Step #7: Determining Most Effective Customer Communication Methods: Each of these previous steps lead wireless carriers to automatically push actions through existing communication channels (SMS, email, push notification, phone, etc.), informing the tone, the offer, and other iterative actions that drive collected balances. Remember, not all channels elicit the best response. For example, 73 percent of Gen Z consumers say SMS is the best method for reminding them when payments are past due. This is where the use of advanced analytics can be particularly helpful, informing customers about the right options for them. 

Implementing a Best-Practice Collections Decisioning Workflow

Modern, cloud-native risk decisioning solutions allow wireless carriers to administer the creation and testing of individual decisioning objects or nodes. These nodes interact with each other, either concurrently or sequentially, and range in complexity from simple business rules to advanced analytics. Users can then create and manage these through a low-code interface to improve returns on collection activities. Additionally, decisioning software that is user-friendly reduces the technical burden and operating costs of the collections function. This means telco providers can manage the end-to-end flow in both test and production environments without involving their IT departments. 

A workflow can include a combination of on-us behavior data (data related to direct transactions made between the customer and telco provider), off-us behavior data from third parties such as credit bureau and specialty telco data, previous contact history data, and socio-demographic data.  

On-us behavioral data includes the customer’s payment history, delinquency history, and returned checks, among other attributes. Off-us behavioral data involves third-party data sources that provide insights into a customer’s financial obligations and commitments, as well as updates on their behavior based on almost real-time updates. 

Previous contact history data is critical in learning from previous collection contact attempts and modifying the treatment approach accordingly. Finally, socio-demographic data can be used to build customer profiles, which in turn assist in selecting the most appropriate channel of communication. 

Together, these components form a holistic and comprehensive view of a delinquent customer. 

Leveraging various data sources and applying advanced analytics, such as random forest or XGBoost machine learning techniques, enables collection teams to predict behavior, propose settlement amounts, and gauge time and channel preferences. This approach enables the development of a more targeted and personalized collections strategy based on customer preferences and circumstances. 

The ability to efficiently manage the collections process is critical to maintaining profitability and customer relationships. However, traditional collections processes have heavily relied on simplistic measures, such as behavior scoring, days past due, and balance, to prioritize outbound call strategies. However, in today’s dynamic and rapidly changing market, this approach falls short. As the industry continues to evolve, it’s imperative for collections professionals to recognize the transformative potential of analytics and leverage them to create a competitive advantage in the dynamic collections landscape.  

This new approach highlights a more modern, individualized way of ensuring efficient, effective collections strategies for wireless carriers. By evolving beyond logistic regression and decision trees to next-generation collection models that lean on machine learning, the final customer treatment is much more personalized, providing more individualized treatments that better reflect customer preferences and circumstances. 

Tech Enabling Collections is Worth the While

In the past, collections haven’t been a hotbed investment area for carriers, but this is changing. Modern technology can be the difference between passive and proactive strategies, enabling organizations to understand what is recoverable and from which customers. This is necessary to achieve maximum revenue with the least amount of effort and to avoid wasting resources on the least likely candidates for return on investment.  

These efforts can also help guide downstream strategies for customer acquisition and revenue growth. Carriers need to realistically account for the likelihood of a subscriber to pay their debts, so that they can accurately account for their potential lifetime value.