- The report highlights the strong performance of high-frequency factors, with notable multi-granularity factor returns and differentiated excess returns in AI-enhanced portfolios [6][10][11] - High-frequency factors such as intraday skewness, downside volatility proportion, and opening buy intention proportion recorded significant multi-long-short returns and excess returns across weekly, monthly, and YTD periods [6][10][11] - Multi-granularity models (5-day and 10-day labels) achieved robust multi-long-short returns, with the 5-day label model yielding 0.91% (weekly), 2.6% (monthly), and 10.22% (YTD), while the 10-day label model delivered 0.71% (weekly), 3.06% (monthly), and 8.9% (YTD) [6][10][11] - AI-enhanced portfolios, including the Air Index Increment and CSI 500/1000 AI Enhanced portfolios, demonstrated varying excess and absolute returns under both wide and strict constraints, with weekly and daily rebalancing strategies [6][15][73] - The optimization objective for AI-enhanced portfolios is to maximize expected returns, represented by the function: $$max\sum\mu_{i}w_{i}$$ where \(w_i\) is the weight of stock \(i\) in the portfolio, and \(\mu_i\) is the expected excess return of stock \(i\) [75][76]

Investment Rating - The report indicates an overall strong performance in high-frequency trading factors, with various multi-granularity factors maintaining positive returns [2][3]. Core Insights - High-frequency trading factors exhibited excellent performance, with daily high-frequency skew factors showing long-short returns of 0.49% for the last week, 0.31% for February, and 4.31% for the year 2026 [9]. - The AI-enhanced portfolio has experienced continuous excess drawdown, indicating potential areas for improvement in strategy [2][3]. Summary by Sections High-Frequency Factors and Deep Learning Factors Performance - Daily high-frequency skew factor returns were 0.49% last week, 0.31% in February, and 4.31% year-to-date [11]. - Daily downside volatility factor returns were 0.23%, 1.06%, and 5.81% respectively [11]. - The opening buy intention ratio factor showed returns of 0.01%, -0.90%, and 2.97% [11]. - The opening large net buy ratio factor had returns of 0.73%, 2.26%, and 4.81% [11]. - The average single outflow amount factor showed returns of -0.56%, -1.33%, and -2.89% [11]. AI Enhanced Portfolio Performance - Weekly rebalancing of the AI-enhanced portfolio showed excess/absolute returns of -1.13%/2.25%, 1.34%/5.23%, and 3.74%/15.79% for the last week, February, and year-to-date respectively [14]. - The CSI 500 AI enhanced portfolio with wide constraints showed excess/absolute returns of -2.69%/1.63%, -1.14%/2.30%, and -3.99%/11.99% [14]. - The CSI 1000 AI enhanced portfolio with strict constraints showed excess/absolute returns of -1.03%/3.31%, 0.06%/3.76%, and 0.86%/13.57% [14]. Multi-Granularity Factor Analysis - Multi-granularity models (5-day label) showed long-short returns of 0.22%, 2.13%, and 7.62% [11]. - Multi-granularity models (10-day label) showed long-short returns of -0.37%, 1.76%, and 5.83% [11]. - The deep learning high-frequency factors demonstrated varying performance, with the improved GRU and LSTM models showing positive returns in different time frames [11][12].

Quantitative Models and Construction Methods - **Model Name**: Dimension Matching Factor **Construction Idea**: The calculation process of high-frequency factors can be divided into several steps of data transformation and K-line aggregation. Dimension matching factors are derived from the final step of matching K-line operators, which aggregate data across multiple dimensions[3][6][55] **Construction Process**: 1. Data transformation: Apply function mapping to transaction information for local processing 2. K-line aggregation: Aggregate data at a certain frequency to reduce high-frequency data to low-frequency data 3. Use residual volatility operators to aggregate transaction volume and transaction amount proportions, constructing transaction matching volatility factors[6][55][59] **Evaluation**: Compared to deep learning, this method focuses on local information. Compared to genetic algorithms, it better corresponds to sources of returns[6][55][84] Model Backtesting Results - **Dimension Matching Factor**: - IC values after neutralizing market capitalization and industry: 3.81% (CSI 300), 3.63% (CSI 500), 4.25% (CSI 1000), 4.15% (CSI All Index)[84] - Annualized excess returns: 5.05% (CSI 300), 3.53% (CSI 500), 5.00% (CSI 1000), 5.77% (CSI All Index)[84] Quantitative Factors and Construction Methods - **Factor Name**: Residual Volatility Factors **Construction Idea**: Derived from residual volatility logic, focusing on price stability and transaction volume volatility[7][35][55] **Construction Process**: 1. High-frequency residual volatility: Time-series regression residual volatility of individual stock returns and three-factor returns at 30-minute frequency 2. Residual transaction volume volatility: Time-series regression residual volatility of individual stock transaction proportions and market transaction