Abstract
Investment in the stock market is currently very popular due to its economic gain. Numerous researchers’ and academicians’ work is focused on financial time series prediction due to its data availability and profitability. Therefore, this study presents the design and implementation of a novel binary classification framework to predict stock market trends. The framework is composed of data preprocessing, feature engineering, feature selection and classification algorithms. The model is built on multiple sector stock market companies’ data collected from NASDAQ over a period of ten years. Various feature selection algorithms are applied in combination with several machine learning algorithms. Furthermore, as the new contribution, we have constructed two new features which have been found to be promising in terms of improving overall performance. Ultimately, a collaboration of feature selection and classification techniques is employed. The application of Principal Component Analysis (PCA) with Multilayer Perceptron and Support Vector Machine (SVM) to added featured datasets shows 100% accuracy on the majority of datasets. In summary, an intensive comparison is presented among the various feature selection and classification algorithms.
Highlights
Every country's economic growth depends upon stock market performance
Principal Component Analysis (PCA) performs as the best feature selection algorithm when it is used with Support Vector Machine, achieving 100% accuracy
The Principal Component Analysis (PCA) with Multilayer Perceptron and Support Vector Machine (SVM) on added feature datasets shows 100% accuracy
Summary
Every country's economic growth depends upon stock market performance. The stock market is highly volatile and unpredictable by nature. People want to invest in the stock market and expect profit from their investments. One may analyze many factors, better stock market performance and future price prediction remain challenging. The forecasting of rapidly changing stock prices is a very challenging task (Fama et al, 1969). Due to its dynamic nature, it is highly challenging to predict a stock price. To address this issue, there should be some system that can both detect the pattern in stock prices when influenced by the political, economic and natural environment and take into account people’s sentiment about a particular company
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call