Abstract: Techniques are provided for forming clusters of individual prediction targets (IPTs). An initial prediction target is a target for which an automated prediction has been generated. IPTs may be, for example, borrowers to which a lending entity has extended loans based on predictions generated by a credit policy. Each cluster includes (a) a “core” of underperforming entities (UEs), and (b) a set of boundary performant entities (PEs). The UEs that belong to the UE core of a cluster are “similarly situated” relative to the values of their features. For example, in the context where the IPTs are borrowers, the UEs at the core of a cluster may correspond to defaulting borrowers that had similar bureau data, lending entity data, and borrower data. The boundary performant entities of the cluster may be borrowers that have not defaulted, but had similar credit qualifications as the UEs of the cluster.

Abstract: Techniques are provided for forming clusters of individual prediction targets (IPTs). An initial prediction target is a target for which an automated prediction has been generated. IPTs may be, for example, borrowers to which a lending entity has extended loans based on predictions generated by a credit policy. Each cluster includes (a) a “core” of underperforming entities (UEs), and (b) a set of boundary performant entities (PEs). The UEs that belong to the UE core of a cluster are “similarly situated” relative to the values of their features. For example, in the context where the IPTs are borrowers, the UEs at the core of a cluster may correspond to defaulting borrowers that had similar bureau data, lending entity data, and borrower data. The boundary performant entities of the cluster may be borrowers that have not defaulted, but had similar credit qualifications as the UEs of the cluster.

Abstract: Embodiments allow a mock-enabled software module to access a store of mock output data. Sets of mock output values (“SMOVs”), stored within the mock output store, are mapped to one or more key input values. When input sent to a mock-enabled software module includes one or more key input values that map to a given SMOV, the SMOV is included in a mock response from a target module of the given SMOV. When a set of input values, sent to a mock-enabled software module, does not include key input values that map to a SMOV, the mock-enabled module produces output without triggering any mock response. The mock output store may contain one or more replacement templates that are used to replace one or more mock output values, in a mock response, with one or more corresponding input values from the set of input values received by the triggering module.