proportions 3. Residual amplitude volatility: Time-series regression residual volatility of individual stock amplitude and market amplitude (CSI All Index)[35][55][59] **Evaluation**: These factors belong to low-volatility return sources and have relatively low correlation with other factors, providing incremental information[35][36][55] Factor Backtesting Results - **Residual Volatility Factors**: - IC values after neutralizing market capitalization and industry: 5.76% (Residual Transaction Volume Volatility), 7.55% (Residual Amplitude Volatility)[7][43][48] - Annualized excess returns: 4.65% (Residual Transaction Volume Volatility), 5.25% (Residual Amplitude Volatility)[7][43][48] - IC values after neutralizing market capitalization, industry, volatility, and turnover: 4.02% (Residual Transaction Volume Volatility), 2.67% (Residual Amplitude Volatility)[7][43][48] - Annualized excess returns after further neutralization: 2.74% (Residual Transaction Volume Volatility), 0.45% (Residual Amplitude Volatility)[7][43][48] - **Factor Name**: Transaction Matching Volatility Factor **Construction Idea**: Derived from dimension matching logic, aggregating transaction volume and transaction amount proportions across multiple dimensions[55][59][84] **Construction Process**: 1. Per transaction volume: Matching transformation operator—division (transaction volume, transaction count) 2. Total transaction volume: Time-series K-line operator—summation (transaction volume) 3. Transaction volume proportion: Matching transformation operator—division (transaction volume, total transaction volume) 4. Transaction matching volatility: Matching K-line operator—regression residual volatility (per transaction volume, transaction volume proportion)[55][59][84] **Evaluation**: This factor mainly correlates with volatility and turnover rate factors, indicating low-volatility return sources and a bias towards small-cap stocks[55][58][61] Factor Backtesting Results - **Transaction Matching Volatility Factor**: - IC values after neutralizing market capitalization and industry: 5.35% (CSI 300), 6.01% (CSI 500), 7.31% (CSI 1000), 7.55% (CSI All Index)[65][68][84] - Annualized excess returns: 5.05% (CSI 300), 3.53% (CSI 500), 5.00% (CSI 1000), 5.77% (CSI All Index)[65][68][84] - IC values after neutralizing market capitalization, industry, volatility, and turnover: 3.81% (CSI 300), 3.63% (CSI 500), 4.25% (CSI 1000), 4.15% (CSI All Index)[65][68][84] - Annualized excess returns after further neutralization: 2.74% (CSI 300), 2.38% (CSI 500), 2.04% (CSI 1000), 2.74% (CSI All Index)[65][68][84]

Quantitative Models and Construction Methods 1. Model Name: High-frequency "Gold" Portfolio CSI 1000 Index Enhanced Strategy - **Model Construction Idea**: This strategy combines three categories of high-frequency factors (price range, price-volume divergence, regret avoidance) equally weighted to enhance the CSI 1000 Index. It aims to leverage high-frequency data to capture microstructure insights and improve stock selection performance[4][38][39] - **Model Construction Process**: 1. Combine the three high-frequency factors (price range, price-volume divergence, regret avoidance) with equal weights (25%, 25%, 50%) 2. Apply industry and market capitalization neutralization to the combined factor 3. Implement weekly rebalancing with a transaction cost rate of 0.2% per side 4. Introduce turnover buffering mechanisms to reduce transaction costs[14][38][39] - **Model Evaluation**: The strategy demonstrates strong out-of-sample performance with stable excess returns, though it has experienced some recent adjustments[42] 2. Model Name: High-frequency & Fundamental Resonance Portfolio CSI 1000 Index Enhanced Strategy - **Model Construction Idea**: This strategy integrates high-frequency factors with fundamental factors (consensus expectations, growth, and technical factors) to improve multi-factor portfolio performance. The low correlation between high-frequency and traditional fundamental factors enhances diversification[43][45] - **Model Construction Process**: 1. Combine the three high-frequency factors and three fundamental factors equally weighted 2. Apply industry and market capitalization neutralization to the combined factor 3. Implement weekly rebalancing with a transaction cost rate of 0.2% per side 4. Introduce turnover buffering mechanisms to reduce transaction costs[43][45] - **Model Evaluation**: The strategy shows improved performance metrics compared to the high-frequency-only strategy, with higher annualized returns and lower maximum drawdowns[45][47] --- Model Backtesting Results 1. High-frequency "Gold" Portfolio CSI 1000 Index Enhanced Strategy - Annualized Return: 10.56% - Annualized Volatility: 23.75% - Sharpe Ratio: 0.44 - Maximum Drawdown: 47.77% - Annualized Excess Return: 9.58% - Tracking Error: 4.36% - Information Ratio (IR): 2.20 - Maximum Excess Drawdown: 6.53%[39] 2. High-frequency & Fundamental Resonance Portfolio CSI 1000 Index Enhanced Strategy - Annualized Return: 14.80% - Annualized Volatility: 23.39% - Sharpe Ratio: 0.63 - Maximum Drawdown: 39.60% - Annualized Excess Return: 13.70% - Tracking Error: 4.23% - Information Ratio (IR): 3.24 - Maximum Excess Drawdown: 4.97%[45] --- Quantitative Factors and Construction Methods 1. Factor Name: Price Range Factor - **Factor Construction Idea**: Measures the activity of stock transactions in different intraday price ranges, reflecting investor expectations for future stock trends[3] - **Factor Construction Process**: 1. Use 3-second snapshot data to calculate transaction volume and count in high (80%) and low (10%) price ranges 2. Construct sub-factors: - High price range transaction volume factor (VH80TAW) - High price range transaction count factor (MIH80TAW) - Low price range average transaction volume factor (VPML10TAW) 3. Combine sub-factors with weights of 25%, 25%, and 50%, respectively 4. Apply industry and market capitalization neutralization[11][14][16] - **Factor Evaluation**: Demonstrates strong predictive power and stable performance out-of-sample[3][16] 2. Factor Name: Price-Volume Divergence Factor - **Factor Construction Idea**: Measures the correlation between stock price and trading volume. Lower correlation indicates higher potential for future price increases[3][19] - **Factor Construction Process**: 1. Use high-frequency snapshot data to calculate correlations: - Price and transaction count correlation (CorrPM) - Price and transaction volume correlation (CorrPV) 2. Combine sub-factors equally weighted 3. Apply industry and market capitalization neutralization[19][22][23] - **Factor Evaluation**: Performance has declined since 2020 due to widespread adoption but remains stable with positive excess returns in 2023[23] 3. Factor Name: Regret Avoidance Factor - **Factor Construction Idea**: Based on behavioral finance, this factor captures investor regret avoidance emotions, such as the impact of selling stocks that later rebound[3][24] - **Factor Construction Process**: 1. Use tick-by-tick transaction data to identify active buy/sell directions 2. Construct sub-factors: - Sell rebound proportion factor (LCVOLESW) - Sell rebound deviation factor (LCPESW) 3. Combine sub-factors equally weighted 4. Apply industry and market capitalization neutralization[24][28][30] - **Factor Evaluation**: Exhibits stable out-of-sample performance, indicating significant influence of regret avoidance on stock returns[31] 4. Factor Name: Slope Convexity Factor - **Factor Construction Idea**: Captures the impact of order book slope and convexity on expected returns, reflecting investor patience and supply-demand elasticity[3][32] - **Factor Construction Process**: 1. Calculate order book slope using cumulative order volume and price at different levels 2. Construct sub-factors: - Low-level slope factor (Slope_abl) - High-level convexity factor (Slope_alh) 3. Combine sub-factors equally weighted 4. Apply industry and market capitalization neutralization[32][35][37] - **Factor Evaluation**: Performance has been stable since 2016, though recent results are relatively flat[35] --- Factor Backtesting Results 1. Price Range Factor - Annualized Excess Return: 3.24% (VH80TAW), 4.45% (MIH80TAW), -0.77% (VPML10TAW)[12][14][16] 2. Price-Volume Divergence Factor - Annualized Excess Return: 2.56% (CorrPM), 2.61% (CorrPV)[19][22][23] 3. Regret Avoidance Factor - Annualized Excess Return: -2.67% (LCVOLESW), 0.33% (LCPESW)[24][26][31] 4. Slope Convexity Factor - Annualized Excess Return: -2.35% (Slope_abl), 0.02% (Slope_alh)[34][35][37]

- The "Buy Intention Factor" showed strong performance at the beginning of the year, with intraday high-frequency skewness factor, intraday downside volatility proportion factor, post-opening buy intention proportion factor, post-opening buy intention strength factor, post-opening large order net buy proportion factor, post-opening large order net buy strength factor, intraday return factor, end-of-day trading proportion factor, average single outflow amount proportion factor, and large order push-up factor all being evaluated[5][6][9] - The "Multi-Granularity Factor" showed average performance, with GRU(10,2)+NN(10) factor, GRU(50,2)+NN(10) factor, multi-granularity model (5-day label) factor, and multi-granularity model (10-day label) factor being evaluated[5][6][9] - The "AI Enhanced Portfolio" had a poor start to the year, with significant drawdowns observed in the weekly rebalanced CSI 500 AI enhanced wide constraint portfolio, CSI 500 AI enhanced strict constraint portfolio, CSI 1000 AI enhanced wide constraint portfolio, and CSI 1000 AI enhanced strict constraint portfolio[5][6][9] Quantitative Factors and Construction Methods 1. **Factor Name: Intraday High-Frequency Skewness Factor** - **Construction Idea**: Measures the skewness of intraday returns to capture the asymmetry in return distribution[5][6] - **Construction Process**: Calculated using high-frequency data to determine the skewness of returns within a trading day[5][6] - **Evaluation**: Demonstrated strong performance at the beginning of the year[5][6] 2. **Factor Name: Intraday Downside Volatility