Stock market prediction with artificial intelligence

• Main Author: Liu, Wenhan
• Other Authors: Mohammed Yakoob Siyal
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/145080
• Institution: Nanyang Technological University

Since it is easy to access stock and financial information of public companies, people, especially investors, try to use this material and public numerical information to make prediction and classification on the stock price and its trend, whether it will increase or not. Artificial Intelligence and Machine Learning techniques are widely applied in lots of fields, whose applications include making classification and prediction. In this final year project, a framework is constructed to be used for making classification on public company stock price, whether it will increase or not, as well as making prediction on public company stock price trend to be upward or downward. A Personal Selection Strategy as well as machine learning techniques, including Decision Tree, Long Short-term Memory Networks (LSTM) and Support Vector Machines (SVM), are applied in this project. There are three main goals of this project. The first one is to select the stocks which will have higher probability of increasing in stock price. The second one is to analyse the accuracy of each technique model applied and make comparison of these technique models. The last one is to analyse whether these models can be commercially applied to help investors make profits. The findings of this project justify that all the machine learning techniques applied give high accuracy and LSTM gives the highest accuracy followed by SVM.