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 30.5%, the mean absolute error (MAE) by 20.8%, and the mean absolute percentage error (MAPE) by 29.7%.

Due to its effectiveness as a risk-hedging trading strategy in financial markets, futures arbitrage is highly sought after by investors in turbulent market conditions. The essence of futures arbitrage lies in formulating strategies based on predictions of future futures price differentials. However, contemporary research predominantly focuses on projections of single indicators for the subsequent temporal juncture, and devising efficacious arbitrage strategies often necessitates the examination of multiple indicators across timeframes. To tackle the aforementioned challenge, our methodology leverages a PSO Deep-ConvLSTM network, which, through particle swarm optimization (PSO), refines hyperparameters, including layer architectures and learning rates, culminating in superior predictive performance. By analyzing temporal-spatial data within financial markets through ConvLSTM, the model captures intricate market patterns, performing better in forecasting than traditional models. Multistep forward simulation experiments and extensive ablation studies using future data from the Shanghai Futures Exchange in China validate the effectiveness of the integrated model. Compared with the gate recurrent unit (GRU), long short-term memory (LSTM), Transformer, and FEDformer, this model exhibits an average reduction of 39.8% in root mean squared error (RMSE), 42.5% in mean absolute error (MAE), 45.6% in mean absolute percentage error (MAPE), and an average increase of 1.96% in coefficient of determination (R2) values.

Financial Time Series Forecasting (TSF) remains a critical challenge in Artificial Intelligence (AI) due to the inherent complexity of financial data, characterized by strong non-linearity, dynamic non-stationarity, and multi-factor coupling. To address the performance limitations of Spiking Neural Networks (SNNs) caused by hyperparameter sensitivity, this study proposes an SNN model optimized by an Improved Cuckoo Search (ICS) algorithm (termed ICS-SNN). The ICS algorithm enhances global search capability through piecewise-mapping-based population initialization and introduces a dynamic discovery probability mechanism that adaptively increases with iteration rounds, thereby balancing exploration and exploitation. Applied to futures market price difference prediction, experimental results demonstrate that ICS-SNN achieves reductions of 13.82% in MAE, 21.27% in MSE, and 15.21% in MAPE, while improving the coefficient of determination (R²) from 0.9790 to 0.9822, compared to the baseline SNN. Furthermore, ICS-SNN significantly outperforms mainstream models such as Long Short-Term Memory (LSTM) and Backpropagation (BP) networks, reducing prediction errors by 10.8% (MAE) and 34.9% (MSE), respectively, without compromising computational efficiency. This work highlights that ICS-SNN provides a biologically plausible and computationally efficient framework for complex financial TSF, bridging the gap between neuromorphic principles and real-world financial analytics. The proposed method not only reduces manual intervention in hyperparameter tuning but also offers a scalable solution for high-frequency trading and multi-modal data fusion in future research.