Proportion Factor** - **Construction Idea**: Measures the proportion of downside volatility in intraday returns[5][6] - **Construction Process**: Calculated using high-frequency data to determine the proportion of downside volatility within a trading day[5][6] - **Evaluation**: Showed moderate performance[5][6] 3. **Factor Name: Post-Opening Buy Intention Proportion Factor** - **Construction Idea**: Measures the proportion of buy intentions after market opening[5][6] - **Construction Process**: Calculated using high-frequency data to determine the proportion of buy intentions after the market opens[5][6] - **Evaluation**: Demonstrated strong performance at the beginning of the year[5][6] 4. **Factor Name: Post-Opening Buy Intention Strength Factor** - **Construction Idea**: Measures the strength of buy intentions after market opening[5][6] - **Construction Process**: Calculated using high-frequency data to determine the strength of buy intentions after the market opens[5][6] - **Evaluation**: Showed moderate performance[5][6] 5. **Factor Name: Post-Opening Large Order Net Buy Proportion Factor** - **Construction Idea**: Measures the proportion of net buy orders of large size after market opening[5][6] - **Construction Process**: Calculated using high-frequency data to determine the proportion of net buy orders of large size after the market opens[5][6] - **Evaluation**: Demonstrated weak performance[5][6] 6. **Factor Name: Post-Opening Large Order Net Buy Strength Factor** - **Construction Idea**: Measures the strength of net buy orders of large size after market opening[5][6] - **Construction Process**: Calculated using high-frequency data to determine the strength of net buy orders of large size after the market opens[5][6] - **Evaluation**: Showed weak performance[5][6] 7. **Factor Name: Intraday Return Factor** - **Construction Idea**: Measures the return within a trading day[5][6] - **Construction Process**: Calculated using high-frequency data to determine the return within a trading day[5][6] - **Evaluation**: Demonstrated strong performance at the beginning of the year[5][6] 8. **Factor Name: End-of-Day Trading Proportion Factor** - **Construction Idea**: Measures the proportion of trading activity at the end of the day[5][6] - **Construction Process**: Calculated using high-frequency data to determine the proportion of trading activity at the end of the day[5][6] - **Evaluation**: Showed strong performance[5][6] 9. **Factor Name: Average Single Outflow Amount Proportion Factor** - **Construction Idea**: Measures the proportion of average single outflow amounts[5][6] - **Construction Process**: Calculated using high-frequency data to determine the proportion of average single outflow amounts[5][6] - **Evaluation**: Demonstrated moderate performance[5][6] 10. **Factor Name: Large Order Push-Up Factor** - **Construction Idea**: Measures the impact of large orders on price increases[5][6] - **Construction Process**: Calculated using high-frequency data to determine the impact of large orders on price increases[5][6] - **Evaluation**: Showed moderate performance[5][6] 11. **Factor Name: GRU(10,2)+NN(10) Factor** - **Construction Idea**: Combines GRU and neural network models to capture complex patterns in data[5][6] - **Construction Process**: Utilizes GRU with 10 units and 2 layers, followed by a neural network with 10 units[5][6] - **Evaluation**: Demonstrated average performance[5][6] 12. **Factor Name: GRU(50,2)+NN(10) Factor** - **Construction Idea**: Combines GRU and neural network models to capture complex patterns in data[5][6] - **Construction Process**: Utilizes GRU with 50 units and 2 layers, followed by a neural network with 10 units[5][6] - **Evaluation**: Showed weak performance[5][6] 13. **Factor Name: Multi-Granularity Model (5-Day Label) Factor** - **Construction Idea**: Uses multi-granularity approach to capture patterns over different time frames[5][6] - **Construction Process**: Trained using a 5-day label to capture short-term patterns[5][6] - **Evaluation**: Demonstrated average performance[5][6] 14. **Factor Name: Multi-Granularity Model (10-Day Label) Factor** - **Construction Idea**: Uses multi-granularity approach to capture patterns over different time frames[5][6] - **Construction Process**: Trained using a 10-day label to capture longer-term patterns[5][6] - **Evaluation**: Showed weak performance[5][6] Factor Backtest Results 1. **Intraday High-Frequency Skewness Factor**: IC -0.007, e^(-rank mae) 0.312, long-short return 0.29%, long-only excess return 0.99%, monthly win rate 1/1[9][10] 2. **Intraday Downside Volatility Proportion Factor**: IC -0.001, e^(-rank mae) 0.313, long-short return 0.22%, long-only excess return 0.95%, monthly win rate 1/1[9][10] 3. **Post-Opening Buy Intention Proportion Factor**: IC 0.032, e^(-rank mae) 0.324, long-short return 1.04%, long-only excess return -0.41%, monthly win rate 0/1[9][10] 4. **Post-Opening Buy Intention Strength Factor**: IC 0.027, e^(-rank mae) 0.323, long-short return 0.65%, long-only excess return 0.62%, monthly