Case study, 2026

RentFair Miami

Evaluates whether a lease renewal offer is fair against live rental market data.

The demo was retired in November 2026; the method is described below.

A tenant receiving a renewal offer has no straightforward way to judge it. Comparable listings exist but are scattered across sites, are not filtered to genuinely comparable units, and go stale quickly.
Live listings are pulled from the RentCast API and filtered to comparable units by bedroom count, location, and unit characteristics, with automated ingestion refreshing the comparison set rather than relying on a stored snapshot.
A renewal offer is placed against the current distribution of comparable rents, turning a number presented without context into one that can be evaluated.

Freshness over volume

Rental comparisons decay quickly. A larger set of stale listings is worse than a smaller current one, so ingestion refreshes automatically when the data ages rather than on a fixed schedule.

Stack

PythonRentCast APINetlify

Machine Learning and Decision Models

Forecasting, risk, fraud and ranking models trained on your data, delivered as applications your team uses. This case study is one instance; the same method is applied to your data and workflow.

About Machine Learning and Decision Models   All case studies

Tell us the workflow. We show you the system.

Describe the process and the data. A reply comes within one business day, from the engineer who would lead the work.