金融市場價格變動受到市場供需、投資人行為及資訊流動等因素影響，傳統投資分析多依賴產業面、基本面、財務面及技術面資訊進行決策，然而短期價格波動往往無法完全由上述因素解釋。近年來，高頻交易與人工智慧（Artificial Intelligence， AI）技術快速發展，使市場微觀結構（Market Microstructure）資訊逐漸成為金融市場研究的重要方向。市場微觀結構能反映價格形成過程中的供需變化，可能提供較價格本身更早的市場訊號。此外，金融市場具有高度複雜性與非線性特徵，與熱力學系統存在相似之動態行為，因此本研究進一步導入熱力學概念量化市場狀態。 本研究以臺灣證券交易所（Taiwan Stock Exchange Corporation， TWSE）提供之台灣加權股價指數（Taiwan Stock Exchange Capitalization Weighted Stock Index， TAIEX）5秒高頻資料為研究對象，利用委託買賣資訊、成交資訊及買賣失衡指標建立市場微觀結構特徵，並建構市場能量（Market Energy）、市場熵（Market Entropy）及市場溫度（Market Temperature）等熱力學特徵。研究中分別採用極端梯度提升（eXtreme Gradient Boosting， XGBoost）、長短期記憶網路（Long Short-Term Memory， LSTM）與轉換器（Transformer）三種AI模型進行未來60秒價格方向預測，並提出熱力學風險覆蓋層（Thermodynamic Risk Overlay， TRO），透過市場熵與市場溫度辨識高風險市場環境，以降低交易風險。 實驗結果顯示，市場微觀結構資訊具備高頻價格預測能力，而導入TRO後，各模型之累積報酬率與風險控制能力皆獲得改善。進一步透過 Walk-Forward Expanding Window Validation 驗證，結果顯示本研究方法在不同市場環境下均具有良好穩健性與泛化能力。 綜合研究結果可知，市場微觀結構與熱力學特徵能有效提升交易策略績效，所提出之TRO亦能改善風險管理能力。本研究提供一套結合市場微觀結構、AI模型與風險控制機制之高頻交易研究架構，可作為未來量化交易與金融科技研究之參考。;Financial market price movements are influenced by various factors， including market supply and demand， investor behavior， and information flow. Traditional investment analysis primarily relies on industry trends， fundamental analysis， financial indicators， and technical analysis for decision-making. However， short-term price fluctuations cannot always be fully explained by these factors. With the rapid development of high-frequency trading (HFT) and artificial intelligence (AI)， market microstructure information has become an increasingly important research area in financial markets. Market microstructure reflects the supply–demand dynamics during the price formation process and may provide earlier market signals than price information itself. Furthermore， financial markets exhibit highly complex and nonlinear characteristics that resemble the dynamic behavior of thermodynamic systems. Therefore， this study introduces thermodynamic concepts to quantify market conditions. This study uses 5-second high-frequency data of the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) provided by the Taiwan Stock Exchange Corporation (TWSE). Market microstructure features are constructed from order flow information， transaction information， and order imbalance indicators. In addition， thermodynamic features， including Market Energy， Market Entropy， and Market Temperature， are developed to characterize market conditions. Three artificial intelligence models， namely eXtreme Gradient Boosting (XGBoost)， Long Short-Term Memory (LSTM)， and Transformer， are employed to predict future price movements over the next 60 seconds. Furthermore， a Thermodynamic Risk Overlay (TRO) is proposed to identify high-risk market environments through market entropy and market temperature， thereby reducing trading risk. Experimental results demonstrate that market microstructure information possesses predictive power for high-frequency price movements. After incorporating the Thermodynamic Risk Overlay， all models achieve improvements in cumulative returns and risk control performance. Furthermore， Walk-Forward Expanding Window Validation is conducted to evaluate the robustness and generalization ability of the proposed approach. The results indicate that the proposed method maintains stable performance across different market conditions. Overall， the findings suggest that market microstructure and thermodynamic features can effectively enhance trading strategy performance， while the proposed Thermodynamic Risk Overlay improves risk management capability. This study provides a high-frequency trading framework that integrates market microstructure， artificial intelligence models， and risk management mechanisms， offering valuable insights for future quantitative trading and financial technology research.
