Delineating Housing Submarkets Using Space–Time House Sales Data: Spatially Constrained Data-Driven Approaches
Bibliographic record
Abstract
With the increasing availability of large volumes of space–time house data, delineating space–time housing submarkets is of interest to real estate agents, homebuyers, urban policymakers, and spatial researchers, among others. Appropriately delineated housing submarkets can help nurture submarket monitoring and housing policy developments. Although submarkets are often expected to represent areas with similar houses, neighborhoods, and amenities characteristics, delineating spatially contiguous areas with virtually no fragmented small areas remains challenging. Furthermore, housing submarkets can potentially change over time along with concomitant urban transformations, such as urban sprawl, gentrification, and infrastructure improvements, even in large metropolitan areas, which can complicate delineating submarkets with data for lengthy time periods. This study proposes a new method for integrating a random effects model with spatially constrained data-driven approaches in order to identify stable and reliable space–time housing submarkets, instead of their dynamic changes. This random effects model specification is expected to capture time-invariant spatial patterns, which can help identify stable submarkets over time. It highlights two spatially constrained data-driven approaches, ClustGeo and REDCAP, which perform equally well and produce similar space–time housing submarket structures. This proposed method is utilized for a case study of Franklin County, Ohio, using 19 years of space–time private house transaction data (2001–2019). A comparative analysis using a hedonic model demonstrates that the resulting submarkets generated by the proposed method perform better than popular alternative submarket creators in terms of model performances and house price predictions. Enhanced space–time housing delineation can furnish a way to better understand the sophisticated housing market structures, and to help enhance their modeling and housing policy. This paper contributes to the literature on space–time housing submarket delineations with enhanced approaches to effectively generate spatially constrained housing submarkets using data-driven methods.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.006 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".