Document AI · CRE Lending

AI STR Report Extraction & Financial Analysis

Uptiq's Document AI extracts monthly and trailing-twelve-month occupancy, ADR, and RevPAR for the subject hotel along with its occupancy, ADR, and RevPAR indexes against the competitive set, landing structured performance data in the underwriting model beside the property operating statement.

95%+
Extraction accuracy
41%
Faster underwriting cycle time
100+
Native integrations

Trusted by financial institutions across banking, lending & credit

CRE LendersCommunity BanksCredit UnionsCommercial LendersNon-Bank Lenders

What is a STR Report?

An STR report benchmarks a hotel's occupancy, average daily rate, and RevPAR against a defined competitive set of nearby properties, giving a lender the index figures that show whether the subject is taking share or losing it.

Uptiq's Document AI extracts monthly and trailing-twelve-month occupancy, ADR, and RevPAR for the subject hotel along with its occupancy, ADR, and RevPAR indexes against the competitive set, landing structured performance data in the underwriting model beside the property operating statement.

Occupancy, ADR, and RevPAR each carry a separate index, and a healthy RevPAR index can mask rate buying that cost the hotel share

Intake / ApplicationUnderwritingClosing / DocumentationServicing / Monitoring
Occupancy, ADR, and RevPAR each carry a separate index, and a healthy RevPAR index can mask rate buying that cost the hotel share
Competitive set membership is chosen by the subscriber, so an index means nothing until the properties behind it are read
Current month, year-to-date, and running twelve-month columns sit side by side, and pulling the wrong one misstates the trend
Month columns run across dense multi-page grids, so copy-paste into an underwriting model loses row alignment
Comp set revisions and different pull dates mean two reports on the same hotel will not reconcile line for line

AI agents built for str report processing

Uptiq's Document AI extracts monthly and trailing-twelve-month occupancy, ADR, and RevPAR for the subject hotel along with its occupancy, ADR, and RevPAR indexes against the competitive set, landing structured performance data in the underwriting model beside the property operating statement.

1
Classification
STR Report documents are classified and matched to the correct extraction schema automatically.
2
95%+ accuracy extraction
Every field is extracted with full data lineage back to the source page.
3
Automatic ratio & metric calculation
Key financial metrics are calculated automatically from the extracted figures.
4
Delivery into your LOS
Structured output flows into your existing LOS — 100+ native integrations, no rip-and-replace.

The result: your team spends time on judgment calls, not re-keying str report data — measured across production deployments.

36%
Less spreading & extraction time
41%
Faster underwriting cycle time
95%+
Extraction accuracy
5 days
To first production deployment

Fields Uptiq extracts from a STR Report

A sample of the structured fields Uptiq's Document AI captures from this document type.

FieldExample
Subject Occupancy (T-12)68.4%
Subject ADR (T-12)$142.75
Subject RevPAR (T-12)$97.64
Occupancy Index104.2
ADR Index96.8
RevPAR Index (Penetration)100.9
Competitive Set5 hotels, 612 rooms
Period CoveredJan 2025 – Dec 2025
Sample structured output
{
  "subject_occupancy_t_12": "68.4%",
  "subject_adr_t_12": "$142.75",
  "subject_revpar_t_12": "$97.64",
  "occupancy_index": "104.2",
  "adr_index": "96.8",
  "revpar_index_penetration": "100.9"
}

What changes when this runs automatically

STR Report Extraction, Not Just Storage

Uptiq's Document AI extracts monthly and trailing-twelve-month occupancy, ADR, and RevPAR for the subject hotel along with its occupancy, ADR, and RevPAR indexes against the competitive set, landing structured performance data in the underwriting model beside the property operating statement.

Handles the Real-World Complexity

Occupancy, ADR, and RevPAR each carry a separate index, and a healthy RevPAR index can mask rate buying that cost the hotel share

Consistent, Structured Output

Current month, year-to-date, and running twelve-month columns sit side by side, and pulling the wrong one misstates the trend

95%+ Accuracy, Full Audit Trail

Every extracted field traces back to its source page — examiner-ready documentation, every time.

Integrates with Your LOS

100+ native integrations across loan origination systems, cores, and workflows. No new infrastructure.

Scales Without Adding Headcount

Process more str report volume with your existing team as application volume grows.

Results from 150+ financial institutions in production

36%
Less spreading & extraction time
41%
Faster underwriting cycle time
95%+
Extraction accuracy
5 days
To first production deployment

Results represent aggregate outcomes across production deployments. Individual results may vary.

From str report receipt to structured output

STR Report arrives at intake

The str report arrives via email, portal, or upload. AI classifies it automatically.

AI extracts key fields

Fields are extracted at 95%+ accuracy with full data lineage back to the source page.

AI calculates key metrics

Derived metrics and ratios are calculated automatically from extracted figures.

Delivery into your LOS

Structured, extracted data lands in your existing loan origination or servicing system.

What teams ask before they start

STR Report AI is Uptiq's Document AI capability for classifying and extracting str report documents, turning them into structured, underwriting-ready data instead of a PDF to read manually.
Uptiq's Document AI is certified to 95%+ extraction accuracy by a Knowledge Team of former underwriters, bankers, and analysts, with every extracted field tracing back to its source page for audit purposes.
No. STR remains the data source and you keep your own subscription — Uptiq reads the report your borrower or your team already receives and structures its figures. Uptiq is not affiliated with STR or CoStar and claims no partnership, license, or endorsement.
Yes. All three indexes are extracted per period alongside the subject's absolute occupancy, ADR, and RevPAR, so penetration above or below 100 becomes a tracked field in the underwriting model instead of a sentence in the credit memo.
Yes. Extracted RevPAR and occupied room nights are placed next to rooms revenue and occupancy from the operating statement, so a variance between what the borrower reports and what the benchmark measures is visible. Explaining that gap stays underwriting work.
Yes. Uptiq connects to 100+ integrations across loan origination systems, core banking platforms, and underwriting workflows — the agent layer sits above your existing stack with no rip-and-replace required.

See STR Report AI in Action

Book a 30-minute session. We'll run a live extraction demo on your own str report documents.

STR Report AI, done right.

150+ financial institutions run Uptiq's AI agents to process financial documents and accelerate underwriting.