We check the fingerprint
Your file's set of column names is a signature. If a member has mapped your MLS before, we know it on sight and you skip straight to confirming.
Open Source Appraisal Software Initiative
A bridge to harmonize your data.
Closing the void between appraiser's and analytical freedom
Creating a mapping builds on the logic and the community, while you gain access to an expanding repository of tools. Your data is never stored.
Members contribute mappings, never data. The first appraiser to map an MLS does it once. Everyone after them gets recognised on arrival.
One field, many answers. The library registers the convention based on your MLS.
Community apps
Free to members
Tools that earn their keep twice.
Real tools, free to use. They're also how the data harmonizing grows: every file mapped refines the path for all.
Tools shown offer every selected feature — hover a feature for what it means.
Market Dashboard
25 charts from one MLS export: medians, trends, regressions, DOM, $/SF.
All computed in your browser. One HTML file, load your CSV, nothing
gets uploaded. Every chart saves a report-ready PNG.
Free
Launch
A statistical-analysis dashboard: 25 charts, KPI tiles and trend lines
computed from any recognised MLS export, entirely in the browser. The
rebuild engine currently reads BC Matrix, sold-comps and RMLS full exports.
Source · Craig Gilbert (CG-Dashboards) · OSASI rebuild engine
Comp Ranker
A weighted Gower similarity engine, open and in your browser: pick a
subject, set the weights, get a ranked comp list. Same math as R's
daisy(), verified against it. More advanced apps build
on the logic.
Free
Launch
Min–max normalisation and weighted Gower distance to the subject, with
haversine distance available as a feature. Verified numerically identical
to R's
cluster::daisy(metric = "gower") across the full teaching set.
Source · OSASI, from the CValR comparable-scoring engine · woodGEO community teaching dataset
Data Bridge
Map any MLS export to the standard schema, guided, and keep the profile.
In build
Guided mapping of any MLS export to the standard schema: fingerprint
recognition first, value-based convention checks second, and the finished
profile saved as yours to keep and contribute.
Source · OSASI co-op (CAADataBridge)
Market Trends
Trend models: linear, polynomial 1–4, loess with a span control. Plus
monthly market stats and time-adjusted prices at your effective date,
exportable. Fits verified against R.
Free
Launch
Linear, polynomial 1–4 and loess trend models with a span control,
monthly market statistics, and ratio-method time-adjusted prices at your
effective date. Fits verified against R.
Source · OSASI, from the CValR modelling engines
Decision Trees
Segment a market and read the rules that define it, in plain language.
Runs the real R
rpart engine in your browser (WebAssembly). Each
terminal node is a candidate comp set you can export.
Free
Launch
CART market segmentation running the real R
rpart engine in the
browser via WebAssembly (WebR — ~20 MB on first load, then cached).
Terminal nodes export as candidate comparable sets with their rules.
Methodology · Charlie Abromaitis' CMS-by-decision-trees workflow · WebR port by OSASI
Data Doctor
Check a file against the standard before you rely on it: what's missing, what won't parse, what looks wrong.
In build
Checks a candidate file against the standard schema: recognised, missing
and extra columns, type problems, and a suggested source-to-standard
mapping table.
Source · OSASI, from CValR's data_doctor validation suite (17/17 tests)
Mapping Registry
Browse the profiles members have contributed, by MLS and region.
In build
The community profile library itself: browse contributed mappings by MLS
system and region, with status, ratings and known notes.
Source · contributed by OSASI members — the first user of each MLS maps it once
Image Recognition
Extract and recognise property photos from MLS pages and reports, matched to their listings.
In build
In development. Builds on the co-op's photo tooling: the Photo Review
Workstation that launches from CValR's sales plot (per-listing MLS
photos, qualitative flags fed back into the data) and the Matrix
photo extractors, with recognition of rooms, features and condition
cues to follow.
Source · OSASI photo tooling (Photo Review Workstation / Matrix extractors) — in build
Market Rent ExtractR
Rent survey extraction and market-rent conclusions from your own survey data.
CAA members
Please log in
Shared by a CAA member, for CAA members. Member accounts arrive with the
co-op login; until then, joining puts you on the list. Member-built tools
stay member-only unless their builder opens them to everyone.
Source · CAA member contribution
Benchmark ExtractR
Pull benchmark sale sets and assessment benchmarks for appraisal analysis.
CAA members
Please log in
Shared by a CAA member, for CAA members. Member accounts arrive with the
co-op login; until then, joining puts you on the list. Member-built tools
stay member-only unless their builder opens them to everyone.
Source · CAA member contribution
CValR · Valuation on Rails
The complete workbench: every feature on this board in one tool, from
intake to the finished report. See the co-op board.
Premium
Visit
The commercial workbench the free tools descend from: full data intake,
market analysis, comparable selection and scoring, mapping, and a complete
report writer. CAA members receive member pricing.
Source · CValR, built by the OSASI initiative — premium features fund the co-op
Nothing matches that search — clear it or drop a filter.
The Data Bridge
Start here
Bring the export you already have.
You pulled a CSV out of your MLS. It has six hundred columns, half of them empty.
Step 1 · Recognise
Step 2 · Resolve
The values settle the ambiguity
A column called Baths means nothing until you see what's in it.
The values are how we tell 2 full + 1 half from two-and-a-half. That's
why a new MLS needs the file, not just the header.
