Addressing strategies for managing vacant, abandoned, and deteriorated (VAD) properties is important for maintaining healthy communities. Yet, the process of identifying these properties can be difficult. Here, we create a human-in-the-loop machine learning (HITLML) model called VADecide and apply it to a parcel-level case study in Savannah, Georgia. The results show a higher prediction accuracy than was achieved when using a machine learning model without human input in the training. The HITLML approach also reveals differences between machine versus human-generated results. Our findings contribute to knowledge about the advantages and challenges of HITLML in urban planning.
AppelSheila U.BottiDerekJamisonJamesPlantLeslieShyrJing Y.VarshneyLav R.2014. “Predictive Analytics Can Facilitate Proactive Property Vacancy Policies for Cities.” Technological Forecasting and Social Change89:161–73. doi:10.1016/j.techfore.2013.08.028.
4.
ArmstrongM. P.DenshamP. J.RushtonG.1986. “Architecture for a Microcomputer Based Spatial Decision Support system.” Proceedings of the Second International Symposium on Spatial Data Handling, Seattle, 120–131.
5.
ArnsteinSherry R.1969. “A Ladder of Citizen Participation.” Journal of the American Institute of Planners35 (4): 216–24. doi:10.1080/01944366908977225.
6.
BasuSumantaKumbierKarlBrownJames B.YuBin. 2018. “Iterative Random Forests to Discover Predictive and Stable High-order Interactions.” Proceedings of the National Academy of Sciences115 (8): 1943–48. doi:10.1073/pnas.1711236115.
7.
BoehnerKirstenDiSalvoCarl. 2016. “Data, Design and Civics: An Exploratory Study of Civic Tech.” Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, San Jose, 2970–81. doi:10.1145/2858036.2858326.
BranasCharles C.RubinDavidGuoWensheng. 2012. “Vacant Properties and Violence in Neighborhoods.” ISRN Public Health2012:1–23. doi:10.5402/2012/246142.
10.
CardulloPaoloKitchinRob. 2019. “Being a ‘Citizen’ in the Smart City: Up and Down the Scaffold of Smart Citizen Participation in Dublin, Ireland.” GeoJournal84 (1): 1–13. doi:10.1007/s10708-018-9845-8.
HillierAmy E.CulhaneDennis P.SmithTony E.TomlinC. Dana. 2003. “Predicting Housing Abandonment with the Philadelphia Neighborhood Information System.” Journal of Urban Affairs25 (1): 91–106. doi:10.1111/1467-9906.00007.
18.
HolzingerAndreas. 2016. “Interactive Machine Learning for Health Informatics: When Do We Need the Human-in-the-loop?”Brain Informatics3 (2): 119–31. doi:10.1007/s40708-016-0042-6.
19.
HopkinsLewis D.ArmstrongMarc P.1985. “Analytic and Cartographic Data Storage: A Two-tiered Approach to Spatial Decision Support Systems.” Proceedings, Seventh International Symposium on Computer-Assisted Cartography, Washington, DC: American Congress on Surveying and Mapping.
ImmergluckDan. 2016. “Examining Changes in Long-term Neighborhood Housing Vacancy During the 2011 to 2014 US National Recovery.” Journal of Urban Affairs38 (5): 607–22. doi:10.1111/juaf.12267.
JanowiczKrzysztofSieberReneeCramptonJeremy. 2022. “GeoAI, Counter-AI, and Human Geography: A Conversation.” Dialogues in Human Geography12 (3): 446–58. doi:10.1177/20438206221132510.
24.
KitchinRob. 2014. The Data Revolution: Big Data, Open Data, Data Infrastructures and Their Consequences. New York: Sage.
25.
Le DantecChristopher A.2016. Designing Publics. Cambridge, MA: MIT Press.
26.
LewisDavid D.CatlettJason. 1994. “Heterogeneous Uncertainty Sampling for Supervised Learning.” Machine Learning Proceedings 1994, New Brunswick, 148–56. doi:10.1016/B978-1-55860-335-6.50026-X.
27.
LiawAndyWienerMatthew. 2002. “Classification and Regression by randomForest.” R News2 (3): 18–22.
LoukissasYanni Alexander. 2019. All Data Are Local: Thinking Critically in a Data-driven Society. Cambridge, MA: MIT Press.
