Please use this identifier to cite or link to this item:
Title: Software development of pattern recognition and forecasting on financial time series data and news
Authors: Huang, YuHang
Keywords: Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Huang, Y. (2022). Software development of pattern recognition and forecasting on financial time series data and news. Final Year Project (FYP), Nanyang Technological University, Singapore.
Abstract: Stock trading is becoming extremely popular and easy with the improvement of technology nowadays. It is also one of the biggest factors that is driving economy growth. It will be very helpful if we are able to predict the stock movement so that we can achieve ”risk free” investment, but it is almost impossible in real life as the stock prices can be easily affected by all types of features. However, if we can achieve significantly good accuracy, it will be sufficient. In this paper, we will be testing the performance of some traditional machine learning models and deep learning models in predicting stock movement. The models we will use include Gaussian Naive Bayes, Logistic Regression, K Nearest Neighbour, Support Vector Classifier, Voting Classifier, Long Short Term Memory(LSTM) and Multilayer Perceptron. We will also introduce the Convolution Neural Network(CNN) model we adapt and an CNN+LSTM model which aims to make use of the feature extraction power of CNN and LSTM’s ability to extract important information across timesteps. The models have been used to predict next day stock movement for NASDAQ composite Index, Dow Jones Industrial Average, S&P 500 and Russell 2000.
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
695.3 kBAdobe PDFView/Open

Page view(s)

Updated on May 20, 2022


Updated on May 20, 2022

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.