Dictionary · Comptroller's Handbook: Model Risk Management, Version 1.0

A set of computational rules to be followed to solve a mathematical problem. More recently, the term has been adopted to refer to a process to be followed, often by a computer.

An alternative prediction or approach used to compare a model’s inputs and outputs to estimates from alternative internal or external data or models.

A form of outcomes analysis that involves the comparison of actual outcomes with modeled forecasts during a development sample time period (in-sample back-testing) and during a sample period not used in model development (out-of-time back-testing), and at an observation frequency that matches the forecast horizon or performance window of the model.

Data that are closely related to and serve in place of data that are either unobservable or immeasurable.

Within the context of AI, the extent to which AI decisioning processes and outcomes are reasonably understood.

One of the three components of a model. This component delivers assumptions and data to the model.

A quantitative method, system, or approach that applies statistical, economic, financial, or mathematical theories, techniques, and assumptions to process input data into quantitative estimates. A model consists of three components: an information input component, which delivers assumptions and data to the model; a processing component, which transforms inputs into estimates; and a reporting component, which translates the estimates into useful business information.

A subcategory of artificial intelligence; a method of designing a sequence of actions to solve a problem that optimizes automatically through experience and with limited or no human intervention.

Judgmental or qualitative adjustments to model inputs or outputs to compensate for model, data, or other known limitations. A model overlay is a type of override.

A group of models that work together.