There are numerous reasons to use automated credit scoring in your credit (and collection) operations, including faster and better quality decisions, enhanced customer service, more effective compliance and controls, and significantly reduced overhead. Employing credit scoring in a B2B environment is credit management  “Best Practice,” especially if you have many customers.

Using Smyyth’s Carixa cloud technology for credit-to-cash management, Leib can seamlessly incorporate Credit2B’s advanced scoring results into Carixa’s enterprise credit management workflow. Leib and are Smyyth affiliates.

Here are some benefits to consider from credit scoring, which includes leveraging your own historical data,  credit bureau business information, and industry trade payments.

7  Good Reasons to Use Credit and Collection Scoring

  1. Speed of Credit Decisions. Scoring can dramatically shorten the time it takes to approve orders, a major customer service and sales benefit.
  2. Prioritized Collections.  Use blended credit risk scores to set collection priorities, ensuring the accounts with the highest risk for non-payment get collection attention first. If you focus on “risk,” not just age and value, you will have better outcomes and less bad debt.
  3. Personnel and Overhead Savings. Scoring automates the decision process, dramatically cutting down the personnel costs associated with credit approvals and letting you do more with less.
  4. Credit and Collection Policy. You can use credit and payment scores to establish corporate policies for risk and slow payment tolerance. Credit and Payment scoring ensures consistency for applying  credit policy.
  5.  Collection Agency placement based on the account age rules eliminates “decision freeze” when deciding when an account is turned over to a bad debt collection agency, reducing write-offs.
  6. Customer Advisory. The credit manager can become a partner to sales if you counsel customers on how they can improve their scores by highlighting areas of weakness.
  7. Fewer Bad Debts. You can expect reduced bad debts using a valid scoring methodology since many smaller customers would not get the same level of manual review as the larger exposures.

Data Elements Used in Automated Scoring

Financial metrics for large corporations can be predictive in the 2-5-year range, and many credit analysts still use a traditional or modified Altman-Z Score for this purpose. However, financials are often not available for smaller customers or they are often stale, unreliable, and subject to fast swings. For these smaller debtors, other data elements become more critical, including:

  1. Years in business
  2. Experience of principals
  3. Number of employees
  4. Revenue and Assets
  5. Business and Industry Trends
  6. Financial information (if available) using a dozen key metrics
  7. Public records information
  8. Supplier payment experience (including your trade credit groups)
  9. Bank and Lender Experience
  10. Credit Line Utilization
  11. Credit exposures of other industry suppliers
  12. Public filings, liens, etc.
  13. Transparency with key suppliers
  14. Derogatory comments; Reputation

Using Big Data and Machine Learning

Building truly predictive credit scoring is now significantly easier with the ability to capture “Big Data” from multiple sources and analyze it with powerful software and hardware, where the “machine” can learn from experience and adjust its conclusions; that is, make and correct its decisions based on experience, patterns and trends it sees in the data. 

This is called “Machine Learning,” where computers are taught to detect patterns in data to both predict and validate outcomes with regression testing of past events and then adjust those based on current events. Reaching this goal has gotten much easier due to the rapidly increasing power of computer processing.

W.E. Deming famously said said, “Without data, you’re just another person with an opinion.”

We would add, “if you can’t process the data to produce real insights, they’re just numbers.”

Our experience is that leveraging machine learning can significantly improve predictive credit and payment scoring. We use these techniques to build and customize automated credit scores and credit lines for large trade creditors that need to improve and accelerate credit decisions. As we are a cloud-based service,  there is no software to buy, and we integrate easily with client processes and systems.

Designing a Scoring Model

Our Credit Scoring Framework has a Simple Flow:

  1. Working with a technology provider like Carixa, decide on the outcomes you would like to predict (e.g., bankruptcy, default, severe delinquency, or X days late), and establish a model.
  2. Create a training sandbox using data attributes from multiple sources, including your own experience; for example, business standing, financials, and debtor payment histories, often as many as a dozen separate data elements, and even unstructured credit data, such as industry “attitudes.”   Sharing this in our cloud platform speeds up adjustments, saves time, and simplifies managing the data.
  3. Adjust for the outcome you are aiming for or test multiple outcomes based on “model training sets” created in your sandbox and adjust the importance or weight of certain elements.
  4. More elements do not always better produce a better outcome; what is important is to pick and test for the right elements. For very small businesses, factors such as years in business, number of employees, and social reputation are critical. Economic factors are important. If the consumer economy turns down, it is a leading indicator of problems with payments and defaults in subsequent quarters.
  5. Machine regression picks and weight-adjusts the credit attributes that are critical for the outcome you are trying to predict in real-time.
  6. Using real-time industry data ensures continuous updates to scoring attributes and weights.

    : The scoring model should self-adjust continuously without manual updates, pulling in more data types than traditional models, including micro and macroeconomic variables, to target the prediction of outcomes that match your company’s needs. The models adjust for specific industry or business needs based on your unique data or information, defining your preferred outcome with great precision.
    To complete a fully automated process, we provide calculated credit lines that can be integrated with any financial or ERP you use.

    Customized Calculated Credit Lines

  • By applying your corporate policies, we can calculate a Dollar Credit Line for you, adjusted to your circumstances. This takes into consideration a number of factors, including your tolerance for risk (are you in a fast growth or more risk-averse environment), lender or insurance limits, or product profit margins (a consumer good with a 60% gross margin will tolerate more risk than a service with a 17% margin).
  • Our modelers interpret your process and policy, replicating your rules in a computer model. By way of example, where no financials are available and the customer has fewer than ten employees, you may decide “do not calculate a credit line” but instead perform a manual review or adjust a CCL based on the presence or absence or magnitude of certain elements.
  • Through feedback through a regressive “fit test,” we can adjust the algorithms as required to bring your scores in line with your desired outcomes.

Advantages: Custom Calculated Credit Lines are built to your circumstances and adjusted as required by your rules, policies, and internal and external events. Machine-generated credit lines are useful for accelerated decisions and risk analysis across an entire portfolio. We can actually do this across 99% of registered businesses in North America.

Summary: By using computational power and a scientific approach to data analysis, you can produce extraordinary results with automated credit decision processing and, in doing so, improve credit decisions and customer service while streamlining credit operations.