您的瀏覽器不支援Javascript,部分功能將無法呈現。

:::

News

:::

Colloquium & Speaker Series
  • Title:Lecture on "Application of Integrated Data Mining Techniques in Stock Market Forecasting"
  • Post Date:2014-10-14

 

Topic:Application of Integrated Data Mining Techniques in Stock Market Forecasting


Speaker林光甫  博士候選人

Co-ModeratorsProf. Chin-Yin Huang
TimeOct 22 (Wednesday), 2014. 12:10 to 13:00            
VenueIEⅡ 107

~歡迎到場聆聽~

為便於準備相關事宜~請事先報名~
報名方式:線上報名
聯絡人:工工系謝小姐 04-23594319#112

Abstract
Stock market is considered too uncertain to be predictable.  Many individuals have developed methodologies or models to maximize the probability of making a profit in their stock investment.  The overall hit rates of these methodologies and models are generally too low to be practical for real-world application.  One of the major reasons is the huge fluctuation of the market.  Therefore, the current research focuses in the stock forecasting area is to improve the accuracy of stock trading forecast.  This paper introduces a system that addresses the particular need.  The system integrates various data mining techniques and supports the decision making for stock trades. The proposed system embeds the top-down trading theory, artificial neural network theory, technical analysis, dynamic time series theory, and Bayesian probability theory.  To experimentally examine the trading return of the presented system, two examples are studied.  The first uses the Taiwan Semiconductor Manufacturing Company (TSMC) dataset that covers an investment horizon of 240 trading days.  The second example examines the stock data of Evergreen Marine Corporation, an international marine shipping company.

  • Attach File:
  • Reference Link:
  • Poster:
  • Last Update Time:2014-11-19 AM 9:54

cron web_use_log