Stock Price Prediction Using a Multivariate Multistep LSTM: A Sentiment and Public Engagement Analysis Model

Abstract:

The impact of many factors on stock price has made the prediction of the stock market a problematic and highly complicated task to achieve. IoT analytics has enabled predictive analysis concerning the stock market, with internet search trends, reactions to current events, Twitter data, and historical stock returns as input data. Although inconsistencies remain as to which data sources are deemed most adequate, data preprocessing techniques have successfully overcome data integrity issues and unstructured data formats in specific applications. Additionally, advancements in computational power and machine learning technologies have led to the ability to handle tremendous amounts of information, accompanied by the growth of interest in this specific domain. In this paper, a Multivariate Multistep Output Long-Short-Term-Memory (MMLSTM) model is proposed to provide a one-week prediction on the stock close value for the technology company, ldquo;Apple Inc.rdquo; with the stock name ldquo;AAPLrdquo;. A large variety of data sources enabled by IoT platforms have been employed to model the impact of public sentiment and engagement on the closing price of this particular stock by looking at Google Search Trends, e-News headlines, and Tweets involving AAPL and its products. The proposed MMLSTM has improved the Mean Square Error (MSE) of up to 65% compared to ARIMA and Random Forest models. In addition, the proposed MMLSTM has outperformed most of the LSTM models introduced in the literature