# US 2022/0284459 A1 · Predictions based on analysis of big data

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

- Number: US 2022/0284459 A1
- Document ID: US20220284459A1
- Status: Published application
- Kind: A1
- Application number: 17/191,058
- Filed: 2021-03-03
- Published: 2022-09-08
- Earliest claimed: 2021-03-03
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Jennifer Kwok; Viraj Chaudhary; Cruz Vargas
- Web page: https://patentgrep.com/patent/US20220284459A1

## CPC

- G06Q 30/0206: {Price or cost determination based on market factors}
- G06N 20/00: Machine learning
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems as described herein may analyze big data to generate predictions for Software-as-a-Service (SaaS) offerings and/or other subscription-based software. A prediction system may receive small business transaction data comprising payment information between a plurality of merchants and a software vendor. The prediction system may receive enterprise merchant insights information. The prediction system may identify, based on the small business transaction data and the enterprise merchant insights information, recurring transactions using a first machine learning model. The prediction system may generate an average contract price and a confidence score, using a second machine learning model. The prediction system may generate a recommendation comprising a renewal rate. Based on a determination that a service provided by the software vendor is coming due for renewal, the prediction system may send, to a particular merchant, an alert associated with the renewal and the recommendation.

## Claims

### Claim 1

A computer-implemented method comprising:
receiving, by a first computing device, small business transaction data comprising payment information between a plurality of merchants and a software vendor;
receiving, from a second computing device, enterprise merchant insights information;
identifying, based on the small business transaction data, based on the enterprise merchant insights information, and using a first machine learning model, recurring transactions associated with a purchase of one or more services from the software vendor;
generating, based on the recurring transactions and using a second machine learning model, an average contract price associated with a first service of the one or more services provided by the software vendor and a confidence score associated with the average contract price;
generating, based on the average contract price and the confidence score exceeding a threshold value, a recommendation comprising a renewal rate; and
based on a determination that the first service provided by the software vendor is coming due for renewal, sending, to a particular merchant, an alert associated with the renewal, wherein the alert comprises the recommendation.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
receiving, from the particular merchant, an input comprising a contract term length, wherein the recommendation is further based on the contract term length; and
generating the recommendation further comprises the contract term length.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, further comprising:
receiving the small business transaction data in a first data format;
receiving the enterprise merchant insights information in a second data format; and
converting the small business transaction data and the enterprise merchant insights information into a common format.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, wherein the first data format comprises a text format, and the second data format comprises unstructured data format.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the first machine learning model and the second machine learning model comprises a supervised machine learning model.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein generating the average contract price comprises:
predicting, using the second machine learning model, a growth rate in the average contract price associated with the first service; and
based on the average contract price and the predicted growth rate, the recommendation comprising the renewal rate.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein generating the average contract price comprising:
collecting training data comprising prediction factors to be used as model input to the second machine learning model;
training the second machine learning model by adjusting a weight associated with each of the prediction factors; and
generating a plurality of contract prices based on the trained second machine learning model.

### Claim 8 (depends on 7)

The computer-implemented method of claim 7, wherein the prediction factors comprise merchant factors comprising:
a merchant size, a merchant location and a merchant industry.

### Claim 9 (depends on 8)

The computer-implemented method of claim 8, wherein the prediction factors comprise transaction factors comprising:
a transaction amount and a frequency of payment.

### Claim 10 (depends on 8)

The computer-implemented method of claim 8, wherein the prediction factors comprise vendor factors comprising:
a vendor size, a vendor location and a type of software-based service.

### Claim 11

A prediction system comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the prediction system to:
receive small business transaction data comprising payment information between a plurality of merchants and a software vendor;
receive, from a computing device, enterprise merchant insights information;
train a first machine learning model to adjust a weight on each of input factors;
identify, based on the small business transaction data, based on the enterprise merchant insights information, and using the trained first machine learning model, recurring transactions associated with purchase of one or more services from the software vendor;
train a second machine learning model to adjust a weight on each of prediction factors;
generate, based on the recurring transactions and using the trained second machine learning model, an average contract price associated with a first service of the one or more services provided by the software vendor, and a confidence score associated with the average contract price;
generate, based on the average contract price and the confidence score exceeding a threshold value, a recommendation comprising a renewal rate; and
based on a determination that the first service provided by the software vendor is coming due for a renewal, send, to a particular merchant, an alert associated with the renewal, wherein the alert comprises the recommendation.

### Claim 12 (depends on 11)

The prediction system of claim 11, the instructions cause the prediction system to:
receive the small business transaction data in a first data format;
receive the enterprise merchant insights information in a second data format; and
convert the small business transaction data and the enterprise merchant insights information into a common format.

### Claim 13 (depends on 12)

The prediction system of claim 12, wherein the first data format comprises unstructured data format, and the second data format comprises a text format.

### Claim 14 (depends on 11)

The prediction system of claim 11, wherein the first machine learning model and the second machine learning model comprises a unsupervised machine learning model or a back propagation model.

### Claim 15 (depends on 11)

The prediction system of claim 11, the instructions cause the prediction system to:
predict, using the second machine learning model, a growth rate in the average contract price associated with the first service; and
generate, based on the growth rate, the recommendation comprising the renewal rate.

### Claim 16 (depends on 11)

The prediction system of claim 11, the instructions cause the prediction system to:
collect training data comprising the prediction factors to be used as model input to the second machine learning model;
train the second machine learning model by adjusting a weight associated with each of the prediction factors; and
generate a plurality of contract prices based on the trained second machine learning model.

### Claim 17 (depends on 16)

The prediction system of claim 16, wherein the prediction factors comprise at least one of:
a merchant size, a merchant location, a merchant industry, a transaction amount, a frequency of payment, a vendor size, a vendor location and a type of software service.

### Claim 18

One or more non-transitory media storing instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:
receiving, by a first computing device, small business transaction data comprising payment information between a plurality of merchants and a software vendor;
receiving, from a second computing device, enterprise merchant insights information;
training, by the first computing device, a first machine learning model to adjust a weight on each of input factors;
identifying, based on the small business transaction data, based on the enterprise merchant insights information, and using the trained first machine learning model, recurring transactions associated with purchase of one or more services from the software vendor;
training, by the first computing device, a second machine learning model to adjust a weight on each of prediction factors;
receiving, from a particular merchant, an input comprising a contract term length;
generating, based on the recurring transactions, the contract term length and using the trained second machine learning model, an average contract price associated with a first service of the one or more services provided by the software vendor, and a confidence score associated with the average contract price;
generate, based on the average contract price and the confidence score exceeding a threshold value, a recommendation comprising a renewal rate; and
based on a determination that the first service provided by the software vendor is coming due for a renewal, send, to the particular merchant, an alert associated with the renewal, wherein the alert comprises the recommendation.

### Claim 19 (depends on 18)

The non-transitory media of claim 18, the instructions cause the one or more processors to perform:
receiving the small business transaction data in a first data format;
receiving the enterprise merchant insights information in a second data format; and
converting the small business transaction data and the enterprise merchant insights information into a common format.

### Claim 20 (depends on 19)

The non-transitory media of claim 19, wherein the first data format comprises a text format, and the second data format comprises unstructured data format.