Group 1: Market Sentiment Model Insights - Market sentiment is gradually recovering, with the sentiment indicator reaching 1.35 as of December 31, up from 1.1 the previous week, indicating a bullish outlook [8][11] - The price-volume consistency indicator has shown a rapid increase this week, suggesting improved market price-volume matching and a rebound in trading activity [11][12] - The total trading volume for the entire A-share market increased by 8.30% week-on-week, with an average daily trading volume of 21,283.35 billion yuan, indicating heightened market activity [15] Group 2: Sector Performance Insights - As of December 31, 2025, sectors such as machinery, media, computers, beauty care, and automobiles have shown a strong upward trend in short-term scores, with defense and non-ferrous metals leading at a score of 88.14 [40][41] - The industry trading volatility has continued to decline, indicating a slowdown in capital switching between sectors, with a decrease in cross-industry rotation willingness [22][24] - The financing balance ratio has been on the rise, reaching a new high, reflecting an increase in leveraged capital sentiment and a recovery in risk appetite [28][30] Group 3: Investment Style Insights - The current model indicates a preference for small-cap and growth styles, with the 5-day RSI relative to the 20-day RSI continuing to rise, suggesting potential strengthening of these signals [49][50] - The model maintains a bullish signal for growth style, although the rapid increase in the 5-day RSI relative to the 20-day RSI may indicate a potential weakening of this signal [49][50]

- The report introduces a quantitative model based on Convolutional Neural Networks (CNN) to analyze price-volume data and predict future stock prices. The model maps learned features to industry theme indices, including chemical, non-bank financial, and satellite sectors[77][79][80] - The construction process involves standardizing price-volume data into graphical formats for each stock within a specific window period. These standardized charts are then used as input for the CNN model to identify patterns and predict future trends[77][78][79] - The model's evaluation highlights its ability to capture complex relationships in price-volume data and its application in thematic industry allocation. It emphasizes the importance of deep learning techniques in quantitative finance[77][80] - Backtesting results show the latest thematic allocations include indices such as CSI Subdivision Chemical Industry Theme Index, CSI Satellite Industry Index, CSI All Share Dividend Quality Index, and others, reflecting the model's predictions[79][80]

Market Performance - The Sci-Tech 50 Index decreased by 0.59% and the ChiNext Index fell by 0.82% over the last five trading days, while the large-cap value index rose by 0.01% and the large-cap growth index declined by 0.39% [1] - The Shanghai Stock Exchange 50 Index increased by 0.20%, and the small-cap index represented by the CSI 2000 rose by 1.09%, with defense and military, as well as oil and petrochemical sectors performing well, while telecommunications and comprehensive sectors lagged [1] Valuation Levels - As of December 31, 2025, the static PE ratio of the CSI All Share Index is at the 82nd percentile, with the Shanghai 50 and CSI 300 both at 75%, and the ChiNext Index close to 58% [1] - The CSI 500 and CSI 1000 are at 62% and 64% respectively, indicating that the ChiNext Index's valuation is relatively at the historical median level [1] Fund Flows - In the last five trading days, ETF inflows amounted to 25.6 billion yuan, and the margin trading balance increased by approximately 23.8 billion yuan, with an average daily trading volume of 208.23 billion yuan across the two markets [2] Thematic Investment - The latest thematic allocation includes sectors such as chemicals, non-bank financials, and satellite communications, specifically focusing on sub-indices like the CSI Sub-Industry Chemical Index, the National Index for Commercial Satellite Communications, and the CSI 300 Non-Bank Financial Index [2][3] AI and Machine Learning Insights - A convolutional neural network (CNN) model has been utilized to analyze charted price and volume data, mapping learned features to industry thematic sectors, indicating a trend towards AI-driven investment strategies [11]