win rate 1/1[9][10] 5. **Post-Opening Large Order Net Buy Proportion Factor**: IC -0.006, e^(-rank mae) 0.306, long-short return -0.52%, long-only excess return -0.53%, monthly win rate 0/1[9][10] 6. **Post-Opening Large Order Net Buy Strength Factor**: IC 0.004, e^(-rank mae) 0.308, long-short return -0.07%, long-only excess return -0.66%, monthly win rate 0/1[9][10] 7. **Intraday Return Factor**: IC 0.037, e^(-rank mae) 0.328, long-short return 1.77%, long-only excess return 1.89%, monthly win rate 1/1[9][10] 8. **End-of-Day Trading Proportion Factor**: IC 0.084, e^(-rank mae) 0.334, long-short return 2.67%, long-only excess return 1.35%, monthly win rate 1/1[9][10] 9. **Average Single Outflow Amount Proportion Factor**: IC 0.013, e^(-rank mae) 0.319, long-short return 0.45%, long-only excess return 0.14%, monthly win rate 1/1[9][10] 10. **Large Order Push-Up Factor**: IC -0.007, e^(-rank mae) 0.327, long-short return 0.22%, long-only excess return 0.43%, monthly win rate 1/1[9][10] 11. **GRU(10,2

Quantitative Models and Construction Methods 1. Model Name: High-frequency "Gold" Combination CSI 1000 Index Enhanced Strategy - **Model Construction Idea**: This model combines three types of high-frequency factors (price range, price-volume divergence, and regret avoidance) with equal weights to enhance the CSI 1000 Index. It aims to leverage the predictive power of high-frequency factors for stock selection[3][62][66] - **Model Construction Process**: 1. Combine the three high-frequency factors (price range, price-volume divergence, and regret avoidance) with weights of 25%, 25%, and 50%, respectively[36][42][51] 2. Neutralize the combined factor by industry market capitalization[36][42][51] 3. Implement weekly rebalancing with a turnover buffer mechanism to reduce transaction costs[62][66] - **Model Evaluation**: The model demonstrates strong excess return performance both in-sample and out-of-sample, with a stable upward trend in the net value curve[39][66] 2. Model Name: High-frequency & Fundamental Resonance Combination CSI 1000 Index Enhanced Strategy - **Model Construction Idea**: This model integrates high-frequency factors with fundamental factors (consensus expectations, growth, and technical factors) to improve the performance of multi-factor investment portfolios[67][69] - **Model Construction Process**: 1. Combine the three high-frequency factors (price range, price-volume divergence, and regret avoidance) with fundamental factors (consensus expectations, growth, and technical factors) using equal weights[67][69] 2. Neutralize the combined factor by industry market capitalization[67][69] 3. Implement weekly rebalancing with a turnover buffer mechanism to reduce transaction costs[67][69] - **Model Evaluation**: The model shows improved performance metrics compared to the high-frequency-only strategy, with higher annualized returns and Sharpe ratios[69][71] --- Model Backtesting Results 1. High-frequency "Gold" Combination CSI 1000 Index Enhanced Strategy - Annualized Return: 9.63% - Annualized Volatility: 23.82% - Sharpe Ratio: 0.40 - Maximum Drawdown: 47.77% - Annualized Excess Return: 9.85% - Tracking Error: 4.32% - IR: 2.28 - Maximum Excess Drawdown: 6.04%[63][66] 2. High-frequency & Fundamental Resonance Combination CSI 1000 Index Enhanced Strategy - Annualized Return: 13.80% - Annualized Volatility: 23.44% - Sharpe Ratio: 0.59 - Maximum Drawdown: 39.60% - Annualized Excess Return: 13.93% - Tracking Error: 4.20% - IR: 3.31 - Maximum Excess Drawdown: 4.52%[69][71] --- Quantitative Factors and Construction Methods 1. Factor Name: Price Range Factor - **Factor Construction Idea**: Measures the activity of stock transactions in different price ranges during the day, reflecting investors' expectations of future stock trends[3][33] - **Factor Construction Process**: 1. Use high-frequency snapshot data to calculate transaction volume and number of transactions in high (80%) and low (10%) price ranges[33][36] 2. Combine sub-factors with weights of 25%, 25%, and 50%[36] 3. Neutralize the combined factor by industry market capitalization[36] - **Factor Evaluation**: The factor shows strong predictive power and stable performance, with a steadily upward excess net value curve[39] 2. Factor Name: Price-Volume Divergence Factor - **Factor Construction Idea**: Measures the correlation between stock price and trading volume. Lower correlation indicates a higher probability of future price increases[3][40] - **Factor Construction Process**: 1. Use high-frequency snapshot data to calculate the correlation between price and trading volume, as well as price and transaction count[40][42] 2. Combine sub-factors with equal weights[42] 3. Neutralize the combined factor by industry market capitalization[42] - **Factor Evaluation**: The factor's performance has been relatively flat in recent years but has shown good excess return this year[44] 3. Factor Name: Regret Avoidance Factor - **Factor Construction Idea**: Based on behavioral finance, this factor captures investors' regret avoidance emotions, such as the