For collection operations and risk alignment, a critical success factor is the ability to predict month-end results accurately and at an early stage of the billing cycle.
This has always been a much-contested topic, due to the nature of accurate predicting early in a billing cycle.
The norm of predicting results in operations has always been a combination of tracking performance points to last-month-same-time, last-3-months-same-time and last-year-same-time, but also to take seasonality and unexpected anomalies into consideration.
While using data is a good start, basic analysis is often unreliable and insufficient to accurately forecast performance. It creates inter-month inaccuracies resulting in an inaccurate month-end expectation. Standard comparisons won’t give you the answers you need to create a strategy that will see the desired results, and it often doesn’t identify areas to implement pro-active remedial action and when to implement these actions to achieve your desired result.
The next question would be What does? Is there an alternative?
And yes, there is an alternative: big data analytics with machine learning capability.
Machine learning driven forecasts
By using predictive analytics and machine learning methods, it is possible to forecast results accurately, and predict which areas need remedial actions in the short or long term to have an impact if you are not tracking favourably to your month-end expectations. You can use these insights to inform your business and collections strategy very effectively.
Tools that offer this are straightforward to use and easy to understand. Based on your call centres past performance, machine learning can predict what your results will be in the current month and identify problematic areas.
By graphically plotting metrics and predictions against targets, it's also effortless to understand the data at a glance.
How are operational problem areas identified?
By accurately predicting month end results (in contrast to month-to-date results) early in the billing cycle, you can identify overall problems if collections will come in below target.
If performance predictions indicate overall unfavourable month-end results, a more granular inspection should be done, and individual portfolios/areas evaluated in the same way as overall performance. This will help identify which portfolios/area are under pressure, and require prioritised focus. This granular breakdown will also give you an overview of the most and least successful portfolios, and help you prioritise your workforce accordingly.
It is also essential to identify which performance metric (connects, Right-Party-Connects, Promise-to-Pay etc.) can be linked to the predicted unfavourable performance. Some performance metric intervention requires "back-office" focus as opposed to call centre agent performance focus (matters worked, negotiation etc.).
By breaking your targets down to a granular level, you’ll be able to identify both portfolio and performance metrics that are in need of pro-active remedial action.
How will I know whether the remedial action I’ve taken is effective?
The benefit of machine learning and accurate forecasting is that these predictions and problem area identification will take place very early in the billing cycle (or reporting period), allowing for sufficient time for any remedial action to make an impact. And if you continually feed your machine learning algorithm with updated information (data), your predictions will update dynamically, and increase in strength.
If you’re interested in using data analytics to optimise your collection performance, download our expert guide. You can also read more on our predictions tool, Prosperity.