Stock Prediction with Random Forests and Long Short-term Memory

Date
2019-01-01
Authors
Han, Shangxuan
Journal Title
Journal ISSN
Volume Title
Publisher
Altmetrics
Authors
Research Projects
Organizational Units
Journal Issue
Series
Abstract

Machine learning as a popular computer science area has been promoted and developed for more than two decades. It has been applied in many fields in our life, like domestic products such as Alexa from Amazon, photographic products such as Mavic from Dji and so many other areas. This report represents an interesting way to apply machine learning and deep learning technologies on the stock market. We explore multiple approaches, including Long Short-Term Memory (LSTM), a type of Artificial Recurrent Neural Networks (RNN) architectures, and Random Forests (RF), a type of ensemble learning methods. The goal of this report is to use real historical data from the stock market to train our models, and to show reports about the prediction of future returns for picked stocks.

Description
Keywords
machine learning, deep learning, artificial neural network, long short-term memory, random forests, ensemble learning.
Citation
DOI
Source