30.
LuceHudson Hayes. 2000. “The Meaning of Blight: A Survey of Statutory and Case Law.” Real Property, Probate and Trust Journal35:389–478.
31.
MallachAlan. 2018. The Empty House Next Door: Understanding and Reducing Vacancy and Hypervacancy in the United States. Cambridge, MA: Lincoln Institute of Land Policy.
32.
MallachAlan. 2021. Making the Comeback: Reversing the Downward Trajectories of African American Middle-Income Neighborhoods in Legacy Cities. Cambridge, MA: Lincoln Institute of Land Policy.
33.
MallachAlanBrachmanLavea. 2013. Regenerating America’s Legacy Cities. Cambridge, MA: Lincoln Institute of Land Policy.
34.
MatternS., 2021. A City Is Not a Computer: Other Urban Intelligences. Princeton, NJ: Princeton Press.
35.
MonarchRobert Munro. 2021. Human-in-the-Loop Machine Learning: Active Learning and Annotation for Human-Centered AI. New York: Simon & Schuster.
36.
MorckelVictoria C.2016. “Using Suitability Analysis to Prioritize Demolitions in a Legacy City.” Urban Geography38 (1): 90–111. doi:10.1080/02723638.2016.1147756.
37.
ReyesEduardo BlancasHelsbyJenniferRaschKatharinavan der BoorPaulGhaniRayidHaynesLaurenCunningham.Edward P.2016. “Early Detection of Properties at Risk of Blight Using Spatiotemporal Data.” Data for Policy 2016: Frontiers of Data Science for Government: Ideas, Practices and Projections. Cambridge, United Kingdom. doi:10.5281/zenodo.556510.
38.
RothsteinRichard. 2017. The Color of Law: A Forgotten History of How Our Government Segregated America. New York: Liveright Publishing.
39.
SchillingJosephPinzonJimena. 2016. The Basics of Blight: Recent Research on Its Drivers, Impacts, and Interventions. Alexandria, VA: Vacant Property Research Network.
40.
SilvermanRobert MarkYinLiPattersonKelly L.2013. “Dawn of the Dead City: An Exploratory Analysis of Vacant Addresses in Buffalo, NY 2008–2010.” Journal of Urban Affairs35 (2): 131–52. doi:10.1111/j.1467-9906.2012.00627.x.
41.
SumellAlbert. 2009. “The Determinants of Foreclosed Property Values: Evidence from Inner-city Cleveland.” Journal of Housing Research18 (1): 45–61. doi:10.1080/10835547.2009.12091996.
42.
SunWeiHuangYingSpahrRonald W.SundermanMark A.SunMinxing. 2019. “Neighborhood Blight Indices, Impacts on Property Values and Blight Resolution Alternatives.” Journal of Real Estate Research41 (4): 555–604. doi:10.22300/0896-5803.41.4.555.
43.
U.S. Census Bureau. 2020. Total Population, ACS 5-Years Estimates Detailed Tables. https://data.census.gov/
44.
WeaverRussell C.Bagchi-SenSharmistha. 2013. “Spatial Analysis of Urban Decline: The Geography of Blight.” Applied Geography40:61–70. doi:10.1016/j.apgeog.2013.01.011.
45.
WhitakerStephanFitzpatrickThomas J.IV. 2013. “Deconstructing Distressed-property Spillovers: The Effects of Vacant, Tax-delinquent, and Foreclosed Properties in Housing Submarkets.” Journal of Housing Economics22 (2): 79–91. doi:10.1016/j.jhe.2013.04.001.
46.
WilsonAlexanderMark Tewdwr-JonesM.2022. Digital participatory planning: Citizen engagement, democracy, and design. New York: Routledge.
47.
WilliamsSarah. 2020. Data Action: Using Data for Public Good. Cambridge, MA: MIT Press.
48.
ZhengZhibinSieberRenee. 2022. “Putting Humans Back in the Loop of Machine Learning in Canadian Smart Cities.” Transactions in GIS26 (1): 8–24.
49.
ZhouJianlongChenFang. 2018. Human and Machine Learning: Visible, Explainable, Trustworthy, and Transparent. Cham: Springer.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
