Doctoral Dissertations
Financial prediction and trading via reinforcement learning and soft computing
Abstract
"The overall goal of this research is to develop a practical intelligent system that can be used in investment decision-making, especially for high-frequency security trading, to help investors realize more desired and reliable returns. The study is specific to two key areas which have direct bearing on high-frequency financial investment issues, i.e. financial time series short-term prediction and discrete technical security trading. The research addresses quantitative data modeling and analysis in financial stock markets using artificial intelligent methodologies. Assisted by traditional soft computing approaches, the focus of the work is to provide a systematic treatment of reinforcement learning design for intelligent high-frequency financial trading systems. The results presented in this dissertation represent an effort toward generic and robust implementations of on-line reinforcement learning / neuro-dynamic programming designs under a very large scale financial market system"--Introduction, page 8.
Department(s)
Engineering Management and Systems Engineering
Degree Name
Ph. D. in Engineering Management
Publisher
University of Missouri--Rolla
Publication Date
Fall 2005
Pagination
x, 142 pages
Note about bibliography
Includes bibliographical references (pages 129-141).
Rights
© 2005 Hailin Li, All rights reserved.
Document Type
Dissertation - Citation
File Type
text
Language
English
Subject Headings
Financial engineering
Neural networks (Computer science)
Dynamic programming
Mathematical optimization
Reinforcement learning (Machine learning)
Thesis Number
T 8854
Print OCLC #
77494793
Link to Catalog Record
Full-text not available: Request this publication directly from Missouri S&T Library or contact your local library.
http://merlin.lib.umsystem.edu/record=b5746513~S5Recommended Citation
Li, Hailin, "Financial prediction and trading via reinforcement learning and soft computing" (2005). Doctoral Dissertations. 1650.
https://scholarsmine.mst.edu/doctoral_dissertations/1650
Share My Dissertation If you are the author of this work and would like to grant permission to make it openly accessible to all, please click the button above.
