查詢結果分析
來源資料
相關文獻
- 神經網路及統計方法在臺股指數期貨預測研究之比較
- 迴歸模式與類神經網路在臺股指數期貨預測之研究
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- 專家系統振動訊號圖型判別之研究
- 反傳遞模糊類神經網路於流量推估之應用
- 類神經網路(Neural Networks)的種類及其在影像處理上的應用
- C++Fuzzy類神經網路物件導向發展系統之建立
- 臺灣汽保費率之估計--對數線性費率模式與類神經網路之比較
- 運用類神經網路於股價指數之套利--以日經225指數為例
頁籤選單縮合
題 名 | 神經網路及統計方法在臺股指數期貨預測研究之比較=The Application of ANN and Statistical Methods for Studying the TAIMEX Index Future |
---|---|
作 者 | 吳宗正; 溫敏杰; 侯惠月; | 書刊名 | 成功大學學報 |
卷 期 | 36(人文.社會篇) 民90.11 |
頁 次 | 頁91-109 |
分類號 | 563.53 |
關鍵詞 | 臺灣加權股價指數期貨; 類神經網路; 迴歸分析模型; 時間序列模型; TAIMEX Taiwan stock index future; Artificial neural network; Regression analysis; Time series analysis; |
語 文 | 中文(Chinese) |
中文摘要 | 台灣加權股價指數期貨自民國87年7月21日正式掛牌交易,至今已有兩年多的時間,投資大眾漸漸暸解它,並開始利用指數與現貨進行避險以及套利的活動。 至於類神經網路是一新興的學科,它是仿效人類神經系統的原理,建構一個可以思考的模式,並且利用外界的刺激,不斷地學習與更新以達到目標值的最佳化。根據國內外學者的研究報告發現,類神經網路不論應用於股價的預測或期貨的買賣點上均有不錯的結果。因此,本研究擬比較類神經網路與統計方法,在台灣加權股價指數期貨的收盤指數預測上,何者預測績效較佳。 由本研究之結果發現,在台灣加權股價指數期貨的收盤指數預測上,類神經網路與迴歸分析的預測績效較時間序列為佳。而類神經網路結合迴歸分析中的逐步迴歸方法篩選變數後的改良式類神經網路預測績效最好,而時間序列模型預測效果則最差。 |
英文摘要 | It’s been two years since TAIMEX Taiwan Stock Index Future begain its public trading on July 21, 1998. As investors have become more familiar with it, they started engaging hedging and arbitrage using the Future and spot. Artificial Neural Network (ANN) is a new and developing subject. The principle of ANN comes from human neural system. It is constructed as a model which can think and continuely learn from outside incentives until its objective is optimized. According to all the reseach papers being published, ANN has manifest effects when it is used to predict both the stock prices and the buy-sell time-point for the future. The objective of this paper is to determine which, ANN or the statistical methods, is better suited for predicting the closing index of TAIMEX. The findings of this paper are that both ANN and Regression Analyses are preferred over Time Series when used to predict the closing index of TAIMEX. Furthermore, the best results came from the revised ANN, which ANN used the variables selected by Regression Analysis. Time Series gave the worst prediction results in all cases. |
本系統中英文摘要資訊取自各篇刊載內容。