[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122490-en":3,"doc-seo-122490-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122490,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Applicability of machine learning methods for classifying lightweight pigs in commercial conditions","The study addresses variability in pig growth within all-in-all-out production systems, where identifying pigs at risk of growth retardation remains inconsistent across stages. Using commercial-condition data from 26,749 weaning pigs, 15,409 nursery-end pigs, and 4,996 slaughter pigs, the work tests classification cut points at the lowest 10%, 20%, and 30% weights. Models are trained and evaluated with AUC after splitting data 2:1, comparing OLS regression, decision tree, random forest, and generalized boosted regression. Random forest and generalized boosted regression achieve the best AUC (0.772–0.861), outperforming OLS (0.752–0.818) and a low-performing single tree (0.608–0.726).","Applicability of machine learning methods for classifying lightweight pigs in commercial conditions  \nPau Salgado-López,†, 1, Joaquim Casellas,‡ Iara Solar Diaz,‖ Thomas Rathje,‖ Josep Gasa,† and David Solà-Oriol†,  \n†Department of Animal and Food Science, Animal Nutrition and Welfare Service (SNIBA), Autonomous University of Barcelona, Bellaterra 08193, Spain  \n‡Department of Animal and Food Science, Autonomous University of Barcelona, Bellaterra 08193, Spain  \n‖DNA Genetics LLC, Columbus, NE 68601, USA 1Corresponding author: [pau.salgado@uab.cat](pau.salgado@uab.cat)  \nAbstract  \nThe varying growth rates within a group of pigs present a significant challenge for the current all-in-all-out systems in the pig industry. This study evaluated the applicability of statistical methods for classifying pigs at risk of growth retardation at different production stages using a robust dataset collected under commercial conditions. Data from 26,749 crossbred pigs (Yorkshire × Landrace) with Duroc at weaning (17 to 27 d), 15,409 pigs at the end of the nursery period (60 to 78 d), and 4996 pigs at slaughter (151 to 161 d) were analyzed under three different cut points (lowest 10%, 20%, and 30% weights) to characterize light animals. Records were randomly split into training and testing sets in a 2:1 ratio, and each training dataset was analyzed using an ordinary least squares approach and three machine learning algorithms (decision tree, random forest, and generalized boosted regression) . The classification performance of each analytical approach was evaluated by the area under the curve (AUC) . In all production stages and cut points, the random forest and generalized boosted regression models demonstrated superior classification performance, with AUC estimates ranging from 0.772 to 0.861. The parametric linear model also showed acceptable classification performance, with slightly lower AUC estimates ranging from 0.752 to 0.818. In contrast, the single decision tree was categorized as worthless, with AUC estimates between 0.608 and 0.726. Key prediction factors varied across production stages, with birthweight-related factors being most significant at weaning, and weight at previous stages becoming more crucial later in the production cycle. These findings suggest the potential of machine learning algorithms to improve decision-making and efficiency in pig production systems by accurately identifying pigs at risk of growth retardation.  \nLay Summary  \nBody weight (BW) variability at slaughter is mainly due to the presence of slow-growing pigs in the herd, which reach market weight later than their faster-growing counterparts. Implementing machine learning algorithms to identify pigs at risk of growth retardation offers significant potential for improving decision-making, production efficiency, and profitability in the swine industry. This research evaluated four different classification algorithms (ordinary least squares regression; decision tree; random forest; and generalized boosted regression) to evaluate their ability to classify commercial lightweight pigs at various production stages. Among these, generalized boosted regression and random forest exhibited the best performance when classifying lightweight pigs at any stage. Thus, the robust performance of these models highlights their practical utility under commercial conditions. These methods could facilitate the identification of lightweight pigs, enabling targeted interventions to optimize growth and reduce variability. As a result, adopting these tools could improve herd management, optimize the use of farm facilities, and ultimately increase overall productivity while reducing shadow production costs in pig farming operations.  \nKey words: area under the curve, classification algorithms, efficiency, growth retardation, live weight, swine  \nAbbreviations: AUC, area under the curve; BIW, birth weight; BW, body weight; DB, difference between the piglet’s birth weight and the ave","cbCainscalYWpId4","https://ap.wps.com/l/cbCainscalYWpId4","pdf",2136505,1,14,"English","en",105,"# Abstract\n## Data and staging\n## Modeling and evaluation\n## Key findings and implications\n# Lay Summary\n## Practical utility in commercial conditions\n## Potential benefits for farm management","[{\"question\":\"Which machine learning models performed best for classifying lightweight pigs across production stages?\",\"answer\":\"Random forest and generalized boosted regression showed superior performance at all production stages and cut points, with AUC estimates from 0.772 to 0.861.\"},{\"question\":\"How were lightweight pigs defined and how was the dataset prepared for training and testing?\",\"answer\":\"Pigs were characterized using three cut points based on the lowest 10%, 20%, and 30% weights. Records were randomly split into training and testing sets in a 2:1 ratio for each training dataset.\"},{\"question\":\"What factors were most important for prediction at different stages?\",\"answer\":\"Key prediction factors varied by stage: birthweight-related factors were most significant at weaning, while weight from previous stages became more important later in the production cycle.\"}]","Applicability of machine learning methods for classifying lightweight pigs in commercial conditions | PDF",1785810922,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"applicability-of-machine-learning-methods-for-classifying-lightweight-pigs-in-commercial-conditions","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/applicability-of-machine-learning-methods-for-classifying-lightweight-pigs-in-commercial-conditions/122490/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Which machine learning models performed best for classifying lightweight pigs across production stages?","Question",{"text":75,"@type":76},"Random forest and generalized boosted regression showed superior performance at all production stages and cut points, with AUC estimates from 0.772 to 0.861.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were lightweight pigs defined and how was the dataset prepared for training and testing?",{"text":80,"@type":76},"Pigs were characterized using three cut points based on the lowest 10%, 20%, and 30% weights. Records were randomly split into training and testing sets in a 2:1 ratio for each training dataset.",{"name":82,"@type":73,"acceptedAnswer":83},"What factors were most important for prediction at different stages?",{"text":84,"@type":76},"Key prediction factors varied by stage: birthweight-related factors were most significant at weaning, while weight from previous stages became more important later in the production cycle.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]