Anfis for trading

• Main Author: Poh, Priscilla Qiong Wei
• Other Authors: Ravi Suppiah
• Format: Final Year Project
• Language: English
• Published: 2015
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: http://hdl.handle.net/10356/62694
• Institution: Nanyang Technological University

For the purpose of this research, adaptive neuro-fuzzy inference system (ANFIS) had been designed and tested to construct a decision making model for the Foreign Exchange Market (Forex) of EUR/USD currency pair. The decision model attempts to imitate how a human will make decision in the Forex market. A set of technical analysis commonly used by traders was used to represent the human decision in this experiment. The proposed model was trained and tested with sets of data processed based on the set of technical analysis. The proposed model was evaluated based on its root mean square error, misclassification error and total profit or loss based on a unit of open price. By the analysis of the output produced, it is possible to conclude that the proposed model developed can predict the trend of the market by making correct decision in the Forex market.