Stratyfy

Take the engine away and nothing remains. The proprietary Probabilistic Rules Engine is the entire product, applied across credit risk assessment, fraud detection and bias mitigation. The company's whole argument is about the properties of a particular kind of model rather than about workflow around one. Interpretability is architectural rather than a layer added afterwards, since decisions are produced as readable probabilistic rules in the first place. That is a modeling choice, not a reporting feature.

The human does not review the model's output; the human writes part of the model. The engine pairs data driven inference with human expertise so that lenders can incorporate market conditions and emerging risk factors directly into it. The company describes the approach as combining automated data evaluation with the wisdom of real people.

Because the model is expressed as interpretable rules rather than weights, a credit officer can read what it will do before it does it and change it, which is oversight before the decision rather than after. That also addresses drift, since a person can inject a market shift the training data has not yet seen.

Interpretability by construction makes the model its own documentation, which is a stronger position than any post hoc explanation technique because there is no second system approximating what the first one did. Predictions of poor loan performance are stated to be explainable to customers, regulators and other stakeholders on the basis of clear rules, and a comparative study is published showing two metrics moving in opposite directions at once, more qualified applicants identified alongside a lower bad rate, which is the correct way to demonstrate a genuine improvement rather than a shift in risk appetite. The ability for lenders to write emerging risk factors into the model directly addresses the drift problem that degrades credit models between retraining cycles.

$10 million was raised in a round co led by the venture arm of a large United States bank and an inclusive investing fund, which was investing for a second time. A major core banking and payments provider, a community bank focused venture firm and a diversity focused fund also took part. Backing from both a bank and a core provider functions as distribution as much as capital.

A published comparative study shows the engine identifying nearly twice as many pre qualified applicants as traditional methods used by small and midsize banks while lowering the overall bad rate. No institution is named as a customer, and the study is the company's own rather than independent.

There is no data boundary statement. The architecture points toward containment without stating it, since the engine is configured per lender with that institution's own experts writing rules into the model. That implies a per customer configuration rather than a single shared model. What is not addressed is whether performance data, learned rules or outcomes from one institution inform the engine deployed at another. Many of the small and midsize banks it sells to compete in the same local markets.

Credit application and performance data on individual borrowers is the payload, processed to reach decisions that determine access to credit. The fraud and compliance modules extend that to behavioral and screening data. No data protection agreement, retention schedule, subprocessor list or deletion commitment is published. Nothing describes handling, retention or what happens to applicant data where a decision is declined.

Investment from a large bank's venture arm and from a core banking provider implies diligence at an institutional standard, yet none of that assurance is published. There is no attestation, certification, trust center or enumerated framework. That is the obstacle a small bank's vendor management process will hit first, for a product otherwise designed around regulatory defensibility.

No supervisor, statute or instrument is named, though the positioning engages the regime directly. Solutions are described as delivering automation without new operational or regulatory risks, and explanations are stated to serve regulators as one of three audiences alongside customers and internal stakeholders. That addresses the adverse action and model explainability regime by function without ever citing it. For a product whose principal claim is regulatory defensibility, naming the rule its interpretability satisfies would be the natural next step.

Bias mitigation is a named product line rather than a claim attached to one, sold alongside credit risk and fraud detection. The founding argument is stated plainly: transparency and controls are essential so that the biases of our past do not encode into our future. That is the direct counter to the institutional memory proposition other vendors sell.

The published study supports it in the right direction, showing nearly twice as many qualified applicants identified while the bad rate fell and the addressable market expanded by 70 percent. That is access widening with risk reduced rather than traded. Two investors are inclusion focused funds. The missing half is outcome data by protected characteristic, which is not published, so a company selling bias mitigation does not show the demographic evidence that would demonstrate it works.

Predictions such as poor loan performance are stated to be clearly explainable to customers, regulators and other stakeholders on the basis of interpretable rules, and the customer is listed first. Credit vendors usually leave a declined applicant with no reason given and no route to challenge the inference. Interpretability by construction gives them both: a decision expressed as rules a person can be shown, disputed against and corrected on. No commercial guarantee or indemnity accompanies it.

The engine is the company's own proprietary technology, which shortens the chain at the decisive point and means no external foundation model sits inside a credit decision. Nothing else is disclosed. No data source is named for the credit, fraud or screening inputs the models consume, and no bureau or alternative data provider appears. There is no public hosting arrangement or subprocessor list.

A major core banking and payments provider sits on the investor register, which implies a distribution relationship and possibly a technical one. Nothing published describes it, and no integration is named on either side. No loan origination system, core platform, bureau connection or developer documentation appears, so an institution cannot establish what deployment involves.

Where applicant data is processed and held goes unanswered: no hosting provider, region selection, residency commitment or private deployment option is published. Exposure is domestic and therefore simpler than for international vendors. A bank outsourcing credit decisioning is nonetheless expected by its examiners to establish that location.

Stratyfy publishes no pricing, packaging or basis of charge. One cost argument is made, and it fits the buyers. The platform is positioned as unlocking data driven decisioning without the need for in house data science expertise, which for a small or midsize bank is the largest cost of adopting machine learning at all. That describes what is avoided rather than what is charged.

Three functions are served by the same engine, spanning credit risk decisioning, fraud detection and compliance, which follows from the technique being general rather than task specific. The buyer focus is stated clearly as financial institutions, with small and midsize banks named as the comparison group in its own research. The no data scientist required positioning points at institutions without internal modeling teams. The limits are geographic and scale: no international footprint is evidenced, and the largest institutions with their own model risk departments are not the target.