Quantitative rating system for prioritizing customers by propensity and buy size

Patent metadata

Field	Value
Publication number	US-11263649-B2
Application number	US-201816042770-A
Country	US
Kind code	B2
Filing date	Jul 23, 2018
Priority date	Jul 23, 2018
Publication date	Mar 1, 2022
Grant date	Mar 1, 2022

Abstract

Quantitative rating systems and techniques are described that prioritize customers by propensity to buy and buy size to generate customer ratings. In one example, a propensity model is used to determine a likelihood of a potential customer to purchase a product, and a projected timeframe buy size for the potential customer is determined. An expected value for the potential customer is generated by combining the likelihood of the potential customer to purchase the product and the projected timeframe buy size. In another example, a ratio model of annualized recurring revenue (ARR) is used to determine a timeframe buy size for an existing customer in consecutive time frames. An upsell opportunity for the existing customer is determined based on the timeframe buy size less an ARR for a current time frame for the existing customer. A rating of the potential or existing customer is output in a user interface.

First claim

What is claimed is:

1. In a digital media environment, a method implemented by at least one computing device, the method comprising:
receiving, by the at least one computing device, interaction data describing interaction of respective client devices with digital services implemented by a service provider system via a network and resource allocation of resources implemented by computing devices of the service provider system in providing the digital services;
determining, by the at least one computing device, a subsequent resource allocation of the resources implemented by the computing devices of the service provider system in providing the digital services based on the interaction data, the determining including:
determining, by the at least one computing device, a likelihood of an entity to obtain access to the digital services based on a propensity model by correlating characteristics of the entity with propensities of a behavior of a customer segment of the entity;
determining, by the at least one computing device, a projected timeframe buy size for the entity by estimating an annualized recurring revenue (ARR) for the entity based on value of recurring components associated with the entity that are normalized over the projected timeframe;
generating, by the at least one computing device, an expected value for the entity based on a combination of the determined likelihood of the entity to obtain access to the digital services and the projected timeframe buy size;
generating, by the at least one computing device, a quantitative rating for the entity based on the expected value, the quantitative rating summarizing the determined likelihood of the entity to obtain access to the digital services via the network and the projected timeframe buy size;

allocating, by the at least one computing device, the resources implemented by the computing devices of the service provider system in providing the digital services based on the projected timeframe buy size, the allocating implementing the subsequent resource allocation;
generating, by the at least one computing device, digital content based on the quantitative rating using the allocated resources implemented by the computing devices, the digital content specifying at least one said digital service available for access via the network from the service provider system;
delivering, by the at least one computing device, the generated digital content to the entity over the network using the allocated resources implemented by the computing devices; and
providing, by the at least one computing device, access to the at least one said digital service via the network using the allocated resources implemented by the computing devices responsive to interaction with the digital content.

2. The method of claim 1 , wherein the propensity model is a random forest model or a logistic regression model with a penalized term.

3. The method of claim 1 , wherein the projected timeframe buy size is determined using a look-alike model configured to generate the projected timeframe buy size by comparing the entity to other entities.

4. The method of claim 1 , further comprising:
generating additional expected values for the entity by combining additional likelihoods of the entity to obtain access to additional digital services via the network and additional projected timeframe buy sizes; and
combining the additional expected values for the entity with the expected value for the entity into an overall expected value for the entity.

5. The method of claim 1 , further comprising filtering characteristics of the entity for comparison to other entities having similar characteristics.

6. The method of claim 5 , wherein the characteristics of the entity include a geographic location.

7. The method of claim 1 , wherein the quantitative rating of the entity is determined by comparing the expected value of the entity to threshold values for different ratings.

8. The method of claim 7 , wherein the quantitative rating of the entity is output as a symbol rating, where different numbers of symbols of the symbol rating correspond to respective ones of the threshold values.

9. In a digital media rating operations environment, a system comprising a processing system and a computer-readable storage medium having instructions stored thereon that, responsive to execution by the processing system, causes the processing system to perform operations including:
receiving interaction data describing interaction of respective client devices with digital services implemented by a service provider system via a network and resource allocation of resources implemented by computing devices of the service provider system in providing the digital services;
determining a subsequent resource allocation of the resources implemented by the computing devices of the service provider system in providing the digital services based on the interaction data, the determining including generating a quantitative rating of an entity by:
determining a likelihood of the entity to obtain access to multiple said digital services by correlating characteristics of the entity with propensities of entity behavior of a segment of the entity;
determining projected timeframe buy sizes for the entity corresponding to the multiple said digital services by estimating respective estimated annualized recurring revenues (ARR) for the entity based on value of recurring components associated with the entity that are normalized over the projected timeframe;
generating multiple expected values for the entity based on a combination of the determined likelihood of the entity to obtain access to the multiple said digital services and the respective projected timeframe buy sizes;
generating an overall expected value by combining the multiple expected values, the quantitative rating of the entity based on the overall expected value to summarize the determined likelihood of the entity to obtain access to the multiple said digital services and the projected timeframe buy size;

allocating the resources implemented by the computing devices of the service provider system in providing the digital services based on the overall expected value, the allocating implementing the subsequent resource allocation;
generating digital content based on the quantitative rating using the allocated resources implemented by the computing devices, the digital content specifying at least one said digital service;
delivering the generated digital content to the entity over the network using the allocated resources implemented by the computing devices; and
providing access to the at least one said digital service via the network responsive to interaction initiated with the digital content, the providing using the allocated resources implemented by the computing devices.

10. The system of claim 9 , wherein the determining the likelihood of the entity to obtain access to the multiple digital services utilizes a propensity model, the propensity model being a random forest model or a logistic regression model with a penalized term.

11. The system of claim 9 , wherein the generating the overall expected value is further configured to compare the overall expected value of the entity to threshold values for different quantitative ratings to determine the quantitative rating of the entity.

12. The system of claim 11 , wherein the quantitative rating of the entity is output as a symbol rating, where different numbers of symbols of the symbol rating correspond to respective ones of the threshold values.

13. In a digital media environment, a system comprising a processing system and a non-transitory computer-readable storage me

Assignees

• Adobe Inc

Inventors

• Xu Jin
• Yan Zhenyu
• Yang Wenqing
• Wang Tianyu
• Pani Abhishek

Classifications

• G06Q30/0204

  Market segmentation · CPC title

• G06Q30/0202 Primary

  Market predictions or forecasting for commercial activities · CPC title