SAN JOSE, California, May 5, 2023 – Every year, approximately one in fifteen or about 400,000 American borrowers encounter problems while obtaining home mortgages. This is because many of them are deemed outcasts due to low credit scores, heavy debt, or being a part of the gig economy (i.e., non-salaried or self-employed workers). Hence, such borrowers use alternative financing and obtain unconventional mortgage loans. Lenders of such loans require them to only provide cash flow and asset statements, bank statements, and a few tax forms. With a rise in low-income and gig economy borrowers and with the rest of the mortgage industry shrinking, the focus has recently intensified on the unconventional mortgage market. In fact, in 2022, this market reached $100 billion, thereby representing 4% of all mortgages. Keeping this in view, Scry AI‘s software, Collatio®, provides a fast, inexpensive, and accurate process for Intelligent Document Processing (IDP) and handling unconventional loan applications.
Collatio® uses more than forty proprietary AI-based algorithms and pre-built ontologies that enable the classification of more than fifty types of documents. These include bank statements and numerous tax forms, e.g., 1040, 1120, 1120(S), 1099, 1065, and related schedules. These also include other documents such as identity cards, passports, drivers’ licenses, utility bills, verification of employment statements, purchase contracts, homeowners’ insurance statements, and payoff statements. After classification, Collatio® extracts the required key-value pairs from each document and reconciles the extracted values. Next, it performs several kinds of analyses that are vital for lenders. For instance, for bank statements, it analyzes income versus the expense behavior of the applicant. And it provides alerts for abnormal situations such as check bounces and potentially fraudulent transactions.
According to Srinivasan Bharadwaj, Head of Digital Transformation of Scry AI, “Analyzing banks statements is an integral part of mortgage processing, and people looking for mortgages don’t rely on just one bank. Each financial institution has a different representation of its customers’ bank statements. Since formats, presentation styles, and nomenclature vary from one bank to another, it is not easy to process them in a unified manner. Moreover, there could be anomalies that are hard to detect especially since the data is not standardized in one format. Collatio® specializes in that.”
Scry AI’s advanced algorithms provide more than 95% accuracy that is boosted to 99% by using its AI-based reconciliation algorithms. Due to such high accuracy, Collatio® provides “straight through processing” for more than 60% of all documents, thereby, obviating the need for human intervention. Equally importantly, it points out the errors in documents where human intervention is necessary. Clearly, reduced human involvement and increased accuracy provide a conspicuously improved experience to lenders and their analysts.
“Currently, Collatio® is the most advanced Intelligent Document Processing (IDP) products and portends the future of AI based lending. On many key tasks related to unconventional mortgage lending, its accuracy often exceeds that of humans. Also, since it processes many documents via straight-through processing, lenders and financial service providers can make their processes faster and less laborious, thereby saving more than 30% of their costs and improving borrowers’ satisfaction,” said Dr. Alok Aggarwal, CEO and Chief Data Scientist of Scry AI.
Finally, Collatio® can be integrated with almost all end-to-end software lending solutions and processes and it comes with a configurable set of APIs and a rich user interface. It is sold in SaaS (software as a service) mode but can also be installed on-premises and behind a firm’s information technology firewall.