(n/v) the use of technology, including algorithms, artificial intelligence (AI), and data analytics, to evaluate loan applications and determine the creditworthiness of borrowers. This process replaces or supplements manual underwriting, allowing for faster, more consistent, and more accurate decisions.

Similarly to automated credit decisions, the accuracy of automated underwriting software ranges from system to system, depending on:

- how the system is engineered

- alignment with internal policy

- breadth of sources processed

- verification of data within the system

- not just traceability, but auditability of how an underwriting decision is made

It’s worth restating here a common refrain from SOLO: trusted decisions are not derived from more data, they are always contingent on the quality, source, and integrity of the data.

Key Components of Automated Underwriting:

1. Data Input: Information from the borrower, such as credit reports, income documents, and financial statements, is submitted electronically.

2. Decision Algorithms: Advanced algorithms analyze the data against predefined lending criteria, such as credit score thresholds, debt-to-income (DTI) ratios, and loan-to-value (LTV) ratios.

3. Risk Assessment: The system assesses the borrower’s risk level based on factors like payment history, financial stability, and other credit indicators.

4. Decision Output: The software provides an underwriting decision, typically categorized as approved, conditionally approved, or denied.