Learn Markus Heid 29 June 2022

Coeo Incasso: debt collection optimization

Deeploy use case

Increasing the probability of payment claims in the incasso industry

Everyone, from private persons to corporations, has been in similar situations. Products or services are being purchased or rented, but payments remain unpaid due to various reasons. In most cases, the majority is settled after several reminders, but there is a part that remains unpaid. For everyone an unsatisfying situation leading to high uncertainty of future payments. The last instance for corporations: hiring an incasso company.

Coeo Incasso

With Coeo Incasso we can find one of the most modern and technologically innovative debt collection companies right in front of our door. At the center of all their actions stays one central aim: finding an amicable solution for everyone. Seeing significant growth in recent years, Coeo is facing a high increase in incoming claims.

An immense challenge for the whole organization to validate and process every single one. But Coeo early on saw the potential for artificial intelligence and machine learning.

“Debt collection optimization” and the challenges for Coeo

Historically the debt collection process has been a rather “manual” and time-consuming process. Validating and following up on every claim, even those with a low probability of success, is not possible anymore. To free time and focus on claims to handle all claims properly, Coeo looked into a first use case: prioritizing claims and automating actions. Based on the likelihood-to-pay in relation to days of outstanding payments, a machine learning model was developed. 

However, as many companies experience, simply deciding on and building a model does not guarantee actual usage. A key business process would be (partly) replaced by automated decisions and machine learning still presents an unknown element to the daily work, transparency and trust among employees were essential. In addition, to ensure legal accountability, every prediction needed to be reproducible at any time. A case perfectly fitted to Deeploy’s mission to ensure explainability, accountability and manageability for machine learning.

Debt collection process optimized using AI

 

Use case “Debt collection optimization”

  • Ambition: Ensuring that the largest possible share of outstanding payments is settled
  • Situation: Evaluation of claims, estimation of likelihood of payments per customer and resource prioritization (e.g. people, time) conducted manually
  • Models: likelihood-to-pay in relation to days of outstanding payments resulting in automatically triggered measures

Challenges

  • Solutions needed to integrate machine learning in business processes to level fast growth while simultaneously reducing high manual effort
  • Limited link and transparency between business units and machine learning applications
  • Desire to reproduce predictions at any time to evaluate the taken measures

The solution: enabling human-machine interaction and accountability through Deeploy

As a start, Deeploy provided Coeo with the platform to easily deploy and update their models without facing any costly downtimes. But even more importantly was another Deeploy feature: the human-feedback loop. Based on customized explainers, Deeploy is able to give Coeo’s business and legal experts detailed insights on each prediction made by the model. Building on those insights, Deeploy creates full transparency and explainability while providing the opportunity to evaluate and provide feedback on the model logic. By involving all relevant stakeholders and providing a chance for feedback, Deeploy creates a perfect feedback loop. Placing high emphasis on accountability and reproducibility, Deeploy allows Coeo to constantly log and trace every change and prediction made by a model. Creating clear audit trails. In that way, Coeo is able to achieve full documentation and accountability for the decisions made by their models. By establishing trust and transparency towards ML models, Coeo was able to significantly free the time of their employees. Time that can now be used to focus on claims that need the involvement to generate payouts. Supporting their fast expansion and growth through AI and ML.

Realized benefits through Deeploy

Coeo trusts Deeploy as a tool to establish transparency and explainability for models throughout their organization, while simultaneously ensuring accountability and manageability. Building the base for Coeo’s future growth!

Deeploy's human feedback loop to validate model predictions

Implemented features

  • Version control of historic models & predictions
  • Automated audit trails
  • Customized explainers for every prediction
  • Human-feedback loop for business experts

Find out more about our product features

“Deeploy has enabled us to respond to the customer’s situation at the debtor level and to take targeted personal actions so that we can put empathy in the way we communicate with them. This is an important aspect for our clients in the context of customer retention.” – Coeo

Contact us to find out more about Deeploy, and how we could help you out.

Want to stay updated?

Please fill in your e-mail and we update you when we have new content!