面對現今的大數據時代,資料的價值需要由資訊技術不斷創造,甚至進一步地預測資料的發展趨勢,人工智慧中的深度學習即為當今預測的最佳工具之一。本研究提出一種新形態之複數模糊類神經分類模型 (Complex Neuro-Fuzzy Classification Model, CNFC),透過複數高斯模糊集合的特性,模糊化輸入資料的類別隸屬程度,更加精確描述類別值域,增強模型的預測及應用能力。以減法分群演算法 (Subtractive Clustering Algorithm, SCA) 識別資料趨向類別,輔助模型進行動態式分類預測,其中採用粒子群最佳化演算法 (Particle Swarm Optimization, PSO) 與遞迴最小平方法 (Recursive Least Squares Estimator, RLSE) 為複合式最佳化演算法 (Hybrid optimization algorithm),針對模型不同部分的參數進行優化,將有效提升模型優化效率。實驗透過重複性與集成學習方法進行多樣化的文獻模型效能比較,驗證CNFC的預測效能與PSO-RLSE的最佳化成效於股價時間序列資料具有較佳能力。;Facing the current era of big data, the value of information is revealed constantly by information technologies, and even further predict the future trend of the data, deep learning in artificial intelligence is one of the best tools for current prediction. This study proposes a novel Complex Neuro-Fuzzy Classification Model (CNFC), through the characteristics of complex Gaussian fuzzy sets, the class degree of input data is fuzzified, which more accurately describes the class value and enhances the prediction and application ability of the model. Identify the directional classification of data by Subtractive Clustering Algorithm (SCA) and assisting models for dynamic classification prediction, the model uses Particle Swarm Optimization (PSO) and Recursive Least Squares Estimator (RLSE) as the hybrid optimization algorithm for parameters optimization of different parts of the model will effectively improve the efficiency of model optimization. The experiment verifies the predictive performance of CNFC and the optimization effect of PSO-RLSE have better ability in stock price time series data through repetitiveness and ensemble learning methods for a variety of literature model performance comparisons.