Accelerate an urgent sustainable economic recovery from Covid19 in the UK mortgage market : Applying an AI lens

Digilytics is a fast growing UK-based SME specialising in Artificial Intelligence. Digilytics is led by Arindom Basu, a technology entrepreneur with 30 years' experience in developing and introducing disruptive technology in financial services. The mortgage application process is a complex and lengthy funding process. The mortgage origination process alone involves the manual processing of around 100 different types of paper documentation. Multiple duplications can occur and errors lead to lengthy and unnecessary delays. Digilytics' innovation will combine computer vision, machine learning and NLP technology to create first-time-right mortgage applications at scale.

In May 2020, the Bank of England warned that the UK economy is facing the sharpest downturn since 1706\. The mortgage sector has been one of the worst-affected sectors by the COVID-19 crisis. First-time home buyers, vulnerable and underprivileged areas and SME businesses have been greatly affected. UK Finance states that the two million repayment holidays have increased the cost of operations and lenders have withdrawn almost two-thirds of their products representing over 75% LTV (Williams, June 2020).

The innovation contributes to more sustainable financing in a number of ways. Firstly, going paperless will lead to environmental benefits. With a simpler and streamlined process, employees can be redeployed to where more human interaction is necessary, providing social benefits, greater customer satisfaction and less reputational risk as well as favourable views by regulators during on-site examinations. This will lead to more favorable governance benefits. Overall, the innovation fits very well within an ESG framework. The reduction in transaction costs should lead to more affordable credit availability and financial stability.

The innovation will achieve one-shot learning of mortgage documents leveraging advanced techniques such as Financial BERT and GPT3\. Validation of extracted data at document and cross-document levels in real-time and at scale will be made possible through innovative software architecture and engineering that leverages massively parallel processing.

In summary, the innovation project is a means to more sustainable finance post Covid19 incorporating environmental, social and governance concerns.