1. Report Industry Investment Rating No relevant content provided. 2. Core View of the Report The report systematically reviews the evolution of financial time - series forecasting models and constructs a prediction model for China's 10 - year treasury bond yield using a long - short - term memory (LSTM) neural network with historical time series as the single input variable, initially exploring the application of this deep - learning model in the fixed - income quantitative field [10]. 3. Summary by Relevant Catalog 3.1 Financial Time - Series Forecasting and Neural Network Models 3.1.1 Evolution of Financial Time - Series Forecasting Models Financial time - series forecasting has gone through three main development stages: traditional econometric models, traditional machine - learning models, and deep - learning models. Traditional econometric models have clear forms and strong interpretability but struggle to depict nonlinear and complex dynamic relationships. Traditional machine - learning models can perform nonlinear fitting and automatic feature screening but need manual feature extraction. Deep - learning models can automatically extract features from raw data and capture complex long - term time - series patterns, adapting well to the complex characteristics of financial time series [11][12]. 3.1.2 Neural Network Models and LSTM Models Neural network models are machine - learning models imitating the connection structure of human brain neurons. Recurrent neural networks (RNN) and their variants, such as LSTM, are designed for processing sequence data. LSTM solves the long - term dependence problem of traditional RNN through a "gating mechanism" and memory units, enhancing robustness to irregular data and being suitable for bond yield prediction [13][18]. 3.2 Treasury Bond Yield Prediction Based on Stacked LSTM Model 3.2.1 Stacked LSTM Model Stacked LSTM connects multiple LSTM layers in sequence, having advantages in long - sequence processing and multi - dimensional feature extraction, more suitable for complex time - series forecasting in financial scenarios [23]. 3.2.2 Construction of Treasury Bond Yield Prediction Model The report uses a classic and robust architecture of three - layer stacked LSTM + Dropout regularization to build a neural network model for predicting the 10 - year treasury bond yield. It only uses the historical time series of the 10 - year treasury bond yield as a single variable for prediction. The data is from the beginning of 2021 to December 12, 2025. After data processing and sample construction, a medium - complexity LSTM neural network model with about 130,000 adjustable parameters is built. The optimal model is obtained at the 27th training iteration, with an average absolute error of 1.43BP for the test set. The predicted yield on December 19, 2025, is 1.8330%, slightly lower than 1.8396% on December 12, 2025 [2][24][30]. 3.3 Follow - up Optimization Directions - Optimize model design: Adjust and optimize the design related to time windows, data processing, network architecture, and training strategies [3][36]. - Input multi - dimensional variables: Expand input variables from a single yield sequence to multi - dimensional variables such as macro, market, and sentiment to make the model more in line with economic logic and capture more comprehensive information [3][36]. - Build hybrid models: Combine the LSTM model with traditional econometric models or other machine - learning models to build hybrid models like ARIMAX - LSTM and CNN - LSTM - ATT, enhancing prediction accuracy [3][36]. - Introduce a rolling back - testing mechanism: Use a rolling time - window back - testing mechanism to update the model dynamically and make continuous predictions, improving the model's adaptability to market changes [3][36].

Summary of the Conference Call on the Bond Market Analysis Industry Overview - The analysis focuses on the Chinese bond market, specifically the ten-year government bond yield predictions for 2025 [2][4]. Key Points and Arguments - **Yield Prediction Model**: The model decomposes the ten-year government bond yield into trend and cycle components, achieving a fitting goodness of 0.98. The predicted yields for June and December 2025 are approximately 1.91% and 1.61%, respectively [2][6]. - **Market Behavior**: The market has shown hesitation around the 1.6% yield level, influenced by macroeconomic data improvements and tightening funds. The model aims to analyze these factors to better understand current yield levels and forecast future trends [4][11]. - **CPI and PMI Correlation**: The relationship between CPI and bond market cycles has changed over time. Before 2013, CPI growth was positively correlated with bond cycles. From 2013 to 2019, PMI data became the key indicator, while post-2020, CPI showed a negative correlation with bond cycles due to monetary policy effects [8][10]. - **Interest Rate Predictions**: The model forecasts other maturities based on the ten-year yield, predicting one-year, three-year, five-year, and seven-year yields to be approximately 0.99%, 1.26%, 1.42%, and 1.59% by December 2025 [10][12]. - **Market Sentiment**: The model serves as a neutral anchor, with actual market values expected to fluctuate around this anchor. Expectations of interest rate cuts may lower yields, while rate hikes could increase them [10][11]. - **Model Reliability**: Backtesting shows the model's fitting deviation is within 10%, indicating its reliability. This deviation can help identify overly optimistic market conditions, aiding investors in adjusting strategies [3][13][15]. Additional Important Insights - **Market Dynamics**: The early 2025 market behavior has led to a pessimistic outlook, with the neutral space being consumed early in the year. A breakthrough below 1.6% will require unexpected market stimuli [11][12]. - **Investment Decision Making**: The model provides a reliable benchmark for assessing market sentiment and potential overvaluation. When market deviations exceed 10%, it signals a need for strategy adjustments [14][16]. - **Future Adjustments**: The model is a tool for judgment and should be used alongside market assessments, especially in the face of unexpected events [7][9]. This comprehensive analysis highlights the dynamics of the Chinese bond market and the predictive capabilities of the model developed by the research team.