[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120451-en":3,"doc-seo-120451-105":29,"detail-sidebar-cat-0-en-105":89},{"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":11},120451,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine Learning Can Reveal Effectiveness of Traffic Safety Countermeasures - Policy Brief","Machine learning framework mines Crash Modification Factors (CMFs) from the CMF Clearinghouse to uncover previously unidentified relationships and enable more rapid, cost-effective CMF assessment for scenarios not covered by the repository. The study addresses limitations of traditional experimental and observational approaches that require years of crash data collection. Trained and tested on CMF Clearinghouse data, the method predicts CMFs with reasonable accuracy, incorporates heterogeneous data, and captures semantic contexts. Results are positioned as preliminary estimates, with recommendations for improving confidence and future extensions combining domain knowledge and traditional methods.","UC Office of the President  \nPolicy Briefs  \nTitle  \nMachine Learning Can Reveal Effectiveness of Traffic Safety Countermeasures  \nPermalink  \n[https://escholarship.org/uc/item/0x26t67j](https://escholarship.org/uc/item/0x26t67j)  \nAuthors  \nLi, Jia, PhD  \nQi, Yanlin  \nZhang, Michael, PhD  \nPublication Date  \n2025-08-01  \nDOI  \n10.7922/G2VD6WVF  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nPOLICY BRIEF Institute of  \nTransportation Studies  \nMachine Learning Can Reveal Effectiveness of Traffic Safety Countermeasures  \nJia Li, Ph.D., Department of Civil and Environmental Engineering,  \nWashington State University  \nYanlin Qi, Institute of Transportation Studies*  \nMichael Zhang, Ph.D., Department of Civil and Environmental Engineering*  \n*University of California, Davis August 2025  \nIssue  \nEmerging machine learning capabilities can be leveraged to make transportation infrastructure safer and reduce fatalities by informing decisions about which countermeasures to apply at crash-prone locations. At this time, project prioritization typically involves assessing effectiveness, cost-benefit ratios, and available funding. Crash Modification Factors (CMFs) play an essential role in project assessment by predicting the effectiveness of safety countermeasures. Their applicability has limitations, however. Some of these may be overcome with innovative approaches such as knowledge-mining.  \nThe US Department of Transportation’s (DOT) CMF Clearinghouse provides practitioners with a list of reliable CMFs developed from individual studies. However, available CMFs do not cover all potential scenarios-of-interest to State DOTs because unique projects may feature novel infrastructure types or countermeasures. Experimental or observational studies are the dominant tools for estimating CMFs. However, these approaches may require years of effort to collect adequate crash data.  \nTo address these challenges, we developed a machine learning framework that mines CMF Clearinghouse data to uncover previously unidentified relationships. This provides a cost-effective and time-efficient solution to assessing CMFs not covered by the CMF Clearinghouse. Our proposed framework fully explores existing CMF data.  \nWe extensively trained and tested the proposed approach on CMF Clearinghouse data with experiments and showed that the framework can predict CMFs with reasonable accuracy. The framework flexibly incorporates heterogeneous data from the CMF Clearinghouse, captures the semantic contexts of countermeasures, and maintains data compatibility.  \nKey Research Findings  \nThe two dominant approaches for estimating CMFs are experimental or observational studies based on before/after or cross-sectional data. Experimental studies are rigorous, requiring years of effort to collect data. This long study cycle hinders wide applications. Observational studies, in contrast, bring fewer ethical concerns than experimentation and can leverage data from sites with already-implemented treatment(s). Before-after studies typically require multiyear crash data collected before and after a treatment. Most cross-sectional studies require crash inventory data collected from multiple sites with and without a treatment in a single period. Both types of studies require substantial quantities of crash data.  \nA machine-learning framework can mine CMF Clearinghouse data. As a one-stop repository, the CMF Clearinghouse has long been used as a search database to support practitioners responsible for infrastructure safety. With thousands of existing CMF records and continuing  \n[www. uc its. org](www. uc its. org)  \nInstitute of Transportation Studies     \nentries, the CMF Clearinghouse has tremendous potential as a knowledge base for deriving additional CMFs. Our knowledge-mining approach for deriving additional CMFs uses information already available, thereby reducing the data-collection and study duration burden of es","cbCaiintwz9ECqR9","https://ap.wps.com/l/cbCaiintwz9ECqR9","pdf",334438,1,3,"English","en",105,"# Issue\n## Challenge and motivation\n## Proposed machine-learning framework\n# Key Research Findings\n## Traditional CMF estimation approaches\n## Mining CMF Clearinghouse knowledge\n## Performance, limitations, and confidence\n# Policy Recommendations","[{\"question\":\"What problem does the policy brief address in traffic safety countermeasure planning?\",\"answer\":\"It addresses how to assess the effectiveness of countermeasures at crash-prone locations when available Crash Modification Factors (CMFs) do not cover all scenarios of interest.\"},{\"question\":\"How does the proposed approach estimate CMF effectiveness?\",\"answer\":\"It develops a machine learning framework that mines existing CMF Clearinghouse data to uncover new relationships and predict CMFs for not-covered scenarios.\"},{\"question\":\"What are the main limitations and future improvements mentioned?\",\"answer\":\"The framework provides predicted CMF values without confidence levels; accuracy could improve by incorporating structured or domain knowledge. Future work also includes combining with traditional approaches and generating confidence intervals using patterns and case-specific records.\"}]","Machine Learning Can Reveal Effectiveness of Traffic Safety Countermeasures - Policy Brief | PDF",1785730176,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":28},"machine-learning-can-reveal-effectiveness-of-traffic-safety-countermeasures-policy-brief","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":21},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/machine-learning-can-reveal-effectiveness-of-traffic-safety-countermeasures-policy-brief/120451/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What problem does the policy brief address in traffic safety countermeasure planning?","Question",{"text":73,"@type":74},"It addresses how to assess the effectiveness of countermeasures at crash-prone locations when available Crash Modification Factors (CMFs) do not cover all scenarios of interest.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"How does the proposed approach estimate CMF effectiveness?",{"text":78,"@type":74},"It develops a machine learning framework that mines existing CMF Clearinghouse data to uncover new relationships and predict CMFs for not-covered scenarios.",{"name":80,"@type":71,"acceptedAnswer":81},"What are the main limitations and future improvements mentioned?",{"text":82,"@type":74},"The framework provides predicted CMF values without confidence levels; accuracy could improve by incorporating structured or domain knowledge. Future work also includes combining with traditional approaches and generating confidence intervals using patterns and case-specific records.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]