Lending ecosystem – how machine learning can help in credit underwriting!

Lending ecosystem – how machine learning can help in credit underwriting!

The biggest challenge today is that the underwriters do not have the time to go through a lot of loan applications and make the decisions. Besides, there are biases that are introduced on a loan application process in assessing whether someone is a creditworthy borrower. 

Here, I am in conversation with Vasudevan Swaminathan, who is the president of Zuci Systems, and we discuss about how their platform Halo, helps in credit underwriting using machine learning.

The machine learning platform takes into account both primary data and alternate data. Primary data is the captive data that the lenders’ provider, while the alternative data are data from various sources that include the fraud data from players like TransUnion and Experian.

Where does Halo help? 

The lending ecosystem is evolving and there are multiple players who are targeting low-value lending as well. It is moving away from traditional models of lending based on credit scores alone. This environment is critical for individuals and businesses to grow. Every financial institution, micro-finance companies, and fintech apps would require something that is objective and logical to help them in their underwriting.

Halo is lender agnostic, and it can work in any environment – independently or in collaboration with an existing engine. It can process cash advances, personal loans, auto loans to complex business loans. The success of Halo depends on the quantity and quality of data that is available.

Data is critical, especially clean data. Data is one thing, cleansing and having the right data is another thing. Halo first identifies that the data is good, and from there it starts building the model. It takes time to get the desired results.

50% accuracy is what Halo starts with and helps you progress your accuracy levels.

Why should a lending institution look at Halo?

Halo can help build more lending applications over a while and help you avoid any and all kinds of biases that can be introduced into the system either through data or the underwriter.

Watch this video where I am in conversation with Vasudevan Swaminathan.


Sabapathy Narayanan

Leave a Reply

Your email address will not be published. Required fields are marked *