Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/149489
Title: Financial trading decisions based on deep learning : predicting the number of shares, action strategies
Authors: Srinivas Avichal Ghoghari
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2021
Publisher: Nanyang Technological University
Source: Srinivas Avichal Ghoghari (2021). Financial trading decisions based on deep learning : predicting the number of shares, action strategies. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/149489
Project: A1108-201
Abstract: Various deep learning techniques that have been used to improve on an existing technical analysis method simple moving average to predict stock price movement Simple moving average is a simple mathematical model used by traders to measure the momentum and direction that stocks are heading. Supervise learning techniques for example linear regression, logistic regression and random forest will be used to improve upon the existing simple moving average. The second portion of the report will have the development and testing of deep Q learning algorithm for implementation to simple moving average. The models are tested over a fixed period for consistency of results (date used for test and train data set). The models will be finetuned over substantial number of hyperparameters e.g., single, and multi-asset class analysis, size of input (batch size), number of epochs, learning rate. The results from the developed deep learning algorithms will compared to both application with vanilla simple moving average without improvement and buying and holding s&p500 and individual stocks on the S & P 500 e.g., Apple, 3M, Amazon etc.
URI: https://hdl.handle.net/10356/149489
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP submission Srinivas Avichal Ghoghari (1).pdf
  Restricted Access
3 MBAdobe PDFView/Open

Page view(s)

90
Updated on Jan 23, 2022

Download(s)

3
Updated on Jan 23, 2022

Google ScholarTM

Check

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