Predicting Automobile Stock Prices Index in the Tehran Stock Exchange Using Machine Learning Models

This paper analyses the performance of machine learning models in forecasting Tehran Stock Exchange's automobile index. Historical daily data from 2018-2022 was pre-processed and used to train Linear Regression (LR), Support Vector (SVR), Random Forest (RF) models. The were evaluated on mean absolute error, squared root error R2 score metrics. results indicate that LR SVR outperformed RF predicting stock prices, with achieving lowest scores. demonstrates capability techniques model complex, nonlinear relationships financial time series data. pioneering study a previously unexplored dataset provides empirical evidence can reliably forecast market holding promise for investing applications.