AiCurio

A loan database is what remains once the model is removed. A deep learning artificial neural network is the entire product, described as the first commercially available machine learning model for residential mortgage loan performance and cash flows. Everything the company sells is an application of it. Life of loan forecasting and portfolio surveillance are readouts from the same model, and so are loss mitigation prioritization and refinance targeting. There is no rules based alternative that produces loan level monthly cash flow projections eight years forward.

The system recommends and a servicer decides, which is stated consistently in the company's own language of model recommended actions, prescribed loss mitigation and default strategies, and guidance for month to month life of loan decisioning. That framing keeps the accountable institution in the decision, which matters because the downstream actions include whether to pursue loss mitigation with a struggling borrower.

What is not described is any threshold, confidence indication or review point, and nothing states how a servicer should treat a prediction that conflicts with what it knows about a particular borrower's circumstances.

The accuracy claim is well specified, not merely large. It names the unit, the individual loan, and the quantity, all monthly cash flows including principal, interest and servicing costs. It names the horizon, up to 96 months forward, and the logical entailment: predicting every cash flow necessarily means predicting every default and prepayment at the same accuracy. Model validation is stated as completed. The training window is the strongest element, and it is rarely available.

It covers 22 years of loan and payment history spanning the housing collapse and its recovery, so the model has observed a complete credit cycle rather than a benign one, which is the single most important property for a mortgage default model. The published figure rises from 96 to 97 to 98 percent across sources over time, with no explanation of what changed.

Three commercial relationships are named, with executives quoted. An outsourced mortgage services provider selected the platform for predictive analytics, and its chief executive noted the depth of data and expected it to serve his own banking and lender clients. A mortgage solutions firm launched a product built on it, describing the engine by name as the base of its own offering. A third arrangement pairs the model with a title decisioning product through an affiliated platform.

The training data is the other evidence: more than 100 million loan records and several billion monthly payment records across 22 years. What is missing is commercial scale. No funding, revenue, portfolio volume or customer count is disclosed, and most published coverage clusters around 2020 with one later confirmation.

The model is trained on an industry wide historical dataset rather than on any one customer's book, which limits the usual concern. No data boundary statement is published. The platform also runs inside other vendors' products as an embedded engine, so portfolio data flows through arrangements with intermediaries as well as directly. Nothing states whether a customer's own portfolio data contributes to model improvement, what happens to it when a contract ends, or how the embedding partners' obligations are constituted.

The dataset holds monthly payment histories for more than 100 million American mortgages spanning 22 years, with up to 300 data elements attached to each monthly record. That is a detailed longitudinal account of how tens of millions of households met or missed their largest obligation. No data protection agreement or retention schedule is published, and there is no subprocessor list or sourcing disclosure. Sources are described only as public and private, and nothing states what permissions underpin the private portion or how borrower level records are held.

Multiple partners have embedded or resold this engine inside their own products, yet no attestation, certification, trust center or enumerated framework is public. The partner arrangements imply vendor assessment has been passed, and they create a further obligation, since those partners inherit the security posture of a component they did not build. For a company holding payment histories on over a hundred million mortgages, a published control set is the obvious missing artifact.

The regulatory grounding is in the leadership rather than in a citation. The chief executive is a consumer finance and securitization attorney recognized nationally in mortgage and banking law, with three decades representing financial institutions in securitization transactions exceeding $1 trillion. The company is run by someone whose profession is the rules this product operates under. Fair lending testing is named as a completed exercise, which engages the relevant regime directly. The gap is that no statute, regulation or supervisor is identified anywhere, so a buyer cannot see which obligations were tested against.

The company states that it completed model validation and fair lending testing, and that the model passed without any statistically significant bias or economic impact. Naming the test and reporting the result is materially more than describing an intention. Three limits matter. The claim is self reported, with no methodology, validator or date published. There is no demographic outcome data.

And one use case carries its own exposure: the model identifies which borrowers should be targeted for refinance marketing, and deciding who is offered better terms is a fair lending question in the same family as deciding who is approved.

Beyond the accuracy claim itself, which is asserted rather than warranted, there is no published guarantee, indemnity or falsifiable commitment. The institutional customer can test predictions against realized performance over time, which is real recourse in a forecasting product. The borrower has none and is materially affected. The model prescribes loss mitigation and default strategy for individual loans and determines who receives refinance offers. A household's treatment in difficulty and its access to better terms both turn on a prediction it will never see, cannot contest and is not told about.

The input side is described by category with useful specificity, covering loan, property and market data from public and private sources, supplemented by economic and housing data, and quantified at more than 100 million loan records and several billion payment records with up to 300 elements per monthly record. That tells a buyer the shape and scale of the evidentiary base even without individual suppliers named. The model is the company's own.

What is not disclosed is any provider behind the private data, which matters because licensing terms on loan level performance data determine what the resulting model may lawfully be used for, and no hosting or subprocessor arrangement appears.

The most substantive integration is embedding rather than connection. A mortgage solutions provider built and launched its own analytics product with this engine named as its base, which means another vendor staked its product on the model and disclosed the dependency. A second arrangement combines the predictions with a title clearance decisioning product so that originators see credit, collateral and title readiness together.

A third supplies the analytics to an outsourcing provider serving its own bank and lender clients. Three routes to market through partners is a real distribution position. No direct integration into servicing or loan management systems is published, and there is no public developer documentation.

AiCurio does not say where it hosts, and publishes no region selection, residency commitment or private deployment option. Exposure is domestic and therefore simpler than for international vendors. The material involved, though, is borrower level payment history at very large scale. It is held on behalf of regulated servicers and investors whose own examiners would expect the processing arrangement to be documented.

The return is published and the cost is not. Model recommended actions can improve portfolio cash flows by more than 100 basis points annually, the company says, and more on distressed pools. No pricing, packaging or basis of charge is public. Nothing states whether charge falls per loan analyzed, per portfolio, by subscription or through the partners who embed the engine.

The buyer set spans the full chain of parties holding mortgage cash flows. It covers loan owners, servicers and investors, along with originators, banks and credit unions, and the company describes its users as all owners and servicers of the mortgage cash waterfall. Instrument coverage reaches beyond whole loans into servicing rights and non performing and reperforming pools, which is the secondary market side of mortgage.

Functional breadth runs from origination targeting through portfolio surveillance to loss mitigation strategy. The limit is scope by design: this is United States residential mortgage only, and the company says so plainly.