Background Finding out the key reproductive performance factors, affecting piglets weaned per sow per year (PSY) can improve the production efficiency and profitability of pig farms. The objective was to understand the actual distribution of different production factors and PSY of breeding pig farms, analyze the correlation to find the main production factors affecting PSY, and formulating a Production Efficiency Improvement Plan in practice. Data included 603 breeding pig farms from September 28, 2020 to September 26, 2021. Regression analysis was used to evaluate the relationship between PSY and key production factors, and the characteristics of total pig farms versus high performance (HP) pig farms (the production performance was in the top 10%) or top 5% pig farms were compared. Spearman’s rank correlation coefficient was used to analyze the correlation between production factors and find the factors related to PSY. Non-linear support vector regression (NL-SVR) was used to analyze the personalized PSY improvement through a various change of the four key factors. Results The median distribution of 15 production factors and PSY in total pig farms were different from those of HP farms. All of data were distributed nonlinearly. Mating rate within 7 days after weaning (MR7DW), farrowing rate (FR), number of piglets born alive per litter (PBAL) and number of weaned piglets per litter (WPL) were moderately correlated with PSY, and the correlation coefficients were 0.5058, 0.4427, 0.3929 and 0.3839, respectively. When the four factors in NL-SVR changed in medium (0.5 piglet or 5%) or high level (1.0 piglet or 10%), PSY can be increased by more than 0.5. Conclusion NL-SVR model can be used to analyze the impact of changes in key production factors on PSY. By taking measures to improve MR7DW, FR, PBAL and WPL, it may effectively improve the current PSY and fully develop the reproductive potential of sows.

Background The purpose of this study was to analyze the relationship between different productive factors and piglets weaned per sow per year (PSY) in 291 large-scale pig farms and analyze the impact of the changes in different factors on PSY. We chose nine different algorithm models based on machine learning to calculate the influence of each variable on every farm according to its current situation, leading to personalize the improvement of the impact in the specific circumstances of each farm, proposing a production guidance plan of PSY improvement for every farm. According to the comparison of mean absolute error (MAE), 95% confidence interval (CI) and R2, the optimal solution was conducted to calculate the influence of 17 production factors of each pig farm on PSY improvement, finding out the bottleneck corresponding to each pig farm. The level of PSY was further analyzed when the bottleneck factor of each pig farm changed by 0.5 standard deviation (SD). Results 17 production factors were non-linearly related to PSY. The top five production factors with the highest correlation with PSY were the number of weaned piglets per litter (WPL) (0.6694), mating rate within 7 days after weaning (MR7DW) (0.6606), number of piglets born alive per litter (PBAL) (0.6517), the total number of piglets per litter (TPL) (0.5706) and non-productive days (NPD) (− 0.5308). Among nine algorithm models, the gradient boosting regressor model had the highest R2, smallest MAE and 95% CI, applied for personalized analysis. When one of 17 production factors of 291 large-scale pig farms changed by 0.5 SD, 101 pig farms (34.7%) can increase 1.41 PSY (compared to its original value) on average by adding the production days, and 60 pig farms (20.6%) can increase 1.14 PSY on average by improving WPL, 45 pig farms (15.5%) can increase 1.63 PSY by lifting MR7DW. Conclusions The main productive factors related to PSY included WPL, MR7DW, PBAL, TPL and NPD. The gradient boosting regressor model was the optimal method to individually analyze productive factors that are non-linearly related to PSY.