Stock Price Prediction Model Using Enhanced LSTM and ARIMA

The price deviation of the stock market, which is determined by a complex interaction of elements, is a basic feature of market dynamics. Investors who want to successfully manage risks, navigate the market, and seize opportunities must comprehend these variations. This article aims to introduce a creative approach using enhanced LSTM and ARIMA algorithms to enhance stock market price predictions. Predictive methods fall into two main categories: statistical methods, which encompass models like logistic regression, ARIMA, and other artificial intelligence techniques such as multi-layer perceptron, RNN, Naïve Bayes, vector bearers, cyclic neural networks, and many others. Among these models, the research shows that LSTM performs with a lower error percentage compared to others. LSTM provides significantly more advantages and ARIMA outperforms other algorithms in many ways. This paper lists out the advantages of LSTM and ARIMA models in stock price prediction and performs a comparison between them.