Browsing by Author "Lin, Chiou-Hung"

Now showing 1 - 2 of 2

Data Mining Application to Financial Market to Discover the Behavior of Entry Point - A Case Study of Taiwan Index Futures Market
(2016)
Wu, Mei-Chen
;
Yang, Bo-Wen
;
Lin, Chiou-Hung
;
Huang, Ya-Hui
;
Chen, An-Pin
The value of the investment method is that investors who are anxious to pursue, there are many value investing methods have been proposed, but only a minority of the value investing method were proved to be effective. The study is based on messages generated defined value of the investment by Steidlmayer in 1984 proposed market profile theory. In order to extract trading behavior of dealer and product value by the huge financial trading information, the model used the trading data to capture feature patterns, and find the double distribution trend day generated by market profile. The experimental results show the single print as an entry point, and the reference to historical support and pressure line as an exit point. The results show the returns are 24.09 points and the accuracy achieved 57.45%. The results had shown the analysis model can find the investment goods real value from the huge trading information, and help investors obtain excess returns.
The Discovery of Financial Market Behavior Integrated Data Mining on ETF in Taiwan
(2016)
Yang, Bo-Wen
;
Wu, Mei-Chen
;
Lin, Chiou-Hung
;
Huang, Chiung-Fen
;
Chen, An-Pin
In practice, many physics principles have been employed to derive various models of financial engineering. However, few studies have been done on the feature selection of finance on time series data. The purpose of this paper is to determine if the behavior of market participant can be detected from historical price. For this purpose, the proposed algorithm utilizes back propagation neural network (BPNN) and works with new feature selection approach in data mining, which is used to generate more information of market behavior. This study is design for exchange-traded fund (ETF) to develop the day-trade strategy with high profit. The results show that BPNN hybridized with financial physical feature, as compared with the traditional approaches such as random walk, typically result in better performance.