Financial time series forecasting is crucial for high-quality economic development, but data has nonlinear, non-stationary, high noise, and multi factor driving characteristics. Traditional models (such as ARIMA) and machine learning models have limitations in complex scenarios. This study constructs a dual model system: the long-term prediction model (PatchCT) captures temporal context dependencies through sparse attention and integrates cross feature trend information through channel attention branches; The short-term prediction model (MSA xLSTM) integrates FinBERT emotion index and technical indicators (filtered by Spearman), achieves feature fusion through multi-scale emotion attention module, and combines xLSTM to establish long-range dependencies to improve short-term accuracy. The data processing adopts RevIN stationary sequence and adaptive patching to enhance local feature extraction. The backtesting verification shows that the long-term prediction strategy returns are better than the baseline, and the short-term model achieves the lowest prediction error on all four stock datasets (such as RMSE/MAE indicators being better than CNN-LSTM, GRU Attention, and other models), providing better decision support for aggressive ultra short term investors. This study forms a "long-term short-term" collaborative financial time series prediction system, promoting the practical application of the model in asset allocation, risk management and other scenarios. In the future, it will expand the joint modeling of time domain frequency domain, explore cross domain generalization ability, and deepen the analysis of multiple factors related to weak fundamental stocks, promoting the evolution of financial time series prediction towards a more universal and accurate direction.

Jingzhi Yin. Research on Financial Time Series Prediction Model Based on Multi Attention Mechanism and Emotional Feature Fusion. Socio-Economic Statistics Research (2025), Vol. 6, Issue 2: 161-169. https://doi.org/10.38007/SESR.2025.060217.

[1] Xu S, Zhang W, Tao S, et al. A Dynamic Pig Face Detection Method Based on Spatial Channel Weight Optimization Attention Mechanism and Adaptive Anchor Point Selection. Instrumentation and Measurement, IEEE Transactions on, 2025, 74(000):1-13.

[2] Huang Q, Chen J. xLSTM-FER: Enhancing Student Expression Recognition with Extended Vision Long Short-Term Memory Network. Communications in Computer and Information Science, 2025:249-259.

[3] Dai Z, Li D. MDSE-SLSTM: A Mobility-Driven Based Deep Learning Framework for Passenger Flow Distribution Forecasting in Multimodal Transportation Hub[C]//International Conference on Traffic and Transportation Studies. Springer, Singapore, 2025.

[4] Wang H, Zou D, Zhao B, et al. RDLinear: A Novel Time Series Forecasting Model Based on Decomposition with RevIN. 2024 International Joint Conference on Neural Networks (IJCNN), 2024:1-7.

[5] Qi, Y. (2025). Data Consistency and Performance Scalability Design in High-Concurrency Payment Systems. European Journal of AI, Computing & Informatics, 1(3), 39-46.

[6] Jiang, Y. (2025). Application and Practice of Machine Learning Infrastructure Optimization in Advertising Systems. Journal of Computer, Signal, and System Research, 2(6), 74-81.

[7] Zou, Y. (2025). Automated Reasoning and Technological Innovation in Cloud Computing Security. Economics and Management Innovation, 2(6), 25-32.

[8] An, C. (2025). Study on Efficiency Improvement of Data Analysis in Customer Asset Allocatior. Journal of Computer, Signal, and System Research, 2(6), 57-65.

[9] Huang, J. (2025). Optimization and Innovation of AI-Based E-Commerce Platform Recommendation System. Journal of Computer, Signal, and System Research, 2(6), 66-73.

[10] Zhang, X. (2025). Optimization of Financial Fraud Risk Identification System Based on Machine Learning. Journal of Computer, Signal, and System Research, 2(6), 82-89.

[11] Wang, Y. (2025). Exploration and Clinical Practice of the Optimization Path of Sports Rehabilitation Technology. Journal of Medicine and Life Sciences, 1(3), 88-94.

[12] Li W. The Influence of Financial Due Diligence in M&A on Investment Decision Based on Financial Data Analysis. European Journal of AI, Computing & Informatics, 2025, 1(3): 32-38.

[13] Sheng, C. (2025). Innovative Application and Effect Evaluation of Big Data in Cross-Border Tax Compliance Management. Journal of Computer, Signal, and System Research, 2(6), 40-48.

[14] Sheng, C. (2025). Research on the Application of AI in Enterprise Financial Risk Management and Its Optimization Strategy. Economics and Management Innovation, 2(6), 18-24.

[15] Tu, X. (2025). Optimization Strategy for Personalized Recommendation System Based on Data Analysis. Journal of Computer, Signal, and System Research, 2(6), 32-39.

[16] Zhu, Z. (2025). Cutting-Edge Challenges and Solutions for the Integration of Vector Database and AI Technology. European Journal of AI, Computing & Informatics, 1(2), 51-57.

[17] Lai L. Data-Driven Credit Risk Assessment and Optimization Strategy Exploration. European Journal of Business, Economics & Management, 2025, 1(3): 24-30.

[18] Chang, Chen-Wei. "Compiling Declarative Privacy Policies into Runtime Enforcement for Cloud and Web Infrastructure. " (2025).

[19] Sun, Jiahe. "Research on Sentiment Analysis Based on Multi-source Data Fusion and Pre-trained Model Optimization in Quantitative Finance. " (2025).

[20] Huang, J. (2025). Promoting Cross-field E-Commerce Development by Combining Educational Background and Technology. Economics and Management Innovation, 2(4), 26-32.