Predictions of Tesla Stock Price based on Linear Regression, SVM, Random Forest, LSTM and ARIMA

Abstract

The stock market of a country is an important financial market. A booming stock market promotes the effective use of social capital, the prudent deployment of economic resources, and the expansion of the country's macroeconomics. Making more informed decisions as an investor is made possible by the development of trustworthy equity market models. A trading model allows market participants to select corporations that pay the highest dividend payments while lowering the risks associated with investing. However, batch processing methodologies make stock market research more challenging as a result of the strong connection between stock prices. The advent of technological achievements like universal digitization has elevated share market forecasting into a highly advanced age. Through the research and comparison of several methodologies, this article tries to discover the most accurate approach for predicting Tesla stock closing prices. Predictions are made using statistical approaches such as ARIMA and machine learning methods such as SVM , Linear Regression, Random Forests, and LSTM. Following a thorough examination of all approaches, it was discovered that the accuracy of machine learning methods in predicting stocks is higher than that of statistical methods and integrated algorithm technologies like Random Forest have excellent anti-interference and anti-overfitting characteristics, which are more suitable for evaluating high-volatility stocks like Tesla.