Author: Zhao, Taobo
Title: Pattern discovery in forex trading market with data mining techniques
Degree: M.Sc.
Year: 2012
Subject: Data mining.
Computer algorithms.
Foreign exchange market.
Hong Kong Polytechnic University -- Dissertations
Department: Department of Computing
Pages: xi, 113 leaves : ill. ; 30 cm.
Language: English
Abstract: Forex (Foreign Exchange) market, the largest financial market with huge trading volume, high liquidity and geographical dispersion, is considered as financial market closest to the ideal perfect competition. Therefore major currency pairs in forex market and U.S. Dollar Index (USDX) is chosen as dissertation research target. Basic concepts, economy theories and investment strategy such as fundamental analysis and technical analysis are discussed in dissertation. Especially technical indicators are completed adopted in experiment. Data mining, the Knowledge Discovery from Databases (KDD) process, the integration of artificial intelligence, machine learning, statistics and database systems as interdisciplinary science, is the dissertation research tools. Data mining algorithms such as decision tree (C5.0 and CHAID), artificial neural network (RBFN), time series (ARIMA and exponential smoothing) and support vector machines are applied to the tasks of classification and prediction in finance fields. Business understanding is crucial for data pre-processing and Excel Indicator Model generate data table as data mining data source. Input nodes include close price, trend indicators such as moving average, MACD, DMI, momentum indicators such as William %R, KDJ, RSI, CCI, BIAS and psychology indicator. Output node is "buy", "sell" or "hold" operation suggestion based on close price. Dissertation Experiment of Data Mining Pattern Discovery and Model Evaluation is based on SPSS PASW/ Clementine and Weka environment, with traditional statistical correlation analysis of major currency pairs and data mining analysis of U.S Dollar Index. The evaluation involves technical indicator variable importance and data mining algorithms accuracy rate.
Rights: All rights reserved
Access: restricted access

Files in This Item:
File Description SizeFormat 
b24736715.pdfFor All Users (off-campus access for PolyU Staff & Students only)3.79 MBAdobe PDFView/Open

Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.

By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

Show full item record

Please use this identifier to cite or link to this item: