Homecastr - AI home price forecasts on a map
Claims 8.0% error vs Zillow's 8.4%, but hard to verify without methodology.

Diffusion models forecast home price ranges, claiming better accuracy than Zillow's baseline.
Real estate investors and homeowners
Zillow · Redfin · HouseCanary
I used an FT-Transformer & Schrödinger Bridge diffusion model, trained on 20+ years of ACS microdata & 8 FRED macro series.
This approach beats Zillow's baseline on 1-year held-out error, achieving 8.0% vs Zillow's 8.4%.
Happy to answer questions about the architecture or anything else!
Claims 8.0% error vs Zillow's 8.4%, but hard to verify without methodology.
Beating NWS forecasts with a 22M model on home sensor data is genuinely impressive.
Diffusion model generates endless novel climbing routes for home walls—solves real boredom.
Parallel token decoding beats autoregressive LLMs on throughput, if the math holds up.
Another AI crypto prediction site when nobody can reliably predict crypto prices.
BLS wage data is a smart anchor, but Angi and Thumbtack already dominate this space.