透過您的圖書館登入
IP:18.222.148.124
  • 期刊

遺傳演算法建構台灣股市期貨買賣決策規則之研究

Building Taiwan Stock Futures Market Trading Rule Using Genetic Algorithms

摘要


本研究採用台灣大盤股價指數及成交值所轉換的18種價量技術指標做為輸入參數,以期末資金最大化做為適應度函數,應用遺傳演算法(Genetic Algorithms)的最佳化能力建構台灣大盤加權指數的買賣決策規則。研究結果顯示,本研究所比較之三種交易策略:雙向GA買賣決策策略、單一雙向GA買賣決策策略及買入持有策略,在測試範例期間的平均年獲利率分別是10.72%、6.30%與-7.2%以及平均相對獲利係數分別是1.19、1.15與1.00。另外由雙向GA買賣決策策略及單一雙向GA買賣決策策略的風險評估得知,其最小年獲利率分別為2.96%與-16.90%及最小總成功率分別為46.70%與26.40%。因此,在雙向獲利的條件下所產生的雙向GA買賣決策規則是一個穩定且有效的台灣股市交易策略。

並列摘要


This research used 18 kinds of price and volume technical indices transferred from the Taiwan stock price index as the input parameters, the maximization of the final capital as the fitness function, the genetic algorithms as the optimization tool to construct the trading rules for the Taiwan stock price index. The findings showed that the three kinds of trading strategies, the bidirectional GA strategy, the sole bidirectional GA strategy, and the buy and hold strategy, in test period produced the average year profit rate respectively with 10.72%, 6.30% and -7.2%, as well as the relative profit coefficient respectively with 1.19, 1.15 and 1.00. Moreover, compared the risk assessment of the bidirectional GA strategy and the sole bidirectional GA strategy, the smallest year profit rate respectively is 2.96% and -16.90%, and the smallest total success ratio respectively is 46.70% and 26.40%. Therefore, the bidirectional GA strategy is a not only effective but also stable Taiwan stock market trading strategy.

參考文獻


陶宏德(1995)。應用遺傳演算法達成知識之最適化-以臺灣股市技術分析指標爲例(碩士論文)。交通大學資訊管理研究所。
邱昭彰、李安邦(1998)。遺傳演算法在發展股市投資專家知識規則之研究。資管評論。8,21-38。
黃焜煌(1999)。以類神經網路預測台灣股價報酬率-以電子股爲例(碩士論文)。朝陽科技大學財務金融系。
簡辰氶(2001)。結合MACD與類神經模糊技術之股票預測模型-以台灣金融股爲例(碩士論文)。靜宜大學企業管理研究所。
林耀堂(2001)。遺傳程式規劃於股市擇時交易策略之應用(碩士論文)。國立中央大學資訊管理學系。

被引用紀錄


Szu, F. (2016). 應用技術分析於期貨市場進行危機預警:以台指期為例 [master's thesis, National Tsing Hua University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0016-0411201614430227

延伸閱讀