System and method to predict and prevent customer churn in servicing business
A system and method for minimizing customer churn in device service businesses commences with execution of a customer service contract. Ongoing customer data capture is made for each contract. Customer data includes contract events, environmental events, service events, device usage analytics and personnel events. Machine learning is applied to captured customer data, which machine learning is based on a state of customer data at the time of contract determination. Customer data is assigned weights, and aggregate data for each customer is compared to a preselected threshold level. Customers above a threshold are deemed happy and customers below the threshold are deemed to be at risk. Remedial measures relative to at risk customer data generates levels of automated remediation followed by remedial measure suggestions to an administrator when not sufficiently successful.
1 . A system comprising:
a multifunction peripheral including a hardware monitor, wherein the hardware monitor includes one or more sensors that generate sensor data based on one or more of a toner level, an ink level, a temperature, and a paper jam of the multifunction peripheral; and
a plurality of computers each including a processor and memory, the memory of one of the computers storing customer data,
wherein the customer data includes usage analytics data of the multifunction peripheral based on generated sensor data received from the hardware monitor, and the customer data further includes at least one of (1) data regarding a service contract of the multifunction peripheral, (2) data regarding prior servicing of the multifunction peripheral, (3) personnel-related data regarding identifying characteristics of a customer or dealer of the multifunction peripheral, and (4) environmental data regarding economic or organizational conditions of the customer, and
wherein the system is configured to perform the following steps to mitigate the risk of customer churn for multifunction peripherals:
executing an artificial intelligence (AI) model based on the customer data to assign a satisfaction weight to each of a plurality of ongoing events represented in the customer data, including assigning negative satisfaction weights to negative customer events and positive satisfaction weights to positive customer events;
determining that there is a customer churn risk by comparing a function of the assigned satisfaction weights to a preselected threshold level;
implementing one or more remedial actions in response to the determined customer churn risk by pushing, to the multifunction peripheral, one or more of (1) new software to be installed, (2) updates to existing software or firmware to be installed, and (3) configuration changes to be applied, wherein the multifunction peripheral then installs the new software or the updates to the existing software or firmware, or applies the configuration changes; and
updating, in response to receiving an input corresponding to loss of the customer, the AI model to modify the assignment of satisfaction weights to ongoing events associated with other multifunction peripherals.
2 . The system of claim 1 , wherein the usage analytics data is comprised of error codes associated with operation of the multifunction peripheral.
3 . The system of claim 1 , wherein the usage analytics data is comprised of a copy count.
4 . The system of claim 1 , wherein the customer data includes the data regarding prior servicing of the multifunction peripheral, including information associated with service calls placed for the multifunction peripheral.
5 . A method of mitigating the risk of customer churn for multifunction peripherals, the method comprising:
storing customer data including usage analytics data of a multifunction peripheral that is based on generated sensor data received from a hardware monitor of the multifunction peripheral, wherein the customer data further includes at least one of (1) data regarding a service contract of the multifunction peripheral, (2) data regarding prior servicing of the multifunction peripheral, (3) personnel-related data regarding identifying characteristics of a customer or dealer of the multifunction peripheral, and (4) environmental data regarding economic or organizational conditions of the customer;
executing an artificial intelligence (AI) model based on the customer data to assign a satisfaction weight to each of a plurality of ongoing events represented in the customer data, including assigning negative satisfaction weights to negative customer events and positive satisfaction weights to positive customer events;
determining that there is a customer churn risk by comparing a function of the assigned satisfaction weights to a preselected threshold level;
implementing one or more remedial actions in response to the determined customer churn risk by pushing, to the multifunction peripheral, one or more of (1) new software to be installed, (2) updates to existing software or firmware to be installed, and (3) configuration changes to be applied, wherein the multifunction peripheral then installs the new software or the updates to the existing software or firmware, or applies the configuration changes; and
updating, in response to receiving an input corresponding to loss of the customer, the AI model to modify the assignment of satisfaction weights to ongoing events associated with other multifunction peripherals.
6 . The method of claim 5 , wherein the usage analytics data is comprised of error codes associated with operation of the multifunction peripheral.
7 . The method of claim 5 , wherein the usage analytics data is comprised of a copy count.
8 . The method of claim 5 , wherein the customer data includes the data regarding prior servicing of the multifunction peripheral, including information associated with service calls placed for the multifunction peripheral.