JADE STOCK PREDICTOR - AN INTELLIGENT MULTI-AGENT BASED TIME SERIES STOCK PREDICTION SYSTEM

摘要

Financial prediction - such as stock forecast is always one of the hottest topics for research studies and commercial applications. In this paper, we propose an innovative intelligent multi-agent based environment, namely (iJADE) - intelligent Java Agent Development Environment - to provide an integrated and intelligent agent-based platform in the e-commerce environment. In addition to contemporary agent development platforms, which focus on the autonomy and mobility of the multi-agents, iJADE provides an intelligent layer (known as the 'conscious layer') to implement various AI functionalities in order to produce 'smart' agents. From the implementation point of view, we introduce the (JADE Stock Predictor - an intelligent agent-based stock Predictory system for stock prediction using our proposed Hybrid RBF recurrent Network (HRBFN). Using the 10-year stock pricing information (1990 - 1999) that consists of 33 major Hong Kong stocks for testing, iJADE Stock Predictor has achieved promising results in terms of efficiency, accuracy and mobility as compared with contemporary stock prediction models.