艾略特波浪理論於台灣期貨指數日內交易之行為知識發現

Abstract

台灣屬於淺碟式經濟體，中長期的走勢往往會受到各消息面的影響而大幅波動。投資人往往因為隔夜持有股票導致開盤承受很大的風險，因此本研究以日內交易規避隔夜持有之風險。本研究嘗試以波浪理論之特徵規則作為依據，發現股價波動所隱含的變動規律。綜觀過去技術分析之研究，發現過去研究大多著重於技術指標之探討，對於以股價型態為基礎進行趨勢變動分析之研究則較少，且波段與趨勢皆建立於型態上。艾略特波浪理論即以型態為基礎，強調股價的波動具有一定的變動規律性，因此若能有效研判型態以掌握大趨勢，投資人可獲得較高的報酬並減低風險。

本研究中採用2008-2012共5年台灣加權股價指數期貨做為研究資料，以不同的時間區隔截取波浪理論的轉折點，將轉折點所形成的波浪的物理力量特徵值正規化，做為倒傳遞類神經網路的輸入值，預測下一個波浪的走勢。同時設定門檻值與停損停利機制，計算其準確率與投資績效。研究結果發現，台灣加權股價指期貨的價格趨勢確實會受到物理力量變動的影響。實驗結果顯示，當時間區隔以15分鐘的區間抓取轉折點的投資獲利率最大，因此在進行日內交易的操作時，宜以15分鐘左右為區隔來分析趨勢。

Taiwan stock market belongs to a shallow-plate market and the long –term trend is often affected by news with high volatility. The investors often bear a huge risk in the opening of the market because of holding stocks overnight. This study uses the intraday trading of TAIEX Futures to avoid overnight risks. Furthermore, this study attempts to find the stock price trend based on the rule of Elliott wave theory. As we find that most researches emphasize on the technical indicators, reviewing technical analysis of the recent researches, but few on stock price patterns as the basis of the trend analysis. Elliott Wave Theory is one of the most important theories, which stresses the stock price variation with certain regularity and consists of eight-wave combination to complete stock market cycle. Therefore, if the entire stock market trend could be effectively expressed by those waves combination, investors could get higher returns and lower risks as long as we can learn the trend pattern.

This study used daily TAIEX from 2008 to 2012 this five years data as the research objective, catching the turning point of the wave from different time sections, then normalized physical force value as input of the Back-propagation neural network to predict the trend of the next wave. At the same time, the different threshold was set with trading strategies and the calling of rules of gain and loss and to calculate their accuracy rate and investment performance. The result shows that the trend of TAIEX is indeed affected by the physical force of price trend. When the time interval is 15 minutes, the investment performance was the largest in the intraday trading. Therefore, we should use the time section of 15 minutes to forecast and analysis when trading in the intraday.