impact of selling stocks that later rebound[3][46] - **Factor Construction Process**: 1. Use tick-by-tick transaction data to identify active buy/sell directions[46] 2. Construct sub-factors like sell rebound ratio and sell rebound deviation, and apply restrictions on small orders and closing trades[46] 3. Combine sub-factors with equal weights and neutralize by industry market capitalization[46][51] - **Factor Evaluation**: The factor shows stable upward performance and strong excess return levels out-of-sample[53] 4. Factor Name: Slope Convexity Factor - **Factor Construction Idea**: Captures the impact of order book slope and convexity on expected returns, reflecting investor patience and supply-demand elasticity[3][54] - **Factor Construction Process**: 1. Use order book data to calculate the slope of buy and sell orders at different levels[54] 2. Construct sub-factors for low-level slope and high-level convexity, and combine them[54][58] 3. Neutralize the combined factor by industry market capitalization[58] - **Factor Evaluation**: The factor has shown stable performance since 2016, with relatively flat out-of-sample results[61] --- Factor Backtesting Results 1. Price Range Factor - Annualized Excess Return: 4.90% - IR: 1.13 - Maximum Excess Drawdown: 1.89%[36][39] 2. Price-Volume Divergence Factor - Annualized Excess Return: 5.59% - IR: 1.29 - Maximum Excess Drawdown: 2.13%[42][44] 3. Regret Avoidance Factor - Annualized Excess Return: -2.62% - IR: -0.61 - Maximum Excess Drawdown: 1.69%[46][53] 4. Slope Convexity Factor - Annualized Excess Return: -10.40% - IR: -2.35 - Maximum Excess Drawdown: 2.42%[58][61]

- The high-frequency skewness factor had long-short returns of 0.67% last week, -1.18% in December, and 22.39% year-to-date 2025[5] - The intraday downside volatility factor had long-short returns of 0.87% last week, -1.33% in December, and 19.08% year-to-date 2025[5] - The post-open buying intention proportion factor had long-short returns of 0.66% last week, 0.61% in December, and 21.12% year-to-date 2025[5] - The post-open buying intention intensity factor had long-short returns of 0.46% last week, 0.94% in December, and 28.09% year-to-date 2025[5] - The post-open large order net buying proportion factor had long-short returns of -0.21% last week, 0.17% in December, and 22.11% year-to-date 2025[5] - The post-open large order net buying intensity factor had long-short returns of -0.25% last week, 0.38% in December, and 12.5% year-to-date 2025[5] - The intraday return factor had long-short returns of 0.35% last week, 0.91% in December, and 22.33% year-to-date 2025[5] - The end-of-day trading proportion factor had long-short returns of -0.94% last week, 1.04% in December, and 16.73% year-to-date 2025[5] - The average single transaction outflow proportion factor had long-short returns of -1.15% last week, -2.15% in December, and -8.11% year-to-date 2025[5] - The large order push-up factor had long-short returns of 0.41% last week, -0.93% in December, and 7.19% year-to-date 2025[5] - The GRU(10,2)+NN(10) factor had long-short returns of 1.13% last week, -0.47% in December, and 47.04% year-to-date 2025, with long-only excess returns of -0.2% last week, -0.26% in December, and 7.1% year-to-date 2025[5] - The GRU(50,2)+NN(10) factor had long-short returns of 1.66% last week, 0.19% in December, and 47.39% year-to-date 2025, with long-only excess returns of 0.15% last week, 0.06% in December, and 8.92% year-to-date 2025[5] - The multi-granularity model (5-day label) factor had long-short returns of 2.46% last week, 1.12% in December, and 68.13% year-to-date 2025, with long-only excess returns of 0.74% last week, -0.18% in December, and 24.48% year-to-date 2025[5] - The multi-granularity model (10-day label) factor had long-short returns of 2.26% last week, 1.11% in December, and 62.71% year-to-date 2025, with long-only excess returns of 0.76% last week, -0.5% in December, and 24.3% year-to-date 2025[5] - The weekly rebalanced CSI 500 AI-enhanced wide constraint portfolio had excess returns of 0.41% last week, -2.64% in December, and 5.46% year-to-date 2025[5] - The weekly rebalanced CSI 500 AI-enhanced strict constraint portfolio had excess returns of 0.92% last week, -1.62% in December, and 9.23% year-to-date 2025[5] - The weekly rebalanced CSI 1000 AI-enhanced wide constraint portfolio had excess returns of 1.55% last week, -2.69% in December, and 15.39% year-to-date 2025[5] - The weekly rebalanced CSI 1000 AI-enhanced strict constraint portfolio had excess returns of 1.48% last week, -1.45% in December, and 19.02% year-to-date 2025[5]

