[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121949-en":3,"doc-seo-121949-105":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},121949,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Developing the use of machine learning models to detect physical and social indicators of gentrification - Master of Philosophy Thesis","Gentrification research has historically been limited by data and modelling constraints when identifying both social and physical indicators of gentrification in cities. This thesis leverages emerging big-data sources and advances in machine learning to build a multi-dimensional, data-driven detection approach. Two models are developed and tested across the Greater Sydney Metropolitan Area, combining a tree-based socioeconomic prediction stage with a deep-learning analysis of Google Street View property upgrades. The results enable validation and aim to distinguish gentrification from other neighbourhood change types while informing policy responses.","Developing the use of machine learning models to detect physical and social indicators of gentrification  \nAuthor:  \nThackway, William  \nPublication Date:  \n2024  \nDOI:  \n[https://doi.org/10.26190/unsworks/25531](https://doi.org/10.26190/unsworks/25531)  \nLicense:  \n[https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nLink to license to see what you are allowed to do with this resource.  \nDownloaded from [http://hdl.handle. net/1959.4/101828](http://hdl.handle. net/1959.4/101828) in [https://](https://)[ ](https://)[unsworks. unsw.edu.au](unsworks. unsw.edu.au) on 2024-05-18  \nDeveloping the use of machine learning models to detect physical and social indicators of gentrification  \nWilliam Thackway  \nA thesis in fulfilment of the requirements for the degree of Master of Philosophy  \nSchool of Built Environment  \nFebruary 2024  \nDeclarations  \nPublications Statement  \nAcknowledgements  \nFirstly, I would like to thank my supervisors, Chris Pettit, Matthew Ng, and Chyi-Lin Lee for their support and guidance over the past 3 years. I would particularly like to thank Chris whom I first met lecturing the Smart Cities course at UNSW, and who subsequently took me on as a research student and encouraged me to do my Masters. Matt, your patience and technical support helped me get several papers over the line, and Chyi-Lin, thank you for your insightful comments and observations which are always well-considered.  \nI would also like to thank FrontierSI, City Futures and the Value Australia project which provided funding for my research scholarship, helped source data for modelling and provided a collaborative and open space to share and discuss findings among other talented researchers.  \nI would like to thank Michael Sawade from the University of Ottawa for generously sharing some code from his 2019 paper (Illic et al., 2019) which was tremendously helpful in forming the deep learning model presented in the thesis. Similarly, I’d like to thank my friend Josh who was very generous in sharing his deep learning knowledge and some tips to create and run my deep learning model more efficiently.  \nFinally, I would like to thank my friends and family for their support throughout my thesis and for trying (with some degree of success) to understand my research topic. Particularly my mother, Susie, for providing advice on many occasions about how to approach roadblocks and general research queries, and my grandparents Brian and Priscilla for proofreading my final draft.  \nAbstract  \nGentrification researchers have historically been constrained by data and modelling limitations in their attempts to detect both social and physical indicators of gentrification in cities. Recently, however, the proliferation of emerging and big data sources, and the emergence of powerful machine learning methods, have enabled a new frontier of data-driven gentrification research. It is in this context that this study explores the use of two different machine learning models to detect socioeconomic and built environment indicators that, together, build a multi-dimensional picture of gentrification occurring within a city. The novel, multi-dimensional gentrification detection approach is tested across the Greater Sydney Metropolitan Area, where constricted housing supply, geographical limitations, and lower socioeconomic inner-city populations provide ideal conditions for gentrification to become manifest. The thesis involves two stages.  \nThe first stage applies a tree-based machine learning model to a dataset comprising socioeconomic, housing, and business variables to predict future gentrification in Sydney. This approach makes both methodological improvements through the application of more powerful modelling techniques and the development of a power explanatory tool, and empirical contributions through the most current and comprehensive appraisal of gentrification in Sydney. The second stage utilises Google Street View data ","cbCaieC65qj47VWd","https://ap.wps.com/l/cbCaieC65qj47VWd","pdf",13942599,1,82,"English","en",105,"# Chapter 1: Introduction\n## 1.1 Introduction\n## 1.2 Gentrification in the Sydney context\n## 1.3 Research questions\n## 1.4 Conceptual framework\n## 1.5 Thesis structure\n# Chapter 2: Reviewing historical attempts to model gentrification\n## 2.1 Contextualising gentrification within the urban context\n## 2.2 Reviewing qualitative assessments of gentrification\n## 2.3 The evolution of quantitative gentrification research\n## 2.4 Persisting limitations of quantitative analyses of gentrification\n## 2.5 Machine learning and gentrification modelling\n# Chapter 3: Building a predictive machine learning model of gentrification in Sydney\n## 3.1 Foreword to paper\n## 3.2 Cities paper\n# Chapter 4: Implementing a deep learning model using Google Street View to combine social and physical indicators of gentr","[{\"question\":\"What problem does the thesis address in gentrification research?\",\"answer\":\"It addresses limitations in detecting both social and physical indicators of gentrification due to prior data and modelling constraints.\"},{\"question\":\"Which machine learning models are used in the study?\",\"answer\":\"The thesis uses a tree-based machine learning model for predicting future gentrification using socioeconomic, housing, and business variables, and a deep learning model with Google Street View data to detect property upgrades.\"},{\"question\":\"How does the study validate a multi-dimensional understanding of gentrification?\",\"answer\":\"Predictions of socioeconomic change from the first stage are compared with detected physical upgrades from the second stage, producing a validation tool that combines social and physical indicators.\"}]","Developing the use of machine learning models to detect physical and social indicators of gentrification - Master of Philosophy Thesis | PDF",1785807931,207,{"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},"developing-the-use-of-machine-learning-models-to-detect-physical-and-social-indicators-of-gentrification-master-of-philosophy-thesis","",{"@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/developing-the-use-of-machine-learning-models-to-detect-physical-and-social-indicators-of-gentrification-master-of-philosophy-thesis/121949/",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},"What problem does the thesis address in gentrification research?","Question",{"text":75,"@type":76},"It addresses limitations in detecting both social and physical indicators of gentrification due to prior data and modelling constraints.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are used in the study?",{"text":80,"@type":76},"The thesis uses a tree-based machine learning model for predicting future gentrification using socioeconomic, housing, and business variables, and a deep learning model with Google Street View data to detect property upgrades.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the study validate a multi-dimensional understanding of gentrification?",{"text":84,"@type":76},"Predictions of socioeconomic change from the first stage are compared with detected physical upgrades from the second stage, producing a validation tool that combines social and physical indicators.","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"]