Stock Market Predictability Using Machine Learning Techniques

The purpose of this article is to examine stock market analysis using machine learning techniques unique and attractive way to reassess products according to the changing times, and to publish information to create textual information from one or more sources in order to identify different threats. This is accomplished by controlling the reader to estimate the value of the stock by determining the need to view chaotic data and estimate the impact of Microsoft. The product uses the Naive Bayes classifier. First, the newsletters and archives have been placed in a free file in the “Date” column after making some significant changes. It also has a structure similar to the data distribution that protects the nearest-neighbor (Well-NN) experiment. Lately, natural language processing is used in the Journal of Captions and has a guide with 20,000 commonly used words and how to convert them to vectorized text. Subsequently, Naive Bayes models were also developed using dropout datasets, 80 based on training data and 20 based on control data. Overall, the neural-based model was found to be slightly better and the macro means for F1 than the standard and configured model, and slightly better. The results of F1-score validate effectiveness of the proposed method, which achieves a satisfying performance.