- Model Name: Timing System Model; Model Construction Idea: The model uses the distance between the long-term moving average (120 days) and the short-term moving average (20 days) to distinguish the overall market environment[2][6][11] - Model Construction Process: The model calculates the distance between the 20-day moving average and the 120-day moving average. The latest data shows the 20-day moving average at 6298 points and the 120-day moving average at 6090 points. The difference between the two lines is 3.41%, and the absolute value of the distance continues to be greater than 3%, indicating that the market is in an upward trend[2][6][11] - Model Evaluation: The model effectively identifies the market's upward trend, providing a positive signal for market timing[2][6][11] - Model Name: Industry Trend Allocation Model; Model Construction Idea: The model identifies industry trends and allocates based on medium-term reversal expectations and sector performance[2][5][7] - Model Construction Process: The model signals to focus on service consumption sectors such as tourism and media based on medium-term reversal expectations. The TWO BETA model continues to recommend the technology sector, focusing on AI applications and commercial aerospace. The industry trend model shows that the communication, industrial metals, and energy storage sectors continue their upward trend[2][5][7] - Model Evaluation: The model provides clear guidance on sector allocation, helping investors to focus on promising sectors[2][5][7] - Model Name: Position Management Model; Model Construction Idea: The model suggests stock allocation based on valuation indicators and short-term trends[5][7] - Model Construction Process: The model uses the PE and PB ratios of the WIND All A Index. The PE ratio is near the 90th percentile, indicating a relatively high valuation, while the PB ratio is at the 50th percentile, indicating a moderate level. Based on these indicators and short-term trends, the model suggests an 80% stock allocation for absolute return products[5][7] - Model Evaluation: The model provides a balanced approach to stock allocation, considering both valuation and market trends[5][7] Model Backtest Results - Timing System Model, Moving Average Distance: 3.41%[2][6][11] - Timing System Model, Market Trend Line: 6262 points[2][6][11] - Timing System Model, Profit Effect: 2.71%[2][6][11] - Position Management Model, PE Ratio: 90th percentile[5][7] - Position Management Model, PB Ratio: 50th percentile[5][7] - Position Management Model, Stock Allocation: 80%[5][7]

Group 1 - Market sentiment score has stabilized at 1.1 as of December 26, indicating a neutral outlook, with signs of improvement in trading activity [7][11][14] - The overall trading volume for the week increased by 11.63% compared to the previous week, with an average daily trading volume of 19,651.66 billion RMB, peaking at 21,811.04 billion RMB on December 26 [14][16] - The financing balance ratio continues to rise, reaching a new high, indicating an increase in leveraged funds and a recovery in risk appetite [25][27] Group 2 - The short-term scores for industries such as computers, real estate, pharmaceuticals, automobiles, and machinery have shown upward trends, with non-ferrous metals, light industry manufacturing, and communications having the highest short-term scores of 88.14 [35][36] - The industry trading volatility has decreased, indicating a slowdown in capital switching between sectors, with liquidity marginally tightening [20][22] - The correlation between industry congestion and weekly price changes is positive at 0.16, suggesting that sectors with high congestion, like defense and construction materials, have seen significant gains [39][41] Group 3 - The RSI indicator has shown significant improvement, indicating a reduction in selling pressure and a recovery in upward momentum [28][30] - The model indicates a preference for small-cap and growth styles, with the 5-day RSI relative to the 20-day RSI continuing to rise, suggesting potential strengthening of these signals [44][45] - The model's findings highlight that high congestion in sectors can lead to strong price movements but also increases the risk of rapid corrections if market expectations change [38][39]

