A significant amount of work has been done in the area of price series forecasting using soft computing techniques, most of which are based upon supervised learning. Unfortunately, there has been evidence that such models suffer from fundamental drawbacks. Given that the short-term performance of the financial forecasting architecture can be immediately measured, it is possible to integrate reinforcement learning into such applications. In this paper, we present the novel hybrid view for a financial series and critic adaptation stock price forecasting architecture using direct reinforcement. A new utility function called policies-matching ratio is also proposed. The need for the common tweaking work of supervised learning is reduced and the empirical results using real financial data illustrate the effectiveness of such a learning framework.

Meeting Name

2004 IEEE International Joint Conference on Neural Networks


Engineering Management and Systems Engineering

Keywords and Phrases

Direct Reinforcement Learning; Financial Forecasting Architecture; Financial Series; Forecasting Theory; Learning (Artificial Intelligence); Neural Nets; Neural Networks; Policies Matching Ratio; Price Series Forecasting; Soft Computing Techniques; Stock Markets; Stock Price Data; Stock Price Forecasting Architecture; Supervised Learning; Utility Function; Utility Theory

International Standard Serial Number (ISSN)


Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 2004 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.