[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120533-en":3,"doc-seo-120533-105":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},120533,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","AN EXPLAINABLE MACHINE LEARNING APPROACH TO TRAFFIC - ACCIDENT FATALITY PREDICTION","Road traffic accidents create a major public health and economic burden worldwide, with developing settings such as Bangladesh facing heightened risk. Reliable modeling for forecasting crash outcomes supports preventive measures and targeted safety interventions. This study proposes an explainable machine learning framework that classifies fatal versus non-fatal road accident outcomes using Dhaka metropolitan crash data from 2017 to 2022. Multiple classifiers are evaluated and LightGBM achieves the strongest performance (ROC-AUC 0.72). SHAP-based global, local, and feature dependency analyses identify casualty class, accident time, location, vehicle type, and road type as key drivers of fatality risk, informing evidence-based road safety strategies.","AN EXPLAINABLE MACHINE LEARNING APPROACH TO TRAFFIC  \nACCIDENT FATALITY PREDICTION  \nA PREPRINT  \narXiv :2409 . 11929v1 [ cs .LG] 18 Sep 2024  \n Md. Asif Khan Rifat  \nInstitute of Information Technology University of Dhaka Dhaka-1000, Bangladesh [msse1728@iit.du.ac.bd](msse1728@iit.du.ac.bd)  \n Ahmedul Kabir ∗  \nInstitute of Information Technology University of Dhaka Dhaka-1000, Bangladesh [kabir@iit.du.ac.bd](kabir@iit.du.ac.bd)  \n Armana Sabiha Huq  \nAccident Research Institute  \nBangladesh University of Engineering and Technology  \nDhaka-1000, Bangladesh  \n[ashuq@ari.buet.ac.bd](ashuq@ari.buet.ac.bd)  \nSeptember 19, 2024  \nABSTRACT  \nRoad traffic accidents (RTA) pose a significant public health threat worldwide, leading to considerable loss of life and economic burdens. This is particularly acute in developing countries like Bangladesh.  \nBuilding reliable models to forecast crash outcomes is crucial for implementing effective preventive measures. To aid in developing targeted safety interventions, this study presents a machine learningbased approach for classifying fatal and non-fatal road accident outcomes using data from the Dhaka metropolitan traffic crash database from 2017 to 2022 . Our framework utilizes a range of machine learning classification algorithms, comprising Logistic Regression, Support Vector Machines, Naive Bayes, Random Forest, Decision Tree, Gradient Boosting, LightGBM, and Artificial Neural Network.  \nWe prioritize model interpretability by employing the SHAP (SHapley Additive exPlanations) method, which elucidates the key factors influencing accident fatality. Our results demonstrate that LightGBM outperforms other models, achieving a ROC-AUC score of 0.72 . The global, local, and feature dependency analyses are conducted to acquire deeper insights into the behavior of the model. SHAP analysis reveals that casualty class, time of accident, location, vehicle type, and road type play pivotal roles in determining fatality risk. These findings offer valuable insights for policymakers and road safety practitioners in developing countries, enabling the implementation of evidence-based strategies to reduce traffic crash fatalities.  \nKeywords accident fatality prediction · road safety · machine learning · LightGBM · SHAP · XAI  \n1 Introduction  \nInjuries caused by road traffic crashes are one of the leading reasons of death every year all over the globe. As per the Centers for Disease Control and Prevention (CDC (2024)), road accident injuries rank as the eighth most prevalent cause of death worldwide across all age groups and are projected to be the primary cause of death among individuals aged 5 to 29 years according to. Reportedly, someone is being killed every 24 seconds due to a road accident (blo, 2023) . Due to road traffic crashes, not only people’s lives are being cut short each year, but almost 20-50 million more people suffer non-fatal injuries, among them many incur disabilities as well. The World Health Organization (WHO  \n∗ Corresponding Author.  \n(2023)) estimates that 92% of the fatalities on the road occur in low and middle-income countries. Road accidents in a developing country such as Bangladesh have become a significant concern, leading to a high number of casualties and economic losses each year. It has been found that in Bangladesh, one of the reasons behind this substantial economic burden is that 67% of the fatalities caused by road crashes occur within the economically productive age group of 15-64 years (ban, 2023) . According to the Bangladesh Road Safety Foundation’s (RSF (2023)) annual report, at least 6,284 people died, and 7,468 others were injured in road accidents in 2021, compared to 5,431 people dead and 7,379 injured in road collisions in 2020 . Given the huge number of vehicles in the complex transportation system, we need not only an understanding of the causes of accidents but also a reliable and precise traffic accident outcome prediction model to mitigate potential ","cbCaimPRVYgmAex6","https://ap.wps.com/l/cbCaimPRVYgmAex6","pdf",3918176,1,10,"English","en",105,"# Abstract\n# Keywords\n# Introduction","[{\"question\":\"What problem does the study address?\",\"answer\":\"The study focuses on predicting whether traffic accident outcomes are fatal or non-fatal, aiming to support effective prevention and targeted road safety interventions.\"},{\"question\":\"Which machine learning models are evaluated in the proposed framework?\",\"answer\":\"The study evaluates Logistic Regression, Support Vector Machines, Naive Bayes, Random Forest, Decision Tree, Gradient Boosting, LightGBM, and Artificial Neural Network.\"},{\"question\":\"How is model interpretability achieved and what factors matter most?\",\"answer\":\"Interpretability is provided using SHAP, including global, local, and feature dependency analyses. SHAP highlights casualty class, time of accident, location, vehicle type, and road type as pivotal in determining fatality risk.\"}]","AN EXPLAINABLE MACHINE LEARNING APPROACH TO TRAFFIC - ACCIDENT FATALITY PREDICTION | PDF",1785730536,25,{"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},"an-explainable-machine-learning-approach-to-traffic-accident-fatality-prediction","",{"@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/an-explainable-machine-learning-approach-to-traffic-accident-fatality-prediction/120533/",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","2026-08-03",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},"What problem does the study address?","Question",{"text":75,"@type":76},"The study focuses on predicting whether traffic accident outcomes are fatal or non-fatal, aiming to support effective prevention and targeted road safety interventions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are evaluated in the proposed framework?",{"text":80,"@type":76},"The study evaluates Logistic Regression, Support Vector Machines, Naive Bayes, Random Forest, Decision Tree, Gradient Boosting, LightGBM, and Artificial Neural Network.",{"name":82,"@type":73,"acceptedAnswer":83},"How is model interpretability achieved and what factors matter most?",{"text":84,"@type":76},"Interpretability is provided using SHAP, including global, local, and feature dependency analyses. SHAP highlights casualty class, time of accident, location, vehicle type, and road type as pivotal in determining fatality 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},[93,97,101,105,110,115,120,123,128,131,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]