Forecasting the return of government exchange-traded funds based on linear and nonlinear models in machine learning algorithms

Predicting the performance of government Exchange-Traded Funds (ETFs) in the Tehran Stock Exchange holds a significant position due to their importance in macroeconomic decision-making and financial markets. This study aims to develop a model for predicting the returns of these funds using advanced machine learning algorithms, such as Support Vector Machines (SVM) and Linear Regression. The primary objective is to enhance economic and investment strategies at the governmental and institutional levels through accurate return analysis of these funds.

The study is applied in terms of purpose and descriptive-analytical in terms of methodology. Data for government ETFs in the Tehran Stock Exchange, covering the four years (2020–2023), were collected from the Tehran Stock Exchange Technology and Information Center (FIP Iran). Data analysis was conducted using two machine learning algorithms (SVM and Linear Regression) in R software. Due to the differences in asset composition, the ETFs "Palaayesh-e-Yekam" and "Daaraay-e-Yekam" were selected as the primary samples.

The results indicated that SVM and Linear Regression algorithms could predict the returns of government ETFs with high accuracy. Specifically, the "Palaayesh-e-Yekam" ETF, due to its less diverse asset composition and the inefficient Tehran market, exhibited lower prediction errors. The comparison of algorithm performance showed that both methods provided satisfactory accuracy and are suitable for future forecasting in this domain.

Originality/Value: 

By employing advanced machine learning algorithms, this research presents a practical model for predicting the returns of government ETFs in the Tehran Stock Exchange. The findings can be utilized in economic and investment decision-making at the governmental and institutional levels.