Intelligent option trading

• Main Author: Manan Maheshwari.
• Other Authors: Quek Hiok Chai
• Format: Final Year Project
• Language: English
• Published: 2012
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: http://hdl.handle.net/10356/49106
• Institution: Nanyang Technological University

NEURAL fuzzy systems are hybrid systems that capitalize on the functionalities of fuzzy systems and neural networks. Existing neural fuzzy systems suffer from the following problems: 1) an inconsistent rulebase; 2) the need for prior knowledge such as the number of clusters to be computed; 3) heuristically designed knowledge acquisition methodologies; and 4) the stability–plasticity tradeoff of the system. Thus under this project, a novel self-organizing neural fuzzy system, named Self-Adaptive Fuzzy Inference Network (SaFIN) is explored to address the above mentioned drawbacks. The model is investigated and changes are proposed to the self-automated rule generating process of the model. As a result, the model is conceived with a more sound technique. Thus a new model, SaFIN++ is proposed in this paper. SaFIN++ is implemented and run over several benchmarking simulations to demonstrate its efficiency and accuracy as a self-organizing neural fuzzy system. Excellent results have been achieved with SaFIN++ being consistently placed among the top performing models for all experiments. The SaFIN++ parameters are analyzed in addition to implementing other features like cross validation, semantic rules creation, , identification of important rules, which serve to assess the accuracy of SaFIN++ more comprehensively, enhance the interpretability of SaFIN++, increase understanding about the working of SaFIN++. Neural fuzzy systems have numerous applications in the financial world today. Among the several financial applications, volatility modeling and forecasting is crucial to financial market investors, as such projections allow the investors to adjust their trading strategies in anticipation of future financial market movements. In this paper, an intelligent straddle trading system framework that consists of a volatility projection module (VPM) and a trade decision module (TDM) is implemented for financial volatility trading via the buying and selling of option straddles to help a human trader capitalize on the underlying uncertainties of the Hong Kong stock market. SaFIN++ is employed as the volatility forecasting neural fuzzy system to realize the volatility projection module. Based on the future volatility levels predicted, trading decisions (hold, buy, sell) are generated by the trade decision module. The volatility modeling, forecasting performances of SaFIN++ and the trading returns of the trading system are remarkable.