Feed conversion ratio (FCR) is a critical indicator of production efficiency in livestock husbandry. Improving FCR is essential for optimizing resource utilization and enhancing productivity. Traditional methods for FCR optimization rely on experience and long-term data collection, which are time-consuming and inefficient. This study explores the feasibility of predicting long-term FCR using short-term FCR data based on machine learning techniques. We employed nineteen machine learning algorithms, including Linear Regression, support vector machines (SVMs), and Gradient Boosting, using historical datasets to train and validate the models. The results show that the Gradient Boosting model demonstrated superior performance, achieving a coefficient of determination (R²) of 0.72 and a correlation of 0.85 between predicted and actual values when the testing interval exceeded 40 kg. Therefore, we recommend a minimum feeding measurement interval of 40 kg. Furthermore, when the testing interval was set to 40 kg and further refined to the range of 50–90 kg, the model achieved an R² of 0.81 and a correlation of 0.90 for FCR prediction in the 30–105 kg range. Among the 19 machine learning algorithms tested, Gradient Boosting, LightGBM, and CatBoost showed superior performance, with Gradient Boosting achieving the best results. Considering practical production requirements, the 50–90 kg feeding stage proved to be the most ideal for FCR testing. This study provides a more effective method for predicting feed efficiency and offers robust data support for precision livestock farming.

Background: In pigs, a hair whorl refers to hairs that form a ring of growth around the direction of the hair follicle at the dorsal hip. In China, a hair whorl is considered a negative trait that affects marketing, and no studies have been conducted to demonstrate whether hair whorl affects pig performance and provide an explanation for its genetic basis. Methods: Performance-measured traits and slaughter-measured traits of hair whorl and non-hair whorl pigs were differentially analyzed, followed by genome-wide association analysis (GWAS) and copy number variation (CNV) methods to investigate the genetic basis of hair whorl in pigs. Results: Differential analysis of 2625 pigs (171 hair whorl and 2454 non-hair whorl) for performance measures showed that hair whorl and non-hair whorl pigs differed significantly (p < 0.05) in traits such as live births, total litter size, and healthy litter size (p < 0.05), while differential analysis of carcass and meat quality traits showed a significant difference only in the 45 min pH (p = 0.0265). GWAS identified 4 SNP loci significantly associated with the hair whorl trait, 2 of which reached genome-significant levels, and 23 candidate genes were obtained by annotation with the Ensembl database. KEGG and GO enrichment analyses showed that these genes were mainly enriched in the ErbB signaling, endothelial apoptosis regulation, and cell proliferation pathways. In addition, CNV analysis identified 652 differential genes between hair whorl and non-hair whorl pigs, which were mainly involved in the signal transduction, transcription factor activity, and nuclear and cytoplasmic-related pathways. Conclusions: The candidate genes and copy number variation differences identified in this study provide a new theoretical basis for pig breeding efforts.