New data and technologies, in particular machine learning, may make it possible to forecast neighbourhood change. Doing so may help, for example, to prevent the negative impacts of gentrification on marginalised communities. However, predictive models of neighbourhood change face four challenges: accuracy (are they right?), granularity (are they right at spatial or temporal scales that actually matter for a policy response?), bias (are they equitable?) and expert validity (do models and their predictions make sense to domain experts?). The present work provides a framework to evaluate the performance of predictive models of neighbourhood change along these four dimensions. We illustrate the application of our evaluation framework via a case study of Buffalo, NY, where we consider the following prediction task: given historical data, can we predict the percentage of residential buildings that will be sold or foreclosed on in a given area over a fixed amount of time into the future?
AlamMRönnegårdLShenX (2015) Fitting conditional and simultaneous autoregressive spatial models in HGLM. The Journal7(2): 5–18.
2.
AnselinL (1995) Local indicators of spatial association—LISA. Geographical Analysis27(2): 93–115.
3.
BartonM (2016) An exploration of the importance of the strategy used to identify gentrification. Urban Studies53(1): 92–111.
4.
BayerPMcMillanRMurphyA, et al. (2016) A dynamic model of demand for houses and neighborhoods. Econometrics84(3): 893–942.
5.
BeauregardRA (2013) The chaos and complexity of gentrification. In: SmithNWilliamsP (eds) Gentrification of the City. Abingdon: Routledge, pp. 51–71.
6.
BoginADoernerWLarsonW (2019) Local house price dynamics: New indices and stylized facts. Real Estate Economics47(2): 365–398.
7.
BoginADoernerWMLarsonW (2016) Missing the mark: House price index accuracy and mortgage credit modeling. FHFA Working Paper 16-04.
8.
BreimanL (2001) Random forests. Machine Learning45(1): 5–32.
9.
Brown-SaracinoJ (2017) Explicating divided approaches to gentrification and growing income inequality. The Annual Review of Sociology43(1): 515–539.
10.
CarlsonHJ (2021) Measuring displacement: Assessing proxies for involuntary residential mobility. City and Community19(3): 573–592.
11.
ChappleKZukM (2016) The use of neighborhood early warning systems for gentrification and displacement: The use of neighborhood early warning systems for gentrification and displacement. Cityscape18(3): 109–130.
12.
ChappleKPoorthuisAZookM, et al. (2022) Monitoring streets through tweets: Using user-generated geographic information to predict gentrification and displacement. Environment and Planning B Urban Analytics and City Science49: 704–721.
13.
ColeyJAdelmanRM (2021) Gentrification in the ‘city of good neighbors’: Race, class, and neighborhoods in Buffalo. Sociological Inquiry91(4): 824–848.
14.
DelmelleEC (2022) GIScience and neighborhood change: Toward an understanding of processes of change. Transactions in GIS26(2): 567–584.
15.
DingLHwangJDivringiE (2016) Gentrification and residential mobility in Philadelphia. Regional Science and Urban Economics61: 38–51.
16.
D’ignazioCKleinLF (2020) Data Feminism. Cambridge, MA: MIT Press.
17.
EastonSLeesLHubbardP, et al. (2020) Measuring and mapping displacement: The problem of quantification in the battle against gentrification. Urban Studies57(2): 286–306.
18.
EnsignDFriedlerSANevilleS, et al. (2018) Runaway feedback loops in predictive policing. In: Conference on fairness, accountability and transparency, New York University, USA, 23 and 24 February 2018, pp. 160–171. New York, NY: PMLR.
19.
FogartyMS (1977) Predicting neighborhood decline within a large central city: An application of discriminant analysis. Environment and Planning A9(5): 579–584.
20.
GibbonsJNaraAAppleyardB (2018) Exploring the imprint of social media networks on neighborhood community through the lens of gentrification. Environment and Planning B Urban Analytics and City Science45(3): 470–488.
21.
GlaeserELNathansonCG (2017) An extrapolative model of house price dynamics. Journal of Financial Economics126(1): 147–170.
22.
GlaeserELKimHLucaM (2018) Nowcasting gentrification: Using Yelp data to quantify neighborhood change. AEA Papers and Proceedings108: 77–82.
23.
GrinsztajnLOyallonEVaroquauxG (2022) Why do tree-based models still outperform deep learning on tabular data? Epub ahead of print, July. DOI: 10.48550/arXiv.2207.08815.
