# US 2023/0275973 A1 · Computerized system and method for churn prediction and system updates based therefrom

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0275973 A1
- Document ID: US20230275973A1
- Status: Published application
- Kind: A1
- Application number: 18/313,148
- Filed: 2023-05-05
- Published: 2023-08-31
- Earliest claimed: 2017-10-13
- Assignees: Plume Design, Inc.
- Applicants: Plume Design, Inc.
- Inventors: Yusuke SAKAMOTO; Muhammad Ali VALLIANI; Nipun AGARWAL; Sachin VASUDEVA
- Web page: https://patentgrep.com/patent/US20230275973A1

## CPC

- H04L 41/149: for prediction of maintenance
- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- H04L 41/22: comprising specially adapted graphical user interfaces [GUI]
- H04L 41/5009: Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
- H04L 41/5067: Customer-centric QoS measurements
- H04L 43/045: for graphical visualisation of monitoring data
- H04L 43/50: Testing arrangements
- H04L 41/12: Discovery or management of network topologies
- H04L 41/147: for predicting network behaviour
- H04L 41/16: using machine learning or artificial intelligence
- H04L 43/0811: by checking connectivity
- H04L 43/0876: Network utilisation, e.g. volume of load or congestion level
- H04L 43/0888: Throughput
- H04W 12/03: Protecting confidentiality, e.g. by encryption
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

Systems, methods, and non-transitory computer-readable storage media are provided for predicting the likelihood or probability of a subscriber of a service to cancel or not renew a subscription. A method, according to one implementation, includes a step of receiving data pertaining to aspects of a service that is provided by a service provider to a subscriber in accordance with a subscription. The data may include one or more impact factors each having a positive, neutral, or negative influence on the likelihood of subscriber churn. The method also includes a step of using the one or more impact factors to predict the likelihood that the subscriber will cancel the subscription.

## Claims

### Claim 1

A method comprising the steps of:
identifying, by a device, data corresponding to a user, the data being collected in accordance with a predetermined time period of activity of the user;
analyzing, by the device, the data, and determining a set of features, the features corresponding to a type of activity indicated by the data;
analyzing, by the device, the data and the set of features, and determining a churn probability for the user, the churn probability providing an indication as to how likely the user is to cancel a subscription from a service provider (SP) based on the type of activities;
determining, by the device, a set of risk factors based on the churn probability, the risk factors corresponding to specific actions by the user that correspond to the set of features; and
generating, by the device, a set of instructions for mitigating the churn probability, the set of instructions corresponding to an actionable campaign that can be implemented via an account of the user with the SP.

### Claim 2 (depends on 1)

The method of claim 1, wherein the actionable campaign comprises information related to functionality for modifying user equipment of the user in relation to services provided by the SP.

### Claim 3 (depends on 2)

The method of claim 2, wherein the functionality comprises non-native functionality to the user equipment that enables the user equipment to function in a modified manner.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
communicating, over a network, an electronic message to the account of the user, wherein the electronic message comprises information related to the campaign, wherein interaction with the information enables installation of functionality to user equipment.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
communicating, for display on a display device, a user interface (UI), the UI providing a dashboard of real-time analytics of the user, the real-time analytics being based on the user data and the churn probability.

### Claim 6 (depends on 5)

The method of claim 5, wherein the dashboard dynamically updates according to updated user data and churn probabilities.

### Claim 7 (depends on 1)

The method of claim 1, wherein the user data is collected from a network cloud location, the network cloud location comprising information related to the account of the user.

### Claim 8 (depends on 1)

The method of claim 1, wherein the analysis and determination performed by the device is performed by a trained machine learning model, wherein the model is trained based on historical data related to the user, wherein the historical data corresponds to analytics of user data from previous time periods.

### Claim 9 (depends on 1)

The method of claim 1, wherein the data comprises information related to at least one of network experience data, subscriber behavior data, support activities data, service consumption data, subscriber satisfaction data, subscriber account data and competitive offerings data.

### Claim 10 (depends on 1)

The method of claim 1, wherein the steps are performed for each active user according to the predetermined time period.

### Claim 11

A device comprising:
a processor configured to:
identify data corresponding to a user, the data being collected in accordance with a predetermined time period of activity of the user;
analyze the data, and determine a set of features, the features corresponding to a type of activity indicated by the data;
analyze the data and the set of features, and determine a churn probability for the user, the churn probability providing an indication as to how likely the user is to cancel a subscription from a service provider (SP) based on the type of activities;
determine a set of risk factors based on the churn probability, the risk factors corresponding to specific actions by the user that correspond to the set of features; and
generate a set of instructions for mitigating the churn probability, the set of instructions corresponding to an actionable campaign that can be implemented via an account of the user with the SP.

### Claim 12 (depends on 11)

The device of claim 11, wherein the actionable campaign comprises information related to functionality for modifying user equipment of the user in relation to services provided by the SP, wherein the functionality comprises non-native functionality to the user equipment that enables the user equipment to function in a modified manner.

### Claim 13 (depends on 11)

The device of claim 11, wherein the processor is further configured to:
communicate, over a network, an electronic message to the account of the user, wherein the electronic message comprises information related to the campaign, wherein interaction with the information enables installation of functionality to user equipment.

### Claim 14 (depends on 11)

The device of claim 11, wherein the processor is further configured to:
communicate, for display on a display device, a user interface (UI), the UI providing a dashboard of real-time analytics of the user, the real-time analytics being based on the user data and the churn probability, wherein the dashboard dynamically updates according to updated user data and churn probabilities.

### Claim 15 (depends on 11)

The device of claim 11, wherein the analysis and determination performed by the device is performed by a trained machine learning model, wherein the model is trained based on historical data related to the user, wherein the historical data corresponds to analytics of user data from previous time periods.

### Claim 16

A non-transitory computer-readable storage medium tangibly encoded without computer-executable instructions that when executed by a device cause the performance of a method comprising:
identifying, by the device, data corresponding to a user, the data being collected in accordance with a predetermined time period of activity of the user;
analyzing, by the device, the data, and determining a set of features, the features corresponding to a type of activity indicated by the data;
analyzing, by the device, the data and the set of features, and determining a churn probability for the user, the churn probability providing an indication as to how likely the user is to cancel a subscription from a service provider (SP) based on the type of activities;
determining, by the device, a set of risk factors based on the churn probability, the risk factors corresponding to specific actions by the user that correspond to the set of features; and
generating, by the device, a set of instructions for mitigating the churn probability, the set of instructions corresponding to an actionable campaign that can be implemented via an account of the user with the SP.

### Claim 17 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein the actionable campaign comprises information related to functionality for modifying user equipment of the user in relation to services provided by the SP, wherein the functionality comprises non-native functionality to the user equipment that enables the user equipment to function in a modified manner.

### Claim 18 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, further comprising:
communicating, over a network, an electronic message to the account of the user, wherein the electronic message comprises information related to the campaign, wherein interaction with the information enables installation of functionality to user equipment.

### Claim 19 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, further comprising:
communicating, for display on a display device, a user interface (UI), the UI providing a dashboard of real-time analytics of the user, the real-time analytics being based on the user data and the churn probability, wherein the dashboard dynamically updates according to updated user data and churn probabilities.

### Claim 20 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein the analysis and determination performed by the device is performed by a trained machine learning model, wherein the model is trained based on historical data related to the user, wherein the historical data corresponds to analytics of user data from previous time periods.