- The report tracks the performance of high-frequency stock selection factors, including Price Range Factor, Price-Volume Divergence Factor, Regret Avoidance Factor, and Slope Convexity Factor. These factors are evaluated based on their excess returns and predictive capabilities[2][3][11] - **Price Range Factor**: This factor measures the activity of stock transactions in different price ranges during the day, reflecting investors' expectations for future stock trends. It includes sub-factors such as high-price range transaction volume (VH80TAW), high-price range transaction count (MIH80TAW), and low-price range average transaction volume (VPML10TAW). The factor shows a strong predictive effect and stable performance this year[3][12][14] - **Price-Volume Divergence Factor**: This factor evaluates the correlation between stock prices and trading volumes. A lower correlation indicates a higher likelihood of future price increases. Sub-factors include price-to-transaction count correlation (CorrPM) and price-to-volume correlation (CorrPV). The factor has shown relatively stable performance this year, despite a declining trend since 2020[3][20][22] - **Regret Avoidance Factor**: Based on behavioral finance, this factor examines the proportion and degree of stock price rebounds after being sold by investors. Sub-factors include sell-rebound proportion (LCVOLESW) and sell-rebound deviation (LCPESW). The factor demonstrates stable out-of-sample excess returns, indicating that regret avoidance sentiment significantly impacts stock price expectations[3][23][31] - **Slope Convexity Factor**: Derived from the elasticity of supply and demand, this factor uses order book data to calculate the slope and convexity of buy and sell orders. Sub-factors include low-level slope (Slope_abl) and high-level convexity (Slope_alh). The factor's performance has been relatively flat in recent years, with some fluctuations in recent weeks[3][32][35] - The report constructs two enhanced strategies: the "High-Frequency Gold" portfolio and the "High-Frequency & Fundamental Resonance" portfolio. The "High-Frequency Gold" portfolio combines the three high-frequency factors with equal weights, achieving an annualized excess return of 10.11% and an IR of 2.36. The "High-Frequency & Fundamental Resonance" portfolio integrates high-frequency factors with fundamental factors (e.g., consensus expectations, growth, and technical factors), achieving an annualized excess return of 14.21% and an IR of 3.39[3][39][44] - **Performance Metrics for High-Frequency Gold Portfolio**: Annualized return: 9.49%, Annualized volatility: 23.87%, Sharpe ratio: 0.40, Maximum drawdown: 47.77%, Annualized excess return: 10.11%, IR: 2.36, Maximum excess drawdown: 6.04%[40][43] - **Performance Metrics for High-Frequency & Fundamental Resonance Portfolio**: Annualized return: 13.66%, Annualized volatility: 23.49%, Sharpe ratio: 0.58, Maximum drawdown: 39.60%, Annualized excess return: 14.21%, IR: 3.39, Maximum excess drawdown: 4.52%[47][48]

Core Insights - The report indicates a general rebound in high-frequency factors, with significant improvement in multi-granularity factor long positions, and AI-enhanced portfolios showing stable performance with positive returns across multiple combinations [2][5]. High-Frequency Factors and Deep Learning Factors Summary - High-frequency skew factor returns for the last week, November, and 2025 YTD are 1.93%, 1.29%, and 23.56% respectively [5][10]. - Downward volatility proportion factor returns for the last week, November, and 2025 YTD are 1.63%, 1.44%, and 20.42% respectively [5][10]. - Opening buy intention proportion factor returns for the last week, November, and 2025 YTD are 1.21%, 1.17%, and 20.51% respectively [5][10]. - Opening buy intention strength factor returns for the last week, November, and 2025 YTD are 1.17%, 1.36%, and 27.15% respectively [5][10]. - Opening large order net buy proportion factor returns for the last week, November, and 2025 YTD are 1.35%, 1.00%, and 21.94% respectively [5][10]. - Opening large order net buy strength factor returns for the last week, November, and 2025 YTD are 0.97%, -0.49%, and 12.12% respectively [5][10]. - Daily return factor for the last week, November, and 2025 YTD is 0.01%, -0.60%, and 21.42% respectively [5][10]. - End-of-day transaction proportion factor returns for the last week, November, and 2025 YTD are 1.64%, -0.07%, and 15.70% respectively [5][10]. - Average single outflow amount proportion factor returns for the last week, November, and 2025 YTD are 0.02%, -2.91%, and -5.96% respectively [5][10]. - Large order driving increase factor returns for the last week, November, and 2025 YTD are -0.34%, -0.49%, and 8.12% respectively [5][10]. AI Enhanced Portfolio Performance - The weekly rebalancing of the CSI 500 AI enhanced wide constraint portfolio shows excess returns of -0.08%, 4.36%, and 8.33% for the last week, November, and 2025 YTD respectively [5][13]. - The weekly rebalancing of the CSI 500 AI enhanced strict constraint portfolio shows excess returns of 0.19%, 2.75%, and 11.02% for the last week, November, and 2025 YTD respectively [5][13]. - The weekly rebalancing of the CSI 1000 AI enhanced wide constraint portfolio shows excess returns of 0.11%, 4.58%, and 18.58% for the last week, November, and 2025 YTD respectively [5][13]. - The weekly rebalancing of the CSI 1000 AI enhanced strict constraint portfolio shows excess returns of 0.11%, 1.93%, and 20.77% for the last week, November, and 2025 YTD respectively [5][13].

