Notes on file

Blog

  1. 2026-11-16

    Field notes: the afternoon we almost shipped a feature that just reproduced zip code

    A field-notes account of catching feature leakage: a "neighborhood quality" variable that turned out to just be zip code in disguise.

  2. 2026-11-16

    What is a kickout rate in AVM performance monitoring?

    A plain explanation of kickout rate in AVM monitoring, how it ties to confidence score thresholds, and why fallback to appraisal climbs on certain parcels.

  3. 2026-11-09

    How to generate adverse action reason codes from a learned imagery embedding in an AVM

    A data-science walkthrough for turning an opaque image embedding feature in an AVM into ECOA-compliant adverse action reason codes.

  4. 2026-11-09

    Proxy discrimination and fair lending review for imagery features

    What proxy discrimination means for AVM features, and how to run a fair lending review before a neighborhood imagery input goes into production.

  5. 2026-11-02

    Hedonic pricing model vs repeat-sales index: which one actually drives an AVM

    Hedonic and repeat-sales models solve different problems. Here's which one actually underpins AVM point estimates, and where imagery fits.

  6. 2026-11-02

    The refresh nobody lines up in the budget

    A field-notes look at what changes on a parcel in twelve months, and why AVM teams underbudget the imagery refresh that catches it.

  7. 2026-10-26

    Desktop appraisal vs. hybrid appraisal: what each one actually inspects

    A field-by-field breakdown of what desktop and hybrid appraisals inspect, and why neither fills the curb-appeal gap in your model.

  8. 2026-10-26

    What is UAD, and how do condition fields get populated?

    UAD standardizes appraisal fields like C1-C6 condition ratings, but those values still come from one appraiser's eyes. Here's where the gap sits.

  9. 2026-10-19

    Field notes: the comp that matched on every field and looked nothing alike from above

    A comp matched every tabular field and nothing on the ground. Curb-appeal and context signal belongs inside the model, as a direct input.

  10. 2026-10-19

    FSD in an AVM: what moves it when you add a feature

    What forecast standard deviation measures in an AVM, why adding a feature doesn't automatically tighten it, and how to test lift before you ship.

  11. 2026-10-14

    Backtesting a curb-appeal signal against repeat-sales pairs

    How to validate a new curb-appeal or parcel-context feature using repeat-sales price pairs before it goes into a production AVM.

  12. 2026-10-14

    What GSD do you need to score curb appeal from satellite imagery?

    A data scientist's answer to the GSD question: what resolution actually resolves curb-appeal and parcel-condition signal for an AVM.

  13. 2026-10-13

    How to join a per-parcel embedding vector to your AVM's record IDs

    A practical walkthrough of joining a per-parcel embedding file to your AVM's record IDs, including key normalization and refresh handling.

  14. 2026-10-13

    What counts as a deferred-maintenance signal in curb-appeal imagery

    A working definition of deferred-maintenance signal in property imagery, what shows up at sub-0.5m resolution, and why tabular fields miss it.

  15. 2026-10-07

    Adding a new data source to an AVM without a full retrain

    A practical path for folding a new data source into a live AVM: feature store conventions, shadow scoring, and when a full retrain is warranted.

  16. 2026-10-07

    How to validate a new AVM feature without appraiser labels

    Appraiser sign-off is slow and expensive. Here's how data science teams validate a new AVM feature using sale prices and residuals instead.

  17. 2026-10-07

    Satellite imagery vs. street-level photos for property condition signal

    A practical comparison of overhead imagery and street-level photos as property condition inputs for AVM pipelines, and where each one breaks down.

  18. 2026-10-07

    What is curb appeal scoring for automated valuation models?

    A plain-language look at curb appeal scoring in AVMs: what it measures, why tabular fields miss it, and how it slots into a valuation model.

← Back to AVM Imagery