[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127287-en":3,"doc-seo-127287-105":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},127287,2336475104736,"Quinn","https://ap-avatar.wpscdn.com/avatar/22000c4c5e0e5b17e70?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786591360781797222",8,"Research & Report","Machine Learning Insights on Farm Exits: Enhancing Resilience in Wisconsin’s Dairy Industry - Paper presentation","Identifying farms at risk of exiting the dairy industry remains difficult due to data scarcity and the limits of traditional econometric approaches such as logit and probit. The study applies machine learning to predict dairy farm exit intentions in Wisconsin using the 2024 DATCP Dairy Producer Survey. Models including Lasso, Ridge, Random Forest, and XGBoost are compared, with XGBoost achieving superior accuracy and sensitivity. SHAP results identify succession planning, operator age, investment behavior, labor constraints, and conservation practices as key predictors, supporting early risk detection. The outputs provide actionable guidance for policymakers, industry partners, and extension services.","The World’s Largest Open Access Agricultural & Applied Economics Digital Library  \nThis document is discoverable and free to researchers across the  \nglobe due to the work of AgEcon Search .  \nHelp ensure our sustainability.  \nGive to AgEcon Search  \nAgEcon Search  \nhttp://ageconsearch.umn.eduaesearch@umn.edu  \nPapers downloaded from AgEcon Search may be used for non-commercial purposes and personal study only.No other use, including posting to another Internet site, is permitted without permission from the copyrightowner (not AgEcon Search), or as allowed under the provisions of Fair Use, U.S. Copyright Act, Title 17 U.S.C.  \nNo endorsement of AgEcon Search or its fundraising activities by the author(s) of the following work or theiremployer(s) is intended or implied.  \nMachine Learning Insightson Farm Exits: Enhancing Resilience in Wisconsin’sDairy Industry  \nMd Azhar Uddin  \nAgricultural Economics  \nUniversity of Wisconsin-River Fall  \nazhar.uddin@uwrf.edu  \nPaper prepared for presentation atthe 2025 AAEA & WAEA Joint Annual Meeting in Denver, CO:  \nJuly 27-29, 2025  \nCopyright 2025 by author. All rights reserved. Readers may make verbatim copies of this document fornon-commercial purposes by any means, provided that this copyright notice appears on all such copies.  \nMachine Learning Insights on Farm Exits: Enhancing Resilience inWisconsin’s Dairy Industry  \n# Abstract\n\nIdentifying farms at risk of exiting the dairy industry remains a major challenge, particularly dueto data scarcity andthe limitations of traditional econometric models such as logitandprobit. Thisstudy applies machine learning (ML) techniques to predict dairy farm exit intentionsin Wisconsinusing data from the 2024 DATCP Dairy Producer Survey. Using abroad set of accessible survey -based variables, including farm demographics, operations, environmental practices, and perceivedchallenges, we compare the performance of Lasso, Ridge, Random Forest, and Extreme GradientBoosting (XGBoost) models. XGBoost outperforms all others in both overall accuracy andsensitivity, effectively identifying farms at risk of exit while maintaining strong performance inpredicting continuation. Furthermore, SHAP (SHapley Additive exPlanations) analysis highlightssuccession planning, operators age, investment behavior, labor constraints, and conservationpractices as key predictors. These findings demonstrate the practical utility of ML models for earlyrisk detection and offer actionable insights for policymakers, industry stakeholders, and extensionservices aiming to sustain Wisconsin’s dairy sector.  \nKeywords: Dairy farm exit, machine learning, farm succession.  \n# Introduction\n\nAs agricultural industries mature, they often undergo structural consolidation characterized by adecreasing number offarms and an increasing average farm (MacDonald, 2018) . This trend hasalso been evident in the U.S. dairy sector, where the number of small- and mid-sized farms hassteadily declined over the past two decades (MacDonald et al., 2020) . Similar patterns have beenobserved in Europe, raising concerns about the socioeconomic implications of dairy farm exits on  \nrural communities (VanLeuven, 2023) . These exits could have far-reaching consequences for ruralemployment, land use, community vitality, and the long-term sustainability of local economies,particularly in dairy-dependent regions such as Wisconsin.  \nWhile the decision to exit dairy farming is often framed as an economic choice, it reflects acomplex interaction of operational, demographic, policy, and environmental factors. Numerousstudies have explored dairy farm exit from multiple perspectives. Some emphasize financialmarket volatility, such as fluctuating milk prices, land price, cow productivity and policy can affectthe exit decision and structural change (Ifft & Yi, 2019; Stokes, 2006) . Farm-level characteristicssuch as age of the operator, farm size (in terms of number of cows, and number of labor) ,technology adoption, and succe","cbCaiqwPNjcrDYqv","https://ap.wps.com/l/cbCaiqwPNjcrDYqv","pdf",1067507,1,23,"English","en",105,"# Abstract\n# Introduction\n# Data\n## Study objective and approach\n## Modeling strategy and predictors","[{\"question\":\"Why is predicting dairy farm exit challenging in existing research?\",\"answer\":\"It is hard to predict exit because farm exit signals are limited by scarce data and traditional binary choice models such as logit and probit may not capture complex or nonlinear patterns driving exit behavior.\"},{\"question\":\"Which machine learning models are compared, and how does XGBoost perform?\",\"answer\":\"The study compares Lasso, Ridge, Random Forest, and Extreme Gradient Boosting (XGBoost). XGBoost outperforms the others in overall accuracy and sensitivity, identifying at-risk farms while still predicting continuation effectively.\"},{\"question\":\"What factors are identified as key predictors of exit risk by SHAP analysis?\",\"answer\":\"SHAP highlights succession planning, operators’ age, investment behavior, labor constraints, and conservation practices as important predictors of exit risk.\"}]","Machine Learning Insights on Farm Exits: Enhancing Resilience in Wisconsin’s Dairy Industry - Paper presentation | PDF",1785938111,58,{"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},"machine-learning-insights-on-farm-exits-enhancing-resilience-in-wisconsins-dairy-industry-paper-presentation","",{"@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/machine-learning-insights-on-farm-exits-enhancing-resilience-in-wisconsins-dairy-industry-paper-presentation/127287/",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","2026-08-05",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},"Why is predicting dairy farm exit challenging in existing research?","Question",{"text":75,"@type":76},"It is hard to predict exit because farm exit signals are limited by scarce data and traditional binary choice models such as logit and probit may not capture complex or nonlinear patterns driving exit behavior.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are compared, and how does XGBoost perform?",{"text":80,"@type":76},"The study compares Lasso, Ridge, Random Forest, and Extreme Gradient Boosting (XGBoost). XGBoost outperforms the others in overall accuracy and sensitivity, identifying at-risk farms while still predicting continuation effectively.",{"name":82,"@type":73,"acceptedAnswer":83},"What factors are identified as key predictors of exit risk by SHAP analysis?",{"text":84,"@type":76},"SHAP highlights succession planning, operators’ age, investment behavior, labor constraints, and conservation practices as important predictors of exit risk.","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"]