Machine learning produces better credit scores
The importance of accurate credit scoring
In times of uncertainty, the ability to make accurate predictions becomes more important than ever. Credit managers across the world are coming under even greater pressure to manage risk and make accurate predictions about the business viability of their customers, but luckily, they have better tools available to them than ever before.
Using Billtrust’s Credit Management solution, credit managers have access to cutting-edge indicators that measure a potential customers’ payment outlook and business viability with more than 80% predictive accuracy.
How does machine learning predict credit outcomes?
Machine learning algorithms work by ingesting large amounts of data over the course of time and utilizing that data to make very clear, accurate predictions of events in the future. If a data analyst were to try to make predictions manually using the same large datasets, it would take an excessively long time to analyze all of it, and the final result wouldn’t be as accurate as computer-generated predictions.
Machine-learning can rapidly analyze massive information sets to uncover trends that can be used for future decisions. This is especially useful in credit management.
Credit analysts at Billtrust and in the larger field have uncovered specific, identifiable patterns that arise in the financial statements of organizations during the years and months before they declare bankruptcy. Machine-learning algorithms can detect these patterns. They can also detect other forms of financial distress in their earliest stages, and predict results that help our customers protect themselves from extending credit to businesses that may not be able to pay in the future.
What credit managers care about
There are two primary questions that credit managers are trying to answer:
- What is the near term risk of non-payment?
- How strong is this business financially?
For the first question, Billtrust Credit Management analyzes trade payment data, credit bureau data, collections alerts, peer remarks and more to determine the short-term likelihood that a company will go “beyond terms” as defined by a set of data rules (e.g., 20% would be 60 days past due). We call this the Payment Outlook Indicator.
To determine business viability, Billtrust uses financial records, credit agency ratings and other business operations metrics to determine the likelihood that the customer will be active in the long-term. We call this the Business Viability Indicator. It relies heavily on financials, but also incorporates other elements like ordering quantity trends, age of the business and scale of operations.
Credit scoring made easy
In order to create credit scores that provide utility and value, Billtrust scores on a scale of 0-100, with each point on this scale representing the probability of a positive outcome. Therefore, a score of 80 for our Payment Outlook Indicator simply means that there is an 80% probability that the company will pay on time. Other agency scores are described in either tiers or bands that often cause confusion for credit practitioners who need to make important decisions quickly. With the tiered approach, two very similar companies may be scored in separate bands. Billtrust’s machine-learning solution delivers scores along a continuum, giving customers information they can process and use quickly.
Billtrust also assigns a score to the quality and timeliness of the underlying data. We call this score percent confidence. Machine-learning solutions crave good data, so we are always seeking more and better data sources to help us give the most accurate scores.
Accurate predictions aid good decisions
With the tools to predict both customers’ short-term payment behavior and long-term business viability, credit managers now have the ability to quickly and accurately make credit decisions that will help their companies thrive in any business environment.