DocumentCode :
1696742
Title :
Robust stock trading using fuzzy decision trees
Author :
Ochotorena, Carlo Noel ; Yap, Cecille Adrianne ; Dadios, Elmer ; Sybingco, Edwin
Author_Institution :
Electron. & Commun. Eng. Dept., De La Salle Univ., Manila, Philippines
fYear :
2012
Firstpage :
1
Lastpage :
8
Abstract :
Stock market analysis has traditionally been proven to be difficult due to the large amount of noise present in the data. Different approaches have been proposed to predict stock prices including the use of computational intelligence and data mining techniques. Many of these methods operate on closing stock prices or on known technical indicators. Limited studies have shown that Japanese candlestick analysis serve as rich information sources for the market. In this paper decision trees based on the ID3 algorithm are used to derive short-term trading decisions from candlesticks. To handle the large amount of uncertainty in the data, both inputs and output classifications are fuzzified using well-defined membership functions. Testing results of the derived decision trees show significant gains compared to ideal mid and long-term trading simulations both in frictionless and realistic markets.
Keywords :
commodity trading; data mining; decision trees; fuzzy set theory; pattern classification; uncertainty handling; ID3 algorithm; Japanese candlestick analysis; computational intelligence; data mining techniques; frictionless markets; fuzzy decision trees; inputs classifications; long-term trading simulations; membership functions; mid-term trading simulations; output classifications; realistic markets; robust stock trading; short-term trading decisions; stock market analysis; stock price prediction; technical indicators; uncertainty handling; Decision trees; Educational institutions; Feature extraction; Market research; Noise; Robustness; Security;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence for Financial Engineering & Economics (CIFEr), 2012 IEEE Conference on
Conference_Location :
New York, NY
ISSN :
PENDING
Print_ISBN :
978-1-4673-1802-0
Electronic_ISBN :
PENDING
Type :
conf
DOI :
10.1109/CIFEr.2012.6327785
Filename :
6327785
Link To Document :
بازگشت