[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127206-en":3,"doc-seo-127206-105":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},127206,549768702563,"Sage","https://ap-avatar.wpscdn.com/avatar/8000c4aa63b76e948b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786536092046926083",8,"Research & Report","Mapping Informality and Violence: Machine Learning Insights into Crime Patterns Across South African Police Jurisdictions - Academic paper summary","This study examines the relationship between neighborhood informality and crime rates in South Africa, where rapid urbanization has enabled criminal organizations and informal networks to step in as service providers within some settlements. Using K-means clustering and Local Moran’s I on 1,164 police jurisdictions, the highest-informality cluster corresponds to the lowest crime rates. Regression and machine learning (KNN, random forest) further show a statistically significant negative association and accurate crime prediction with low MSE, with k-complexity as a key feature, and policy-relevant implications for public safety and governance.","THE UNIVERSITY OF CHICAGO  \nMapping Informality and Violence: Machine Learning Insights into Crime Patterns Across South African Police Jurisdictions  \nBy  \nYingyi Liang  \nMay, 2025  \nA paper submitted in partial fulfillment of the requirements for the Master of Arts degree in the Master of Arts in Computational Social Science  \nFaculty Advisor: Professor Benjamin Lessing  \nPreceptor: Fabricio Vasselai  \nAcknowledgements  \nTo my parents, for the longing.  \nTo Ruge, for the wishing.  \nAbstract  \nThis study examines the relationship between neighborhood informality and crime rates in South Africa, where rapid urbanization has led to criminal organizations stepping into provide services within some of these settlements. Applying K-means clustering and Local Moran’s I analysis to 1,164 police jurisdictions, we observe that the cluster with the highest level of informality also exhibited the lowest crime rates. Furthermore, in clusters representing moderately dense urban areas, linear regression reveals a statistically significant negative correlation between levels of informality and crime rates. Machine learning models, including KNN and random forest, show that crime can be predicted with low MSE, with k-complexity emerging as a key feature. Finally, a longitudinal case study on crime and growth data offers further insight into potential causal relationships, though the results are not statistically significant. These findings have implications for urban governance and public safety policies in developing countries.  \nKeywords: Urbanization; Crime; Informality; K-means clustering; Machine Learning; Granger Causality;  \n1 Introduction  \nThe United Nations (2022) has projected that the most rapid urbanization over the next decade will take place in low-income developing countries. However, it is already evident that in many nations within the Global South, the development of infrastructure needed to accommodate this increasing population density is lagging. One significant outcome is the migration of individuals into informal settlements, such as slums, where competition for scarce resources becomes more intense. By the informality of neighborhoods in this paper, I refer to the lack of formal planning and regulation by governing authorities on properties, leading to inadequate access to roads, other infrastructure and services. In the Method section, I will detail how I use measures derived from building footprints to proxy informality and frame this analysis.  \nIn these environments, non-governmental actors, including organized criminal groups and informal networks, frequently intervene to provide essential goods and services, stepping  \ninto roles traditionally served by formal institutions. This phenomenon prompts critical questions regarding its implications for violence within these communities. Specifically, what factors influence the degree of involvement of non-governmental actors in resource allocation, and how does this involvement affect the levels of violent conflict in different urban settings? Understanding these complex relationships is not only critical for managing the immediate challenges posed by urban expansion but will also inform future policies for fostering long-term stability and security in urban areas of low-income developing countries.  \nSouth Africa presents a compelling context for this study. Its tumultuous history has led to a weakened government system and a proliferation of vigilantes and criminal organizations across various industries (Vigneswaran, 2014) . The country’s legacy of apartheid has resulted in persistent economic inequalities that continue to the present day, contributing to a lack of governmental monopoly over violence. Criminal organizations have gained political control by leveraging influence over votes to further their business interests. Scholars have studied the phenomenon of “state capture” in South Africa, whereby state apparatus is appropriated for private gains (February, ","cbCaivHefxnXCSq8","https://ap.wps.com/l/cbCaivHefxnXCSq8","pdf",11778186,1,36,"English","en",105,"# 1 Introduction\n# 2 Literature Review\n## 2.1 Slums in South Africa\n# 3 Data and Variables\n# 4 Methodology\n## Cluster identification, spatial autocorrelation, and crime prediction\n# 5 Results and Interpretation\n# Conclusion: Findings, limitations, and future directions","[{\"question\":\"How does the study define neighborhood informality in South Africa?\",\"answer\":\"Informality refers to the lack of formal planning and regulation by governing authorities on properties, which leads to inadequate access to roads, infrastructure, and services.\"},{\"question\":\"Which methods are used to connect informality with crime rates across police jurisdictions?\",\"answer\":\"The study applies K-means clustering to group jurisdictions and Local Moran’s I to analyze spatial autocorrelation patterns, then uses linear regression to test relationships in moderately dense urban clusters.\"},{\"question\":\"How accurate are the machine learning models for crime prediction, and what feature matters most?\",\"answer\":\"KNN and random forest predict crime with low MSE; k-complexity emerges as a key feature driving model performance.\"}]","Mapping Informality and Violence: Machine Learning Insights into Crime Patterns Across South African Police Jurisdictions - Academic paper summary | PDF",1785937523,91,{"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},"mapping-informality-and-violence-machine-learning-insights-into-crime-patterns-across-south-african-police-jurisdictions-academic-paper-summary","",{"@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/mapping-informality-and-violence-machine-learning-insights-into-crime-patterns-across-south-african-police-jurisdictions-academic-paper-summary/127206/",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},"How does the study define neighborhood informality in South Africa?","Question",{"text":75,"@type":76},"Informality refers to the lack of formal planning and regulation by governing authorities on properties, which leads to inadequate access to roads, infrastructure, and services.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which methods are used to connect informality with crime rates across police jurisdictions?",{"text":80,"@type":76},"The study applies K-means clustering to group jurisdictions and Local Moran’s I to analyze spatial autocorrelation patterns, then uses linear regression to test relationships in moderately dense urban clusters.",{"name":82,"@type":73,"acceptedAnswer":83},"How accurate are the machine learning models for crime prediction, and what feature matters most?",{"text":84,"@type":76},"KNN and random forest predict crime with low MSE; k-complexity emerges as a key feature driving model performance.","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"]