Group 1: Market Sentiment Model Insights - The market sentiment score has stabilized at 1.1 as of December 26, indicating a neutral outlook, with signs of improvement in trading activity [8][12] - The price-volume consistency indicator showed a rebound in the latter part of the week, suggesting a recovery in market sentiment, although risk appetite remains insufficient [12][19] - The total trading volume for the week increased by 11.63% compared to the previous week, with an average daily trading volume of 19,651.66 billion RMB, indicating heightened market activity [16][18] Group 2: Sector Performance and Trends - The short-term scores for sectors such as computer, real estate, pharmaceutical, automotive, and machinery have shown upward trends, with non-ferrous metals, light industry manufacturing, and communication leading with the highest short-term scores of 88.14 [41][42] - The industry trading volatility has decreased, indicating a slowdown in capital switching between sectors, with a notable decline in the participation of high-elasticity sectors [23][25] - The financing balance ratio continues to rise, reaching a new high, reflecting an increase in leveraged capital sentiment and a recovery in risk appetite [29][31] Group 3: Investment Style and Sector Crowding - The model indicates a preference for small-cap and growth styles, with the 5-day RSI relative to the 20-day RSI showing potential for strengthening signals [50][51] - The correlation between sector crowding and weekly price changes is positive, with sectors like defense and construction materials showing significant gains due to rapid capital inflows [44][46] - High crowding sectors such as food and beverage, and retail have shown lower price increases, while low crowding sectors like beauty care and coal have lagged behind [46][47]

Core Viewpoint - The A-share market is expected to enter a new upward trend based on technical signals from sentiment models indicating a bullish signal [1][2]. Market Outlook - The market is anticipated to return to an upward trend, with liquidity shock indicators for the CSI 300 index at 0.34, lower than the previous week (0.41), indicating current market liquidity is 0.34 standard deviations above the average level over the past year [2]. - The PUT-CALL ratio for the SSE 50 ETF options increased to 0.88 from 0.83, reflecting a rise in investor caution regarding the short-term performance of the SSE 50 ETF [2]. - The five-day average turnover rates for the SSE Composite Index and Wind All A Index are 1.06% and 1.66%, respectively, indicating increased trading activity, positioned at the 69.45% and 75.13% percentiles since 2005 [2]. - The RMB exchange rate fluctuated last week, with onshore and offshore rates increasing by 0.46% and 0.42%, respectively [2]. - Historical data shows that the SSE Composite Index, CSI 300, CSI 500, and ChiNext Index have respective probabilities of rising in the second half of December at 50%, 55%, 45%, and 40%, with average gains of 1.2%, 1.08%, -0.11%, and -0.84% [2]. Technical Analysis - The Wind All A Index broke above the reversal indicator on December 1 according to the SAR indicator [2]. - The market score based on moving average strength is 212, placing it at the 77.2% percentile for 2023 [2]. - A sentiment model score of 3 out of 5 indicates a positive trend signal and a positive weighted model signal [2]. - The A-share market experienced a rebound last week, influenced by U.S. President Trump's strong expectations for a Federal Reserve rate cut and the rapid growth of new momentum industries such as equipment manufacturing and high-tech manufacturing in China [2]. Market Review - Last week, the SSE 50 Index rose by 1.37%, the CSI 300 Index increased by 1.95%, the CSI 500 Index grew by 4.03%, and the ChiNext Index climbed by 3.9% [3]. - The current overall market PE (TTM) stands at 22.3 times, which is at the 76.6% percentile since 2005 [3]. Factor Crowding Observation - The crowding degree for small-cap factors has decreased to 0.15, while the crowding degree for low valuation factors is at -0.61 [4]. - The crowding degree for high profitability factors is 0.14, and for high profitability growth factors, it is 0.46 [4]. - Industry crowding degrees are relatively high in telecommunications, non-ferrous metals, comprehensive, power equipment, and electronics, with defense and military industry and commercial retail showing significant increases [4].