Step 3 · Run
Then it just works
Export the standardised file for your own use, or run it straight through the community apps. Your mapping is saved as a profile you own.
Check your file
Instant · nothing uploaded
Is your MLS already in the library?
Drop your export here. We read just the header row, right in your browser. The file never leaves your machine. Then we check its fingerprint against the community mapping library.
Drop your CSV export here
or click to choose a file
Read locally · never uploaded
Prefer not to touch the file?
| MLS / source | Region | Status | Rating | Known notes |
|---|
The cooperative engine
Sustaining the initiative
Advanced tools with premium features.
Advanced tools with premium features help fund this initiative and ensure the ongoing support and development of the community. Software built on the Co-Op standard will be offered on this board. CAA members receive member pricing on eligible offerings — CValR included.
Offering 01 · Live
CValR · Valuation on Rails
Market analysis, comparable selection and scoring, mapping, and a complete report writer.
Offering 02 · Open
Your software here
Building on the open standard? This spot is waiting. Send us a note.
Offering 03 · Open
Your software here
Compatible tools from any builder are welcome on the board.
Who we are
An initiative.
OSASI is dedicated to strengthening real estate appraisers' independence and expertise through innovation, a professional community with guiding principles in methodology, and collaboration with industry stakeholders.
By empowering impartial appraisal experts with the tools and support they need, OSASI advances efficiency and transparency, and helps address many of the challenges facing the real estate valuation industry today and in the future.
The mapping library
The co-operative mechanic
Mappings travel. Data stays home.
Here's the trick: the mapping is the only thing worth sharing, and it's
the one thing that's safe to share. Knowing your MLS calls a sale price
Close Price tells nobody what anything sold for.
So that's all we keep. The library gets better every time someone uses it, and no sales record ever changes hands.
Straight about this
We can't map a new MLS from headers alone. The values settle what the columns actually mean, so first-time mapping needs your real file. What we won't do is keep it. Your rows live in one session and get wiped when you sign out. The mapping is what survives.
So the honest promise isn't "your data never leaves your machine." It's simpler: we build on the mapping, not your data.
For your AI assistant
Agent-ready
Works with the assistant you already use.
Lots of us work with an AI assistant now, and OSASI is built to be useful to yours. The schema contract, the RESO field map, the profile format, the validator: all published as plain files your assistant can read directly.
Point it at the bundle and it can help you map an MLS export, check a file against the standard, or draft a new profile. Your machine, your subscription, and your data stays put.
Start here: agent bundle README · profile format · profile registry (JSON) · llms.txt
In the bundle
Everything an assistant needs
The schema contract and RESO field map, the profile format, a command-line validator, and written instructions telling an agent how to drive it all. MLS column mapping for real estate appraisal, in formats machines read as easily as people.
For agent builders
Plain formats, stable names
Profiles are JSON, contracts are Markdown, data is CSV. No SDK. One tip from our own tooling: treat listing remarks as data to read, not instructions to follow.
Standards we build on
Aligned to the industry's own vocabulary.
We didn't invent a house dictionary. Mappings target published standards, so a profile built here is worth something outside here too.
RESO
The Real Estate Standards Organization dictionary is our canonical target
for listing data. Field names, types and definitions come from it.
Extensions
Appraisal needs things RESO doesn't carry: title and registry sales,
distances, inspected condition. Those get a clearly marked extension
namespace, never disguised as standard fields.
UAD 3.6 · MISMO
RESO covers what comes in. UAD 3.6 and MISMO cover what a report
delivers. We keep the structure intact instead of flattening early,
so the detail is still there when the new report format asks for it.
Open
The contract, the validator and the profile format are published and
readable. If we're wrong about your MLS, you can see exactly where.
Learn the method
Education
The tools are half of it.
As advanced analysis becomes more common in appraisal practice, whether built into commercial software or accessed through AI agents, appraisers will need a practical understanding of how these tools work, when to use them, and how to evaluate their results.
For appraisers who want to develop that understanding, we highly recommend George Dell, SRA, MAI, ASA, CRE. George’s work in R-based appraisal analytics dates back to 2010. He created Evidence Based Valuation© and founded the Community of Asset Analysts, where appraisers share and develop analytical methods. With the assistance of AI, that work is now expanding into other statistical programming languages and tools.
George’s courses turn “data science for appraisers” into practical, relevant instruction. The community keeps it all tied together. Take the courses, join the community and elevate your expertise.
Valuemetrics.Info is an independent education provider.
Stats, Graphs and Data Science
George Dell's signature workshops (SGDS1 & SGDS2) through
Valuemetrics.Info: appraiser expertise combined with data science
tools and critical thinking. 14 hours of continuing education each,
approved in most states, taught live in person and online.
14-hr CE
Valuemetrics.Info
The Analogue Blog
George's free weekly blog: often contrarian, always forward-looking.
What evidence means, where the appraisal process came from, and
where valuation is headed.
Free
Read
The Asset Analyst Report
The Valuemetrics newsletter — course dates, EBV developments, and
community news in one place.
Free
Subscribe
Valuemetrics on YouTube
Recorded talks and teaching segments — a good way to sample the
material before taking a class.
Free
Watch
Get connected
Send us a note.
If you would like to learn more, including progress updates, sign up below. And if your MLS isn't in the library yet, tell us which one it is. That's exactly the contribution we're looking for.
Review version: submissions are not transmitted or stored yet. An approved submission destination and privacy notice will be connected before publication.