Featured forecast
Boston leads on value. Providence leads on momentum.
Our first two-city matchup compares 80 months of hyperlocal home-value history and tests multiple forecasting approaches against a naive baseline.
Read the box score →Independent quantitative research
Evidence for better decisions.
Original housing-market forecasts and applied machine-learning studies, presented with transparent methods, measured limitations, and production context.
Latest city research
2 of 64 markets published
Boston · 02114
A high-value market with measured near-term growth
Boston’s latest observed value is $778,846. The selected drift model forecasts $779,306 for the next month.
View Boston analysis →Providence · 02903
Lower price level, stronger projected momentum
Providence’s latest observed value is $436,391. The selected drift model forecasts $438,308 for the next month.
View Providence analysis →Matchup analysis
Why price and momentum tell different stories
A plain-language guide to reading market level, projected growth, forecast uncertainty, and model error without declaring a misleading universal winner.
Explore the standings →Forecast snapshot
Boston vs Providence
Boston forecast$779,306September 2026
Boston momentum+0.06%Month-ahead projection
Providence forecast$438,308September 2026
Providence momentum+0.44%Forecast pick
Applied machine-learning projects
Real data. Reproducible evaluation. Operational context.
Project 01 · Forecasting
Hyperlocal housing forecast pipeline
A repeatable workflow for ingesting monthly market data, comparing multiple time-series candidates, conducting rolling backtests, and publishing decision-ready forecasts.
Read the methodology →Project 02 · Scientific AI
Scientific methods, operationalized
A platform proof of concept that converts experimental workflows into governed, versioned, observable services consumable by scientists and autonomous tools.
Explore the platform →Research standard
Every claim should remain inspectable
Each publication identifies data provenance, study design, baselines, primary measures, uncertainty, limitations, and reproducibility artifacts.
Review the standard →The 64-city research program
Scale deliberately, publish transparently
Program progress
Two markets complete. A reusable system is taking shape.
The objective is not simply to publish 64 forecasts. It is to build a comparable evidence base across markets—using consistent evaluation, clear local context, and a production workflow that can scale without sacrificing rigor.
2 / 64 cities published
Next phase: validate the publishing workflow across additional Northeast markets before expanding regionally.
01
Boston, MA · 02114
Forecast and box score
PublishedForecast and box score
02
Providence, RI · 02903
Forecast and box score
PublishedForecast and box score
03
Next Northeast market
Data qualification
Up nextData qualification
04
Regional expansion
Standardized market comparisons
PlannedStandardized market comparisons
Research partnerships
Bring a market, dataset, or decision problem.
We are building partnerships around local data access, independent model validation, sponsored city research, and applied machine-learning systems. Every engagement starts with a defined question and an evidence plan.
Start a partnership conversationData partnersImprove coverage, granularity, and local context.
Research partnersCo-design studies and independently review methods.
City sponsorsSupport a transparent market forecast and publication.