Deepening social inequalities have remained a constant in our contemporary urban landscapes. Particularly within global cities like London, the disparities have become increasingly apparent with the city being home for the majority of the UK’s richest 1%, or indeed the 0.1% and also a large proportion of its urban poor. In spite of such polarisations, a sense of indifference towards the needs of the average Londoner seemingly prevails throughout London’s hyper-commodified housing market, which is typified by sky-rocketing property prices and a chronic undersupply of truly affordable housing options.
Gentrification, emanating from the nexus of such trends, has been endemic in London; propelling socio-spatial transformations in localised neighborhoods and displacing incumbent residents. Despite gentrification manifesting in more accentuated and diversified ways than ever before, recent research has only been tepid in honing the critical edge necessary for effectively distinguishing gentrification from other forms of neighborhood change and to rigorously disaggregate gentrification’s nuances.
Addressing such issues, the research team comprising Joshua Yee and Dr Adam Dennett from the Centre of Advanced Spatial Analysis (CASA), University College London (UCL) employed a novel empirical approach, that synergised recent advancements in Machine Learning, new data sets and Spatial Data Science techniques, to systematically examine the variegated past and future trajectories of neighborhood change across London.
The nature of gentrification’s mutations and its spatial patterning in London were further extracted using a combination of Principal Component Analysis (PCA), K-Means clustering and in-depth spatial analysis. Machine Learning (ML) was subsequently adopted to model gentrification’s observed trends and predict its future frontiers; thereby offering policy-makers unprecedented and highly-contextualised insights into gentrification’s projected dynamics and geographies.
The aims were threefold:
Undergirding the originality of this study is a repertoire of novel ML, spatial analytical techniques and new sources of multi-dimensional data, leveraged to comprehensively examine the diversified patterns of neighborhood change and gentrification trajectories across London.
The datasets utilised in this study were derived from three main sources:
Diverse methods, straddling across statistics, ML and spatial analysis, were chained into a multi-level workflow with every phase building upon results of the former in order to unpack the diversity and trajectories of gentrification across neighborhoods in London.
Firstly, statistical geographies known as Lower Layer Super Output Areas (LSOAs) in London were classified according to whether they were ascending, stable or declining in terms of house price, levels of highly educated, high socio-economic status residents or median income. Ascending neighborhoods were then further classified into gentrifying and non-gentrifying areas, with three main typologies identified. The gentrification cluster was then further re-classified into three categories of gentrification. These classifications were then used to predict future areas of gentrification in the city using machine learning algorithms.
Variables on house price, levels of highly educated, high socio-economic status residents or median income neighborhoods in London were combined into a composite index score using PCA and were then classified according to the changes observed between 2001 and 2011. Between 2001-2011, 732 LSOAs were highlighted as ascending, 619 LSOAs in decline, whereas the remaining 3,484 LSOAs were considered stable. While LSOAs in ascent and decline were dotted throughout the city, ascending LSOAs tended toward locations in Central and East London while a denser congregation of declining LSOAs was situated toward the western peripheries.
A k-means algorithm was used to isolate clusters of neighborhoods within the ascending areas, with similar ascent characteristics. Three clusters were identified: Gentrification, Incumbent-upgrading and re-urbanisation - their profiles shown in Figure 1, with their spatial distributions shown in Figure 2.
Figure 1: Clusters of Ascending Neighborhoods
Figure 2: Spatial Distribution of the Typologies of Neighborhood Ascent
Neighborhoods identified as gentrifying were further classified according to changes in the socio-economic status of residents, house price and income. Three further clusters were identified: Super-gentrification, Marginal Gentrification and Mainstream Gentrification (Figure 3 and 4).
Figure 3: Clusters of Gentrifying Neighborhoods
Figure 4: Spatial Distribution of Gentrification Types
Deeper spatial analysis identified statistically significant, distinct hotspots of gentrifying neighborhoods and their variant typologies, as visualised in the following map:
A suite of ML models were trained on the observed trends and spatial patterns of neighborhood ascent and gentrification that unfolded between 2001-2011, with the aim of predicting which LSOAs will gentrify in the near future and their corresponding typologies. To further optimise the model, geographic covariates which layer on spatial perspectives and can enable the model to recognise the spatiality of gentrification’s manifestations, were incorporated in two ways. Firstly, through the addition of an inner London dummy and secondly through a gentrification neighbor dummy. The addition of geographic covariates improved the prediction of gentrifying and non-gentrifying areas to 100% and 85% respectively.
A similar modeling methodology incorporating additional variables can be used to predict the specific typologies of future gentrifying LSOAs. According to the predictions visualized on the interactive map below, super-gentrifying trends will potentially retain a stronghold over LSOAs in central-western London, around Hampstead Heath, Richmond Park and the northern edges of Barnet and Enfield. Previously isolated islands of super-gentrification near Chiswick, Clapham South and Dulwich are nonetheless anticipated to expand. LSOAs experiencing marginal gentrification in future are likely to stay in East London, although potentially becoming more extensive around Brockley and Kensal Green. Separately, future mainstream forms of gentrification are predicted to be domineering within London’s inner boroughs and north of the Thames, in boroughs such as Camden, Islington and Hackney.
The analysis has shown that two broad processes of neighborhood change – neighborhood ascent and decline – collectively accounted for 1,351 LSOAs or almost 30% of all LSOAs in the city. No borough, except for the City of London, was spared from these processes, thereby underscoring the extensiveness of socio-spatial transformations happening in London.
Gentrifying LSOAs were found to comprise around 15% of all LSOAs in London; affecting over half-a-million residents. Percolating through traditionally richer, upscale West London boroughs like Kensington and Chelsea and Westminster, as well as boroughs in East London that are conventionally viewed as working-class and less desirable. These contrasting, and indeed almost conflicting, urban backdrops against which gentrification has materialised clearly hint toward its existence in variegated forms – to which our study has shown that super-gentrification, marginal gentrification and mainstream gentrification were simultaneously taking place in London and are unlikely to diminish in the near future according to our model’s predictions.
Want to discover more?Click here to read the working paper
The global data monetization market is projected to reach over $370 billion by 2023. 68% of organizations will increase investment in Spatial Data Science over the next two...Spatial Data
Continuing on our mission to improve the efficiency of Data Science teams who need to work with spatial data, and after several months of testing, validation, and continuou...Spatial Data
Spatial data used for market research, geomarketing, and other types of analysis requiring insights into consumer behavior typically consists of categories such as age, gen...Spatial Data
Please fill out the below form and we'll be in touch real soon.