24.
GuerrieriVHartleyDHurstE (2013) Endogenous gentrification and housing price dynamics. Journal of Public Economics100: 45–60.
25.
HwangJDingL (2020) Unequal displacement: Gentrification, racial stratification, and residential destinations in Philadelphia. The American Journal of Sociology126(2): 354–406.
26.
HwangJSampsonRJ (2014) Divergent pathways of gentrification: Racial inequality and the social order of renewal in Chicago neighborhoods. American Sociological Review79(4): 726–751.
27.
JärvelinKKekäläinenJ (2002) Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems20(4): 422–446.
28.
LazerDKennedyRKingG, et al. (2014) Big data. The parable of Google flu: Traps in big data analysis. Science343(6176): 1203–1205.
29.
LundbergSMLeeSI (2017) A unified approach to interpreting model predictions. In: Proceedings of the 31st international conference on neural information processing systems, Long Beach, CA, USA, 4–9 December 2017, pp. 4768–4777.
30.
MitchellTM (2006) The Discipline of Machine Learning. CMU- ML-06-108. Carnegie Mellon University, School of Computer Science, Machine Learning Department. Available at: http://www.cs.cmu.edu/~tom/pubs/MachineLearning.pdf (accessed 15 March 2021).
31.
MurphyA (2018) A dynamic model of housing supply. American Economic Journal Economic Policy10(4): 243–267.
32.
ObermeyerZPowersBVogeliC, et al. (2019) Dissecting racial bias in an algorithm used to manage the health of populations. Science366(6464): 447–453.
33.
PreisBJanakiramanABobA, et al. (2021) Mapping gentrification and displacement pressure: An exploration of four distinct methodologies. Urban Studies58(2): 405–424.
34.
RadfordJJosephK (2020) Theory in, theory out: the uses of social theory in machine learning for social science. Frontiers in Big Data3: 18.
35.
RaschkaS (2018) Model evaluation, model selection, and algorithm selection in machine learning. Epub ahead of print, 13November. DOI: 10.48550/arXiv.1811.12808.
RobertsDRBahnVCiutiS, et al. (2017) Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography40(8): 913–929.
38.
Schnake-MahlASJahnJLSubramanianSV, et al. (2020) Gentrification, neighborhood change, and population health: A systematic review. Journal of Urban Health: Bulletin of the New York Academy of Medicine97(1): 1–25.
39.
SilvermanRMTaylorHLYinL, et al. (2019) There goes our family friendly neighborhood: Residents’ perceptions of institutionally driven inner-city revitalization in buffalo, NY. Journal of Community Practice27(2): 168–187.
40.
SmithN (1987) Gentrification and the Rent Gap. Oxford: Taylor & Francis.
StapletonLLeeMHQingD, et al. (2022) Imagining new futures beyond predictive systems in child welfare: A qualitative study with impacted stakeholders. In: 2022 ACM conference on fairness, accountability, and transparency, Seoul, South Korea, 21–24 June 2022, pp. 1162–1177. New York, NY: Association for Computing Machinery.
SzumiloN (2021) Prices of peers: Identifying endogenous price effects in the housing market. The Economic Journal131(639): 3041–3070.
45.
TaylorHSilvermanRYinL (2018) Buffalo Turning the Corner. Buffalo, NY: University at Buffalo: Center for Urban Studies.
46.
TiefelsdorfMBootsB (2010) A note on the extremities of local Moran’s Iis and their impact on global Moran’s I. Geographical Analysis29(3): 248–257.
47.
VilaRFerreiraLSauloH, et al. (2020) A bimodal gamma distribution: Properties, regression model and applications. Statistics54(3): 469–493.
48.
WilliamsSGalsterGVermaN (2013) Home foreclosures as early warning indicator of neighborhood decline. Journal of the American Planning Association79(3): 201–210.
49.
YontoDSchuchC (2020) Developing and ground-truthing multi-scalar approaches to mapping gentrification. Papers in Applied Geography6(4): 352–368.
50.
ZhouZG (1997) Forecasting sales and price for existing single-family homes: A VAR model with error correction. Journal of Real Estate Research14(2): 155–167.
51.
ZukMBierbaumAHChappleK, et al. (2018) Gentrification, displacement, and the role of Public Investment. Journal of Planning Literature33(1): 31–44.
