407 Random Road

Method and limits. MSI v0.2-baltimore-2026-09 weights eighteen public signals by how much each one changed the recorded five-month arm’s-length transfer rate across all 180,000 residential parcels in Baltimore City, using only dated records (SDAT transfers, vacant-building notices, tax-sale lists, permits and 311 requests) so no signal reads the buyer’s state, checked on a holdout the model never saw (the top 0.5% of homes by score sold at 4.5x the citywide rate, the top 1% at 4.2x).: use / occupancy permit +24, vacant-building 311 request +17, alteration / rehab permit +14, building-permit 311 complaint +13, high grass and weeds 311 request +12, bought since 2024 +10, abandoned-vehicle 311 request +6, trade permit +5, sanitation / dumping 311 request +5, on the 2022 or 2023 tax-sale list +4, vacant building notice +3, demolition permit +3, exterior permit +2, structure-maintenance 311 request +2, permit valued at $25,000 or more -3, owned for 20 years or more -4, rodent 311 request -7, vacant building notice issued this year -11. The "in 100 homes" figure is the model's fitted probability for this combination of signals. It describes homes like this one in aggregate; it is not a claim about this owner's intentions, and it is not LienSuite's paid deal score.