Using AI to Improve Credit Application Efficiency and Customer Satisfaction
HarMoney is an online marketplace lending company that offers personal loans to borrowers and matches them to lenders. Key AI themes for Andrew and Miles are customer satisfaction, innovation, operationalizing models, and speed to insights, with lower risk and higher returns for everyone involved. Miles says, “DataRobot is fantastic at helping us understand all the information that we are giving it — what is really important towards the predictability of the model that we are trying to create?”
Understanding the customers is key, per Andrew Cathie: “For us, it’s all about understanding the customer experience and understanding the customer journey, and mapping out that journey in a way that we are able to think about those steps that they go through.” Traditional lenders assess risk of default by asking prospective borrowers a list of questions. The longer the list of questions, the higher the dropout rate. HarMoney discovered that machine learning models can be highly effective when assessing risk of default. By understanding the information that is truly predictive of default risk with AI, HarMoney has reduced the number of questions they must ask borrowers.
So, what does AI innovation look like at HarMoney? “Automated machine learning with a product such as DataRobot is quite a change from traditional approaches to predictive analytics. Prepare to be adaptive and change the way you work. Take the time to understand this technology, see what it does well, and give it the freedom to do its best for your company. From an internal perspective, DataRobot removes some distractions of technical data science and keeps us focused on applying our skills and experience to improve our business.” AI is now so ingrained in HarMoney, from data managers to analytics managers. Miles says, “So, what would we do if DataRobot and Snowflake were taken away from us? Probably run for the hills!”
How does MLOps and automation radically improve their model deployment process? “Model deployment in our legacy environment was complicated and it could take us three to four months to complete the transition. With DataRobot, model deployment is trivial and can be achieved in a few mouse clicks. This is a huge enabler for our business. Working at a higher cadence at the interface between data science and IT engineering creates faster returns on our investment in machine learning.”
By creating demonstrably more accurate risk assessments based on each individual’s circumstances, Harmoney is more efficient than the large incumbents, resulting in better value for borrowers and a low default risk for lenders, while simultaneously providing momentum for the company to win an increasing share of a highly competitive market. In today’s rapidly changing global economy, Andrew and Miles are heroes for using AI to better help individuals, companies, and investors.
For the amount of business that we write, 1% improvement in the area under the curve for the model is worth about a million dollars for us. So, getting the best performance out of a risk model is essential to us for a business.
DataRobot’s platform makes my work exciting, my job fun, and the results more accurate and timely – it’s almost like magic!
I think we need to take it upon ourselves in the industry to build the predictive models that understand what the needs and wants of our customers are, and go through the whole curation process, become their concierge.
At LendingTree, we recognize that data is at the core of our business strategy to deliver an exceptional, personalized customer experience. DataRobot transforms the economics of extracting value from this resource.
DataRobot allows us to understand the data that’s being fed into our models without blindly feeding whatever we get into our system. DataRobot makes my team very effective.
We know part of the science and the heavy lifting are intrinsic to the DataRobot technology. Prior to working with DataRobot, the modeling process was more hands-on. Now, the platform has optimized and automated many of the steps, while still leaving us in full control. Without DataRobot, we would need to add two full-time staffers to replace what DataRobot delivers.