QUESTIONS? 844.937.3268


Risk-Based Collections

Originally Published: September 2012

Using Statistical Scoring to Drive Collections Prioritization

This article is provided by SunGard Avantgard and reprinted with permission.

Risk-based collections is not a new concept. Surprisingly though, many credit and collections departments have not adopted this method and still prioritize collections based on aging. The customer who owes the most money for the longest period of time receives the highest priority. But using aging alone to prioritize collections activities may be the wrong strategy; especially if the company's goal is to optimize collection efficiency, improve DSO and reduce write-offs. By incorporating statistical-based risk modeling into collection strategies, corporations have better information to use to segment accounts and assign the proper resources and collection methods.

Judgmental Versus Statistical-based Scoring Models
Not all risk modeling, however, is the same. Companies that use only judgmental scoring models (i.e., credit bureau data, various forms of public record data such as liens, judgments and published financial statements, and even a company's history with an account) are primarily looking at data that accounts for how a customer paid its invoices with other companies. Judgmental models also cannot quantify risk. They are essentially ranking systems where the company with the highest score is considered the lowest risk. But, the score can’t tell you the probability or odds that a given company will pay its bill within any particular time period, since this type of score is not calibrated and validated on the company’s portfolio.

Statistical-based scoring models however have become one of the most powerful tools available for automating risk analysis to evaluate the collectability of a company's accounts receivable portfolio. The models leverage historical payment behavior with the company and are designed to predict the inherent risk of a customer, including the probability that the customer will become seriously delinquent or go to write-off.

Statistical models "quantify risk" by telling you what the odds or probability of the delinquency occurring is, thereby giving you the ability to also apply accounts receivable balance data, from a monetary perspective, to identify the financial value of your risk. Knowing which accounts are most likely to become seriously delinquent and how severe the cash impact will be can be used to help segment account strategies and prioritize collections resources in order to collect more money faster.

Why Are Statistical-Scoring Models the Best Fit for Collection Prioritization?
Statistical-based scoring quantifies specific risk probabilities on the accounts in your portfolio by calibrating the model to the payment relationships of your customers. By doing the calibration, the model will output probabilities on how your customers pay you. The model is also validated to prove a high level of predictability of future severe delinquencies called "bad accounts". The model uses the most valuable data, which is your internal payment experiences with your customers, among other internal data such as tenure of customers and history of non-sufficient funds to make these validated predictions

The best predictor of future customer payment performance is customer payment history. It is information that you have on every customer and comes at no cost. Commercial bureau data can be added to these models, but generally are not, since it typically doubles the cost for a small lift (only 5-10%) in predictability.

The score produced by the statistical-based scoring model essentially provides a measure of the risk that a given customer will pay their bill on a timely basis. The standard output from a statistical-based scoring system includes not only a collection score, but also the probability that the account will go bad i.e. Probability of Bad (PBAD) within a specified period from the scoring date, usually six months, and an estimate of the cash value of the account that is at risk, i.e., Cash at Risk (CAR). These values, when properly applied, will aid you in allocating collections resources to specific accounts such that the return on investment (ROI) from collections operations will be maximized.

Edward Don & Company, a privately held and the largest distributor of foodservice equipment and supplies in the United States with annual revenue in excess of $600 million, has implemented statistical scoring into their credit and collections processes.

According to John Fahey, Director of Credit at Edward Don & Company,

"Statistical scoring has helped us drive improved collection prioritization and ultimately lower DSO by 5.3 days. Instead of focusing on terms and past due balances, the statistical scoring models help us focus on risk and tell us which accounts have a probability of going delinquent and the dollars at risk. We are able to be more proactive with those accounts."

By knowing your customer's expected future paying behavior and utilizing statistical scores, it is possible to optimize the allocation of the resources available in a given credit and collections environment. Risk-based collections and specifically statistical-based scoring helps companies prioritize collections activities to higher risk accounts and reduce outstanding A/R while maximizing revenue opportunities with lower risk accounts.


The AvantGard solution suite includes credit risk modeling, collections management, treasury risk analysis, cash management, payments system integration, and payments execution delivered directly to corporations or via banking partners. AvantGard solutions help consolidate data from multiple in-house systems, drive workflow and provide connectivity to a broad range of trading partners including banks, SWIFT, credit data providers, FX platforms, money markets, and market data. The technology is supported by a full range of services, including managed cloud services, treasury operations management, SWIFT administration, managed bank connectivity, bank on-boarding, and vendor enrollment, and is delivered by a team of domain experts. For more information, visit