- The report introduces a timing system that uses the distance between the 120-day long-term moving average and the 20-day short-term moving average of the WIND All A Index to determine market trends. The short-term moving average is above the long-term moving average, with a distance of 3.38%, which is significantly greater than 3%, indicating the market has returned to an upward trend[2][6][11] - The "profitability effect" is used as a core indicator to assess market conditions. The current market trend line is at 6237 points, and the profitability effect is 3.12%, which is significantly positive, suggesting the upward trend is likely to continue[5][7][11] - The "Mid-term Distress Reversal Expectation Model" signals a focus on retail, tourism, and other service-oriented consumption sectors[5][7][11] - The "TWO BETA Model" continues to recommend the technology sector, with a focus on domestic computing power and commercial aerospace[5][7][11] - The "Industry Trend Model" indicates that sectors such as communication, industrial metals, and energy storage are maintaining an upward trend[5][7][11] - The valuation metrics for the WIND All A Index show that the PE ratio is at the 85th percentile, indicating a relatively high level, while the PB ratio is at the 50th percentile, indicating a medium level[5][7][11] - Based on the "Position Management Model," the report suggests an 80% equity allocation for absolute return products using the WIND All A Index as the primary stock allocation benchmark[5][7][11]

Market Performance - The Sci-Tech 50 Index increased by 2.85% over the last five trading days, while the ChiNext Index rose by 3.90%. The large-cap value index fell by 0.02%, and the large-cap growth index increased by 2.70%. The Shanghai 50 Index gained 1.37%, and the small-cap index represented by the CSI 2000 rose by 3.55%. The sectors of non-ferrous metals and national defense performed well, while beauty care and social services lagged behind [1]. Valuation Levels - As of December 26, 2025, the static PE ratio of the CSI All Share Index is at the 82nd percentile. The Shanghai 50 and CSI 300 both stand at 74%, while the ChiNext Index is close to 59%. The CSI 500 and CSI 1000 are at 62% and 64%, respectively. The valuation of the ChiNext Index is relatively at the historical median level [1]. Risk Premium - The risk premium, calculated as the inverse of the static PE of the CSI All Share Index minus the yield of the 10-year government bond, is at 2.69% as of December 26, 2025. The two standard deviation boundary is at 4.70% [1]. Fund Flows - In the last five trading days, ETF inflows amounted to 41.6 billion yuan, and the margin trading balance increased by approximately 45.7 billion yuan. The average daily trading volume across the two markets was 1.9454 trillion yuan [2]. Thematic Investment - The latest thematic investment configuration includes sectors such as chemicals, non-bank financials, communications, and satellite industries. Specific indices mentioned are the CSI Sub-Industry Chemical Index, CSI 300 Non-Bank Financial Index, CSI All Share Communication Equipment Index, and the National Satellite Communication Industry Index [2][3]. AI and Machine Learning Application - The application of convolutional neural networks (CNN) for modeling price and volume data has been explored, focusing on standardizing chart data to predict future prices and mapping learned features to industry themes [10].

Group 1 - The market sentiment score has slightly decreased to 1.1 as of December 21, down from 1.35 the previous week, indicating a neutral outlook despite a recent rebound on Friday [1][6] - The overall sentiment index has shown significant improvement this week, with signs of a rebound in market trading activity [1][6] - The price-volume consistency indicator has improved, suggesting a better correlation between capital attention and stock price increases, although the risk appetite remains insufficient as indicated by the declining proportion of the STAR 50 index's trading volume [1][9] Group 2 - The total trading volume for the entire A-share market decreased by 9.86% week-on-week, with an average daily trading volume of 17,604.84 billion yuan, reflecting a decline in market activity compared to the previous week [1][12] - The short-term scores for industries such as beauty care, pharmaceuticals, non-bank financials, agriculture, and retail have shown upward trends, with the communication sector having the highest short-term score of 79.66 [1][33] - The correlation between trading congestion and weekly price changes is strong, with high congestion sectors like retail and light manufacturing leading in gains, while sectors with lower congestion such as power equipment and computers lag behind [1][38] Group 3 - The current model indicates a preference for small-cap and growth styles, with the 5-day RSI showing a decline relative to the 20-day RSI, suggesting potential weakening of signals [1][42] - The financing balance ratio continues to rise, reaching a new high for the phase, indicating increased risk appetite and active capital utilization in the market [1][22] - The main capital inflow has broken through the fluctuation range, reflecting a stronger willingness of institutional funds to enter the market, which supports a bullish momentum [1][28]