperform statistical models significantly in predicting net profit. *Corresponding author Mirzaei, S., Ashtab, A., Zavari Rezaei, A. (2023) . Comparing

FAQs

What is the main purpose of the study?

To compare the predictive efficiency of statistical models and machine-learning models for forecasting net profit and future operating cash flows using accrual and cash variables.

Which variables show stronger explanatory power for net profit and future operating cash flow?

Accrual variables demonstrate greater explanatory power than cash variables for both net profit and future operating cash flows.

How do machine-learning models compare with statistical models overall?

On average, machine-learning models outperform statistical models for predicting net profit and future operating cash flows, though some specific models outperform others in certain comparisons.

Aug 4, 2026

Upload by Ivy