Hybrid BiLSTM-ARIMA Architecture with Whale-Driven Optimization for Financial Time Series Forecasting

作者：Panke Qin, Bo Ye, Ya Li, Zhongqi Cai, Zhenlun Gao, Haoran Qi, Yongjie Ding · 发表于：Algorithms · 年份：2025 · DOI：10.3390/a18080517 · 被引用次数：4 · 研究领域：Stock Market Forecasting Methods、Energy Load and Power Forecasting、Time Series Analysis and Forecasting

Financial time series display inherent nonlinearity and high volatility, creating substantial challenges for accurate forecasting. Advancements in artificial intelligence have positioned deep learning as a critical tool for financial time series forecasting. However, conventional deep learning models often fail to accurately predict future trends in complex financial data due to inherent limitations. To address these challenges, this study introduces a WOA-BiLSTM-ARIMA hybrid forecasting model leveraging parameter optimization. Specifically, the whale optimization algorithm (WOA) optimizes hyperparameters for the Bidirectional Long Short-Term Memory (BiLSTM) network, overcoming parameter tuning challenges in conventional approaches. Due to its strong capacity for nonlinear feature extraction, BiLSTM excels at modeling nonlinear patterns in financial time series. To mitigate the shortcomings of BiLSTM in capturing linear patterns, the Autoregressive Integrated Moving Average (ARIMA) methodology is integrated. By exploiting ARIMA’s strengths in modeling linear features, the model refines BiLSTM’s prediction residuals, achieving more accurate and comprehensive financial time series forecasting. To validate the model’s effectiveness, this paper applies it to the prediction experiment of future spread data. Compared to classical models, WOA-BiLSTM-ARIMA achieves significant improvements across multiple evaluation metrics. The mean squared error (MSE) is reduced by an average of 30...