# US 2021/0081706 A1 · Configurable predictive models for account scoring and signal synchronization

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

- Number: US 2021/0081706 A1
- Document ID: US20210081706A1
- Status: Published application
- Kind: A1
- Application number: 16/878,568
- Filed: 2020-05-19
- Published: 2021-03-18
- Earliest claimed: 2019-09-15
- Assignees: Oracle International Corporation
- Applicants: Oracle International Corporation
- Inventors: Andrew Kiang; Yu-Hui Huang
- Web page: https://patentgrep.com/patent/US20210081706A1

## CPC

- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06F 18/2113: by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 18/231: Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram
- G06F 18/2413: based on distances to training or reference patterns
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G06Q 10/00: Administration; Management
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Techniques for generating and evaluation predictive models to optimize computing applications are described herein. In some embodiments, a system generates, using a model, a first set of scores for a plurality of accounts, wherein a score in first set of scores for a respective account characterizes a priority of interacting with the respective account relative to other accounts in the plurality of accounts, wherein the model defines a set of criteria for scoring accounts, wherein each criterion in the set of criteria is associated with one or more feature values and a weight. The system may receive user input that modifies the set of criteria. Responsive to the user input the system may update the model and generate, using the updated model, a second set of scores for the plurality of accounts. Actions may be prioritized/executed based at least in part on the account scores.

## Claims

### Claim 1

A method comprising:
generating, using a model, a first set of scores for a plurality of accounts, wherein a score in first set of scores for a respective account characterizes a priority of interacting with the respective account relative to other accounts in the plurality of accounts, wherein the model defines a set of criteria for scoring accounts, wherein each criterion in the set of criteria is associated with one or more feature values and a weight;
receiving user input that modifies the set of criteria;
responsive to the user input:
updating the model; and
generating, using the updated model, a second set of scores for the plurality of accounts; and
performing at least one action using the set of one or more computing resources with respect to a subset of the plurality of accounts based at least in part on the second set of scores.

### Claim 2 (depends on 1)

The method of claim 1, wherein generating the second set of scores for the plurality of accounts comprises generating a first score for a first account by matching criteria in the modified set of criteria to a set of company attributes associated with the first account; and aggregating weights for each of the matching criteria.

### Claim 3 (depends on 1)

The method of claim 1, further comprising presenting a distribution of a sample set and a random set of companies based on the first set of scores; and tuning the set of criteria until the distribution of the sample set satisfies an expected distribution relative to the random set of companies.

### Claim 4 (depends on 1)

The method of claim 1, further comprising segmenting the plurality of accounts into tiers based at least in part on the second set of scores; wherein each tier defines a threshold number of companies or percentile score; wherein performing the at least one action based at least in part on the second set of scores comprises performing the at least one action based at least in part on the tiers; and wherein the at least one action is only performed for accounts that fall within a particular tier.

### Claim 5 (depends on 4)

The method of claim 4, further comprising causing display of a user interface comprising a moveable or otherwise configurable bar that defines a cutoff between different tiers.

### Claim 6 (depends on 1)

The method of claim 1, wherein the first set of criteria is determined by a machine learning model trained from a plurality of examples labeled as successful or unsuccessful; wherein the each score in the first set of scores is indicative of a probability that interacting with a respective account in the first set of accounts will be successful.

### Claim 7 (depends on 1)

The method of claim 1, further comprising causing display of a user interface comprising a moveable or otherwise configurable bar that defines a cutoff between companies to be contacted in a content distribution campaign and companies to not be contacted in the content distribution campaign.

### Claim 8 (depends on 1)

The method of claim 1, wherein at least one criterion in the set of criteria adds a weight to accounts that use a particular technology or set of technologies.

### Claim 9 (depends on 1)

The method of claim 1, wherein at least one criterion assigns weights based at least in part on a company location, headcount, or revenue.

### Claim 10 (depends on 1)

The method of claim 1, wherein at least one criterion is associated with a negative weight.

### Claim 11

One or more non-transitory computer-readable media storing instructions which, when executed by one or more hardware processors cause:
generating, using a model, a first set of scores for a plurality of accounts, wherein a score in first set of scores for a respective account characterizes a priority of interacting with the respective account relative to other accounts in the plurality of accounts, wherein the model defines a set of criteria for scoring accounts, wherein each criterion in the set of criteria is associated with one or more feature values and a weight;
receiving user input that modifies the set of criteria;
responsive to the user input:
updating the model; and
generating, using the updated model, a second set of scores for the plurality of accounts; and
performing at least one action using the set of one or more computing resources with respect to a subset of the plurality of accounts based at least in part on the second set of scores.

### Claim 12 (depends on 11)

The media of claim 11, wherein generating the second set of scores for the plurality of accounts comprises generating a first score for a first account by matching criteria in the modified set of criteria to a set of company attributes associated with the first account; and aggregating weights for each of the matching criteria.

### Claim 13 (depends on 11)

The media of claim 11, further comprising presenting a distribution of a sample set and a random set of companies based on the first set of scores; and tuning the set of criteria until the distribution of the sample set satisfies an expected distribution relative to the random set of companies.

### Claim 14 (depends on 11)

The media of claim 11, further comprising segmenting the plurality of accounts into tiers based at least in part on the second set of scores; wherein each tier defines a threshold number of companies or percentile score; wherein performing the at least one action based at least in part on the second set of scores comprises performing the at least one action based at least in part on the tiers; and wherein the at least one action is only performed for accounts that fall within a particular tier.

### Claim 15 (depends on 14)

The media of claim 14, wherein the instructions further cause display of a user interface comprising a moveable or otherwise configurable bar that defines a cutoff between different tiers.

### Claim 16 (depends on 11)

The media of claim 11, wherein the first set of criteria is determined by a machine learning model trained from a plurality of examples labeled as successful or unsuccessful; wherein the each score in the first set of scores is indicative of a probability that interacting with a respective account in the first set of accounts will be successful.

### Claim 17 (depends on 11)

The media of claim 11, wherein the instructions further cause display of a user interface comprising a moveable or otherwise configurable bar that defines a cutoff between companies to be contacted in a content distribution campaign and companies to not be contacted in the content distribution campaign.

### Claim 18 (depends on 11)

The media of claim 11, wherein at least one criterion in the set of criteria adds a weight to accounts that use a particular technology or set of technologies.

### Claim 19 (depends on 11)

The media of claim 11, wherein at least one criterion assigns weights based at least in part on a company location, headcount, or revenue.

### Claim 20 (depends on 11)

The media of claim 11, wherein at least one criterion is associated with a negative weight.
