智慧型外匯自動交易系統之設計與實作

DESIGN AND IMPLEMENTATION OF AN INTELLIGENT AUTOMATED FOREX TRADING SYSTEM

張育偉(Yu-Wei Chang)

指導教授 ： 陳志誠

大同大學/經營設計學院/資訊經營學系所/碩士(2010年)

摘要

本研究旨在設計並實作一個智慧型外匯交易系統，來模擬外匯市場上的交易情形，透過設計中智慧型外匯交易系統的不斷測試與改良後，使其具有替代手動交易，能夠實現精確決策的自動交易系統之目的。研究中，擷取慣性定律為理論基礎，來分析外匯市場的正向與負向能量。故，根據慣性定律，若是無外力影響，則動者會恆動之，外力若為目前趨勢帶來負向能量，將造成前進的動能變緩慢，甚至反轉，進而導致手動交易時，無法即時得知精確資訊，並做出良好決策。是故，本研究除了使用一個實現策略的完整投資工具外，在策略設計上，加上趨勢指標與震盪指標來輔助決策判斷。
在策略測試後，針對其策略面臨的問題與挑戰，做系統的評估與改善。讓此策略在外匯市場投資上，提供較低風險並能適應市場環境的決策，將來可作為未來真實外匯交易使用。

關鍵字

慣性定律 ； 外匯 ； 外匯市場 ； 自動交易系統

並列摘要

In this study an intelligent automated trading system for foreign exchange is designed and implemented. An intelligent trading system is developed to simulate the foreign exchange market transactions. Through continuous training and improvements, the system will be able to assist manual trading, achieving more accurate decision-making. Based on the law of inertia, we analyze positive and negative forces in the foreign exchange market. According to the law of inertia, if no external force exists, the movement will continue constantly. The external force can be viewed as the negative energy in reverse to the current trend. It will result in reduction of the forward momentum, even reversion of the current direction of movement. In the kernel of the system, trend indicators and oscillation indicators are referenced to improve the accuracy of investment decision. The paper also addresses the issues of strategies and the challenges of automated trading. After simulation, results are systematically analyzed and improvement suggestions are fed back. The system is expected to be able to trade automatically at a lower risk level.

並列關鍵字

Foreign Exchange ； Automated Trading ； Law of Inertia

參考文獻

13.Tier, M., (2005), The winning Investment Habits of Warren Buffett & George Soros. Taipei: Linking Pub

7.Bank for International Settlements (2007) Triennial central bank survey of foreign exchange and derivatives market activity in 2007

8.Dempster, M. H. A. & Jones, C. M. (2001) A real-time adaptive trading system using genetic programming. Quantitative Finance ,1, pp.397-413.

9.Dempster, M. A. H. & Leemans, V. (2006) An automated FX trading system using adaptive reinforcement learning. Expert Systems with Applications, 30(3):543-552.

12.Slaný, K. (2009), Towards the Automatic Evolutionary Prediction of the FOREX Market Behaviour, icais, 2009 International Conference on Adaptive and Intelligent Systems, pp.141-145