Quantitative Models and Construction Methods Model Name: GRU(10,2)+NN(10) - **Model Construction Idea**: This model combines Gated Recurrent Units (GRU) with a neural network (NN) to capture temporal dependencies in high-frequency data[4] - **Model Construction Process**: The model uses a GRU with 10 units and 2 layers, followed by a neural network with 10 units. The GRU processes sequential data, and the NN captures non-linear relationships[4] - **Model Evaluation**: The model shows strong performance in capturing temporal patterns and generating significant returns[4] Model Name: GRU(50,2)+NN(10) - **Model Construction Idea**: Similar to the GRU(10,2)+NN(10) model but with more GRU units to capture more complex temporal dependencies[4] - **Model Construction Process**: The model uses a GRU with 50 units and 2 layers, followed by a neural network with 10 units. This setup allows for deeper temporal feature extraction[4] - **Model Evaluation**: The model is effective in capturing complex temporal patterns and generating significant returns[4] Model Name: Multi-Granularity Model (5-day label) - **Model Construction Idea**: This model uses multiple granularities of data to improve prediction accuracy[4] - **Model Construction Process**: The model labels data with a 5-day horizon and uses a combination of features from different time scales to enhance prediction[4] - **Model Evaluation**: The model shows strong performance in capturing multi-scale patterns and generating significant returns[4] Model Name: Multi-Granularity Model (10-day label) - **Model Construction Idea**: Similar to the 5-day label model but with a 10-day horizon to capture longer-term dependencies[4] - **Model Construction Process**: The model labels data with a 10-day horizon and combines features from different time scales to enhance prediction[4] - **Model Evaluation**: The model is effective in capturing longer-term patterns and generating significant returns[4] Model Backtesting Results - **GRU(10,2)+NN(10)**: - Multi-Period Return: -1.32% (last week), -0.71% (November), 44.83% (2025)[4] - Excess Return: -0.77% (last week), -1.01% (November), 7.21% (2025)[4] - **GRU(50,2)+NN(10)**: - Multi-Period Return: -1.5% (last week), -1.23% (November), 44.56% (2025)[4] - Excess Return: -0.83% (last week), -0.92% (November), 7.9% (2025)[4] - **Multi-Granularity Model (5-day label)**: - Multi-Period Return: 0.75% (last week), 2.56% (November), 63.15% (2025)[4] - Excess Return: 1.07% (last week), 2.36% (November), 24.44% (2025)[4] - **Multi-Granularity Model (10-day label)**: - Multi-Period Return: 0.91% (last week), 2.55% (November), 57.7% (2025)[4] - Excess Return: 0.98% (last week), 2.27% (November), 24.14% (2025)[4] Quantitative Factors and Construction Methods Factor Name: Intraday Skewness Factor - **Factor Construction Idea**: This factor captures the skewness of intraday returns to identify asymmetric return distributions[4] - **Factor Construction Process**: The factor is calculated using the skewness of intraday returns over a specified period[4] - **Factor Evaluation**: The factor is effective in identifying stocks with asymmetric return distributions[4] Factor Name: Downside Volatility Proportion Factor - **Factor Construction Idea**: This factor measures the proportion of downside volatility to capture risk characteristics[4] - **Factor Construction Process**: The factor is calculated as the proportion of downside volatility relative to total volatility over a specified period[4] - **Factor Evaluation**: The factor is effective in identifying stocks with higher downside risk[4] Factor Name: Post-Open Buy Intention Proportion Factor - **Factor Construction Idea**: This factor measures the proportion of buy intentions after market open to capture investor sentiment[4] - **Factor Construction Process**: The factor is calculated as the proportion of buy orders relative to total orders after market open[4] - **Factor Evaluation**: The factor is effective in capturing investor sentiment and predicting stock movements[4] Factor Name: Post-Open Buy Intensity Factor - **Factor Construction Idea**: This factor measures the intensity of buy intentions after market open to capture investor sentiment strength[4] - **Factor Construction Process**: The factor is calculated as the intensity of buy orders relative to total orders after market open[4] - **Factor Evaluation**: The factor is effective in capturing the strength of investor sentiment and predicting stock movements[4] Factor Backtesting Results - **Intraday Skewness Factor**: - Multi-Period Return: -0.26% (last week), 0.49% (November), 22.76% (2025)[4] - Excess Return: 0.42% (last week), 1.46% (November), 6.14% (2025)[4] - **Downside Volatility Proportion Factor**: - Multi-Period Return: 0.38% (last week), 1.35% (November), 20.32% (2025)[4] - Excess Return: 0.41% (last week), 1.08% (November), 3.54% (2025)[4] - **Post-Open Buy Intention Proportion Factor**: - Multi-Period Return: 0.28% (last week), -0.01% (November), 19.33% (2025)[4] - Excess Return: 0.47% (last week), 0.28% (November), 8.78% (2025)[4] - **Post-Open Buy Intensity Factor**: - Multi-Period Return: 0.27% (last week), 0.57% (November), 26.36% (2025)[4] - Excess Return: -0.22% (last week), -0.55% (November), 10.06% (2025)[4]