Chen Xinying, Yang Fengjiao, Sun Qianhan, Yi Weiguo
School of Computer and Communication Engineering, Dalian Jiaotong University, 794 Huanghe Road, Shahekou District, Dalian, Liaoning, China.
School of software, Dalian Jiaotong University, 794 Huanghe Road, Shahekou District, Dalian, Liaoning, China.
Sci Rep. 2024 Nov 10;14(1):27462. doi: 10.1038/s41598-024-78984-1.
To tackle the challenge of low accuracy in stock prediction within high-noise environments, this paper innovatively introduces the CED-PSO-StockNet time series model. Initially, the model decomposes raw stock data using the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) technique and reconstructs the components by estimating their frequencies via the extreme point method. This process enhances component stability and mitigates noise interference. Subsequently, an Encoder-Decoder framework equipped with an attention mechanism is employed for precise prediction of the reconstructed components, facilitating more effective extraction and utilization of data features. Furthermore, this paper utilizes an Improved Particle Swarm Optimization (IPSO) algorithm to optimize the model parameters. On the Pudong Bank dataset, through ablation experiments and comparisons with baseline models, various optimization strategies incorporated into the proposed CED-PSO-StockNet model were effectively validated. Compared to the standalone LSTM model, CED-PSO-StockNet achieved a remarkable 45.59% improvement in the R metric. To further assess the model's generalization capability, this paper also conducted comparative experiments on the Ping An Bank dataset, and the results underscored the significant advantages of CED-PSO-StockNet in the domain of stock prediction.
为应对高噪声环境下股票预测准确率低的挑战，本文创新性地引入了CED-PSO-StockNet时间序列模型。首先，该模型使用带自适应噪声的完全集成经验模态分解（CEEMDAN）技术对原始股票数据进行分解，并通过极值点法估计其频率来重构各分量。这一过程增强了分量稳定性并减轻了噪声干扰。随后，采用配备注意力机制的编码器-解码器框架对重构后的分量进行精确预测，便于更有效地提取和利用数据特征。此外，本文利用改进粒子群优化（IPSO）算法对模型参数进行优化。在浦发银行数据集上，通过消融实验以及与基线模型的比较，有效验证了所提出的CED-PSO-StockNet模型中纳入的各种优化策略。与单独的LSTM模型相比，CED-PSO-StockNet在R指标上实现了45.59%的显著提升。为进一步评估该模型的泛化能力，本文还在平安银行数据集上进行了对比实验，结果凸显了CED-PSO-StockNet在股票预测领域的显著优势。
