OpenGrade

One bank connection.
Verified identity, scored trust.

The trust layer for Open Finance — prove a person is real and price their financial risk, without storing a single document.

Real-person verification 0–100 trust score Zero data stored
Amit Zamir · Noa Elmakies · May Gurevich · Hai Tal opengrade.cs.colman.ac.il
The problem

Trusting a stranger is still a guess.

Landlords, lenders and marketplaces have to judge people they've never met — with tools that are opaque, invasive, or trivial to fake.

Black-box scores

A single number with no reasons. No factors, no recourse — and nothing you can act on.

Invasive paperwork

Statements and IDs over-share a person's entire financial life — and are still forged every day.

Fakes & bots

Synthetic identities and bots sail through sign-up. You genuinely can't tell who's a real person.

OpenGradeProblem
The product

Verify the human. Score the risk.

A consented bank login proves a unique, real person — then turns their real banking behavior into a 0–100 trust score. Read in memory, deleted the instant it's scored.

Verify mode

Just the connection proves a real person. We read nothing, store nothing.

Score mode

7 behavioral factors → a 0–100 score, then the raw data is deleted.

85
Green · Good Renting · real engine output
Income Stability100
Balance Health70
Recurring Pmts50
Savings63
Expense Disc.55
OpenGradeProduct
Why now · market

Open Finance just opened two markets.

Israel's regulated bank API (PSD2-style) makes consented, real-time bank data available — and by design returns zero identifying info. That's perfect for behavior-based trust and for proving personhood. It's live, and no incumbent owns it.

Financial trust

Deep score for high-stakes decisions.

RentingLendingHiringB2B partnerships

Identity & personhood

Lightweight, high-volume verification.

MarketplacesDating & socialP2PKYC onboardingBot defense
OpenGradeWhy Now & Market
Why us

Not a demo — built, validated, live.

Learned, not guessed
Factor weights are derived by ML per use case — 2,500 synthetic applicants, non-negative regression.
Validated on real data
Benchmarked on UCI German Credit (1,000 records) — beats uniform & prior baselines on 4 of 5 use cases.
Zero-PII by design
Raw bank data is deleted in the same DB transaction that saves the score. Provable, not promised.
Deployed & running
Live on a real bank integration with CI — a working product, not slideware.
7explainable
factors
5use-case
models
0PII / raw data
stored
<5mincreate check
→ score
OpenGradeWhy Us
Business model

Pay per check. No subscription.

Customers buy credits up front and spend one per check — for a Verify or a Score. Bigger packs lower the per-check price; declined checks are refunded.

Lean

Marginal cost per check ≈ one Open Finance call

Two engines

High-volume Verify + premium Score, same credits

Expandable

Usage-based API for platforms & partners

CREDIT PACKS

PRICE · PER CHECK

Starter10 credits₪40₪4.00
Standard25 credits₪90₪3.60 · −10%
Pro50 credits₪160₪3.20 · −20%
Enterprise100 credits₪280₪2.80 · −30%

Prices served live from the API · revenue scales linearly with checks

OpenGradeBusiness Model
Team & ask

Verify a human. Score the risk. Store nothing.

Amit ZamirBackend & architecture
Noa ElmakiesProblem & market
May GurevichProduct & design
Hai TalScoring & validation

CS finalists in the Fintech & Algorithmic-Trading track — we designed, built, validated and deployed the full platform.

What we're looking for — pilot partners in rentals and online marketplaces, to run real checks and shape the Verify API.

OpenGrade

See it live · opengrade.cs.colman.ac.il

Let's talk
OpenGradeTeam & Ask