SYSTEM, METHOD, AND COMPUTER PROGRAM FOR PERSONALIZED CUSTOMER DUNNING

1 . A method for personalized customer dunning, performed by at least one processor and comprising:

monitoring a status of a plurality of invoices;

obtaining a customer score for a customer corresponding to an invoice of the plurality of invoices, based on the status of the invoice; and wherein the customer score is previously determined based on customer data;

receiving customer-specific data via a real time data ingestion pipeline from one or more customer data sources;

generating a dunning score for the customer based on the received customer-specific data and the customer score;

determining one or more dunning actions, based on the dunning score;

performing the one or more dunning actions; and

notifying the customer of the performed one or more dunning actions via a first engagement channel.

2 . The method of claim 1 , wherein the customer specific data comprises information on at least one of whether the customer has any open customer service tickets, a roaming status of the customer, a current bill amount, network performance data, whether any partial payments have been made, a number of previous notifications to the customer, whether the customer has received and/or read a prior notification, any auto payment failure, and whether any other lines on an account of the customer have been paid.

3 . The method of claim 1 , wherein the dunning action is one of a soft barring, a hard barring, an extension of time, delayed barring, and a reminder.

4 . The method of claim 1 , wherein the first engagement channel is a preferred channel of engagement determined based on customer behavior.

5 . The method of claim 1 , wherein the dunning score is only calculated when a status of the invoice is overdue.

6 . The method of claim 1 , further comprising:

generating a fraud score,

wherein the fraud score distinguishes the customer from a good faith debtor and a customer with fraudulent activity on the invoice, and

wherein the generating the dunning score comprises generating the dunning score based on the fraud score.

7 . The method of claim 1 , further comprising:

tracking a status of a channel response of the first engagement channel based on a channel type;

changing the channel type to a second engagement channel based on the status of the channel response being unsuccessful; and

notifying the customer of the one or more dunning actions via the second engagement channel.

8 . A system for personalized customer dunning, the system comprising:

at least one memory configured to store program code; and

at least one processor configured to read the program code and operate as instructed by the program code, the program code including:

monitoring code configured to cause the at least one processor to monitor a status of a plurality of invoices;

obtaining code configured to cause the at least one processor to btain a customer score for a customer corresponding to an invoice of the plurality of invoices, based on the status of the invoice, and wherein the customer score is previously determined based on customer data;

receiving code configured to cause the at least one processor to receive customer-specific data via a real time data ingestion pipeline from one or more customer data sources;

first generating code configured to cause the at least one processor to generate a dunning score for the customer based on the received customer-specific data and the customer score;

determining code configured to cause the at least one processor to determine one or more dunning actions, based on the dunning score;

performing code configured to cause the at least one processor to perform the one or more dunning actions; and

notification code configured to cause the at least one processor to notify the customer of the performed one or more dunning actions via a first engagement channel.

9 . The system of claim 8 , wherein the customer specific data comprises information on at least one of whether the customer has any open customer service tickets, a roaming status of the customer, a current bill amount, network performance data, whether any partial payments have been made, a number of previous notifications to the customer, whether the customer has received and/or read a prior notification, any auto payment failure, and whether any other lines on an account of the customer have been paid.

10 . The system of claim 8 , wherein the dunning action is one of a soft barring, a hard barring, an extension of time, delayed barring, and a reminder.

11 . The system of claim 8 , wherein the first engagement channel is a preferred channel of engagement determined based on customer behavior.

12 . The system of claim 8 , wherein the dunning score is only calculated when a status of the invoice is overdue.

13 . The system of claim 8 , the program code further including second generating code configured to cause the at least one processor to generate a fraud score, wherein the fraud score distinguishes the customer from a good faith debtor and a customer with fraudulent activity on the invoice.

14 . The system of claim 8 , the program code further including:

tracking code configured to cause the at least one processor to track a status of a channel response of the first engagement channel based on a channel type;

updating code configured to cause the at least one processor to change the channel type to a second engagement channel based on the status of the channel response being unsuccessful; and

notifying code configured to cause the at least one processor to notify the customerof the one or more dunning actions via the second engagement channel.

15 . A non-transitory computer readable medium storing instructions, the instructions comprising: one or more instructions that, when executed by at least one processor of a system for personalized customer dunning storing instructions that, cause the at least one processor to:

monitor a status of a plurality of invoices;

obtain a customer score for a customer corresponding to an invoice of the plurality of invoices, based on the status of the invoice; and wherein the customer score is previously determined based on customer data;

receive customer-specific data via a real time data ingestion pipeline from one or more customer data sources;

generate a dunning score for the customer based on the received customer-specific data and the customer score;

determine one or more dunning actions, based on the dunning score;

perform the one or more dunning actions; and

notify the customer of the performed one or more dunning actions via a first engagement channel.

16 . The non-transitory computer readable medium of claim 1 , wherein the customer specific data comprises information on at least one of whether the customer has any open customer service tickets, a roaming status of the customer, a current bill amount, network performance data, whether any partial payments have been made, a number of previous notifications to the customer, whether the customer has received and/or read a prior notification, any auto payment failure, and whether any other lines on an account of the customer have been paid.

17 . The non-transitory computer readable medium of claim 15 , wherein the dunning action is one of a soft barring, a hard barring, an extension of time, delayed barring, and a reminder.

18 . The non-transitory computer readable medium of claim 15 , wherein the first engagement channel is a preferred channel of engagement determined based on customer behavior.

19 . The non-transitory computer readable medium of claim 15 , wherein the instructions further cause the at least one processor to generate a fraud score, wherein the fraud score distinguishes the customer from a good faith debtor and a customer with fraudulent activity on the invoice.

20 . The non-transitory computer readable medium of claim 15 , wherein the instructions further cause the at least one processor to:

track a status of a channel response of the first engagement channel based on a channel type;

change the channel type to a second engagement channel based on the status of the channel response being unsuccessful; and

notify the customer of the one or more dunning actions via the second engagement channel.