資訊管理學報
郝沛毅;龔千芬;
頁: 303-333
日期: 2022/10
摘要: 股價預測是橫跨金融與計算機科學領域的經典預測問題，由於成功預測股價 的潛在好處，它吸引一代又一代的學者與投資者從不同的角度、無數的學理、眾 多的投資策略和不同的實踐經驗來開發各種預測方法。股價預測的困難癥結點在 於影響股票漲跌的因素太多。股市波動通常是由熱門新聞推動的，社群媒體上的 推文則是反映了新聞事件的熱度，以及投資者對於該事件的態度。因此，分析社 群推文的文字資訊與股價技術指數的數值資料，為能夠幫助於我們預測未來的股 價變化。 由於股價受到眾多因素影響，很難通過簡單的模型進行預測。深度學習擁有 優異的特徵學習能力，支持向量機則是擁有優異的推理能力，本研究將結合兩者 的優點。本研究將提出一個混和深度模型來自動學習重要的特徵，該混和深度模 型是由卷積神經網絡（CNN）、雙向長短期記憶（BiLSTM）與注意力機制（AM） 組成。CNN 用於擷取輸入數據的位置不變特徵，BiLSTM 則是提取長時間依賴 性的特徵，AM 用於捕捉過去不同時間特徵狀態對股票收盤價的影響，以提高預 測的正確率。接著，本研究將擷取得到的特徵餵給模糊孿生支持向量機來建立最 佳的股價預測模型，並且透過轉移學習理論建立嶄新的深層模糊孿生支持向量機。 本研究在台積電股票的預測正確率最高為76.9667%，友達股票的預測正確率最 高為87.0856%，與經典的股價預測模型相比，本研究所提出的方法的預測正確 率明顯優於最先進的股價預測模型。
關鍵字: 股價預測;模糊支持向量機;卷積神經網路;雙向長短期記憶體;注意 力機制;
Abstract: Stock closing price prediction is an important problem in the intersection of computer science and finance. Due to the potential advantages of stock closing price prediction, it attracts generation after generation of investors as well as scholars to continuously develop various prediction methods from different perspectives, a multitude of investment strategies, different practical experiences and a myriad of theories. The stock closing price is often affected by hot news, and the tweets related to news reflect the heat of the breaking news, as well as the sentiment of investors towards the breaking news. Consequently, analyzing tweets and historical stock market index may help us to predict future price changes. Since stock price is affected by many factors, it is difficult to predict through a simple model. Deep learning methods have the advantage of learning features. Support vector machines have the advantage of generalizing very well. This paper will combine the advantages of both models. Therefore, this paper will develop a hybrid deep model to automatically learn important features. This deep model is composed of convolutional neural networks (CNN), bi-directional long short-term memory (BiLSTM), and attention mechanism (AM). CNN is utilized to discovery the time invariant features of the input data. BiLSTM is used to extract time dependency features. AM is used to extract the influence of feature states on the stock closing price at different times in the past to improve theclassification performance. The obtained feature will be fed to a deep fuzzy support vector machine to build an optimal stock prediction model. As for this study, the highest forecast accuracy is 76.9667% and 87.0856% for Taiwan Semiconductor Manufacturing Corporation and AU Optronics Corporation, respectively. When compared with previous prediction models, the method proposed in this study is significantly better than the state-of-the-art support vector machine and deep learning models.
Keywords: Stock prediction, Fuzzy support vector machine, Convolutional neural networks, bi-directional long short-term memory, Attention mechanism.;
瀏覽次數: 16888 下載次數: 1067
引用 導入Endnote
頁: 303-333
日期: 2022/10
摘要: 股價預測是橫跨金融與計算機科學領域的經典預測問題，由於成功預測股價 的潛在好處，它吸引一代又一代的學者與投資者從不同的角度、無數的學理、眾 多的投資策略和不同的實踐經驗來開發各種預測方法。股價預測的困難癥結點在 於影響股票漲跌的因素太多。股市波動通常是由熱門新聞推動的，社群媒體上的 推文則是反映了新聞事件的熱度，以及投資者對於該事件的態度。因此，分析社 群推文的文字資訊與股價技術指數的數值資料，為能夠幫助於我們預測未來的股 價變化。 由於股價受到眾多因素影響，很難通過簡單的模型進行預測。深度學習擁有 優異的特徵學習能力，支持向量機則是擁有優異的推理能力，本研究將結合兩者 的優點。本研究將提出一個混和深度模型來自動學習重要的特徵，該混和深度模 型是由卷積神經網絡（CNN）、雙向長短期記憶（BiLSTM）與注意力機制（AM） 組成。CNN 用於擷取輸入數據的位置不變特徵，BiLSTM 則是提取長時間依賴 性的特徵，AM 用於捕捉過去不同時間特徵狀態對股票收盤價的影響，以提高預 測的正確率。接著，本研究將擷取得到的特徵餵給模糊孿生支持向量機來建立最 佳的股價預測模型，並且透過轉移學習理論建立嶄新的深層模糊孿生支持向量機。 本研究在台積電股票的預測正確率最高為76.9667%，友達股票的預測正確率最 高為87.0856%，與經典的股價預測模型相比，本研究所提出的方法的預測正確 率明顯優於最先進的股價預測模型。
關鍵字: 股價預測;模糊支持向量機;卷積神經網路;雙向長短期記憶體;注意 力機制;
A Stock Closing Price Prediction Model based on CNN-BiLSTM-AM and Deep Fuzzy Twin Support Vector Machine
Abstract: Stock closing price prediction is an important problem in the intersection of computer science and finance. Due to the potential advantages of stock closing price prediction, it attracts generation after generation of investors as well as scholars to continuously develop various prediction methods from different perspectives, a multitude of investment strategies, different practical experiences and a myriad of theories. The stock closing price is often affected by hot news, and the tweets related to news reflect the heat of the breaking news, as well as the sentiment of investors towards the breaking news. Consequently, analyzing tweets and historical stock market index may help us to predict future price changes. Since stock price is affected by many factors, it is difficult to predict through a simple model. Deep learning methods have the advantage of learning features. Support vector machines have the advantage of generalizing very well. This paper will combine the advantages of both models. Therefore, this paper will develop a hybrid deep model to automatically learn important features. This deep model is composed of convolutional neural networks (CNN), bi-directional long short-term memory (BiLSTM), and attention mechanism (AM). CNN is utilized to discovery the time invariant features of the input data. BiLSTM is used to extract time dependency features. AM is used to extract the influence of feature states on the stock closing price at different times in the past to improve theclassification performance. The obtained feature will be fed to a deep fuzzy support vector machine to build an optimal stock prediction model. As for this study, the highest forecast accuracy is 76.9667% and 87.0856% for Taiwan Semiconductor Manufacturing Corporation and AU Optronics Corporation, respectively. When compared with previous prediction models, the method proposed in this study is significantly better than the state-of-the-art support vector machine and deep learning models.
Keywords: Stock prediction, Fuzzy support vector machine, Convolutional neural networks, bi-directional long short-term memory, Attention mechanism.;
瀏覽次數: 16888 下載次數: 1067
引用 導入Endnote