# US 2024/0202730 A1 · Systems and methods for identifying risks in a sales pipeline

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

- Number: US 2024/0202730 A1
- Document ID: US20240202730A1
- Status: Published application
- Kind: A1
- Application number: 18/083,120
- Filed: 2022-12-16
- Published: 2024-06-20
- Earliest claimed: 2022-12-16
- Assignees: Dell Products L.P.
- Applicants: Dell Products L.P.
- Inventors: Pratik Jain; Anna V. Popova; Vinod Babu Palani; Sudipta Pradhan
- Web page: https://patentgrep.com/patent/US20240202730A1

## CPC

- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G06Q 10/0635: Risk analysis of enterprise or organisation activities
- 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

A method for identifying a risk deal in a dynamic sales pipeline, the method that includes selecting, by a risk data generator, a model based on historical accuracy, generating risk data for a sales entry in a dynamic sales pipeline, using the model, making a determination that the risk data indicates a risk deal, and in response to the determination, setting a risk flag in the sales entry.

## Claims

### Claim 1

A method for identifying a risk deal in a dynamic sales pipeline, the method comprising:
selecting, by a risk data generator, a model based on historical accuracy;
generating risk data for a sales entry in a dynamic sales pipeline, using the model;
making a determination that the risk data indicates a risk deal; and
in response to the determination:
setting a risk flag in the sales entry.

### Claim 2 (depends on 1)

The method of claim 1, wherein prior to selecting the model, the method further comprises:
generating historical pipeline data comprising user input;
training a plurality of models using the historical pipeline data, wherein the plurality of models comprises the model; and
identifying, based on the training, the model as the most accurate model.

### Claim 3 (depends on 2)

The method of claim 2, wherein training the plurality of models, comprises:
generating a plurality of identified risks datasets using the plurality of models, respectively;
analyzing the identified risks datasets to calculate a plurality of historical accuracies, respectively, wherein the plurality of historical accuracies comprises the historical accuracy; and
identifying the historical accuracy as the most accurate, wherein the historical accuracy is calculated using the model.

### Claim 4 (depends on 1)

The method of claim 1, wherein generating the risk data, comprises:
analyzing the sales entry to identify a risk factor; and
assigning a risk value to the risk factor, wherein the risk data comprises the risk value and the risk factor.

### Claim 5 (depends on 4)

The method of claim 4, wherein making the determination that the risk data indicates the risk deal, comprises:
determining that the risk value is greater than a threshold.

### Claim 6 (depends on 1)

The method of claim 1, wherein after setting the risk flag, the method further comprises:
providing the risk data in a user interface.

### Claim 7 (depends on 6)

The method of claim 6, wherein after providing the risk data in the user interface, the method further comprises:
receiving user input, in the user interface, from a user; and
saving the user input in the sales entry.

### Claim 8 (depends on 7)

The method of claim 7, wherein the user input unsets the risk flag.

### Claim 9

A non-transitory computer readable medium comprising instructions which, when executed by a processor, enables the processor to perform a method for identifying a risk deal in a dynamic sales pipeline, the method comprising:
selecting, by a risk data generator, a model based on historical accuracy;
generating risk data for a sales entry in a dynamic sales pipeline, using the model;
making a determination that the risk data indicates a risk deal; and
in response to the determination:
setting a risk flag in the sales entry.

### Claim 10 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein prior to selecting the model, the method further comprises:
generating historical pipeline data comprising user input;
training a plurality of models using the historical pipeline data, wherein the plurality of models comprises the model; and
identifying, based on the training, the model as the most accurate model.

### Claim 11 (depends on 10)

The non-transitory computer readable medium of claim 10, wherein training the plurality of models, comprises:
generating a plurality of identified risks datasets using the plurality of models, respectively;
analyzing the identified risks datasets to calculate a plurality of historical accuracies, respectively, wherein the plurality of historical accuracies comprises the historical accuracy; and
identifying the historical accuracy as the most accurate, wherein the historical accuracy is calculated using the model.

### Claim 12 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein generating the risk data, comprises:
analyzing the sales entry to identify a risk factor; and
assigning a risk value to the risk factor, wherein the risk data comprises the risk value and the risk factor.

### Claim 13 (depends on 12)

The non-transitory computer readable medium of claim 12, wherein making the determination that the risk data indicates the risk deal, comprises:
determining that the risk value is greater than a threshold.

### Claim 14 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein after setting the risk flag, the method further comprises:
providing the risk data in a user interface.

### Claim 15 (depends on 14)

The non-transitory computer readable medium of claim 14, wherein after providing the risk data in the user interface, the method further comprises:
receiving user input, in the user interface, from a user; and
saving the user input in the sales entry.

### Claim 16 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the user input unsets the risk flag.

### Claim 17

A computing device, comprising:
a processor; and
memory storing instructions which, when executed by the processor, enables the processor to perform a method for identifying a risk deal in a dynamic sales pipeline, the method comprising:
selecting, by a risk data generator, a model based on historical accuracy;
generating risk data for a sales entry in the dynamic sales pipeline, using the model;
making a determination that the risk data indicates the risk deal; and
in response to the determination:
setting a risk flag in the sales entry.

### Claim 18 (depends on 17)

The computing device of claim 17, wherein prior to selecting the model, the method further comprises:
generating historical pipeline data comprising user input;
training a plurality of models using the historical pipeline data, wherein the plurality of models comprises the model; and
identifying, based on the training, the model as the most accurate model.

### Claim 19 (depends on 18)

The computing device of claim 18, wherein training the plurality of models, comprises:
generating a plurality of identified risks datasets using the plurality of models, respectively;
analyzing the identified risks datasets to calculate a plurality of historical accuracies, respectively, wherein the plurality of historical accuracies comprises the historical accuracy; and
identifying the historical accuracy as the most accurate, wherein the historical accuracy is calculated using the model.

### Claim 20 (depends on 17)

The computing device of claim 17, wherein generating the risk data, comprises:
analyzing the sales entry to identify a risk factor; and
assigning a risk value to the risk factor, wherein the risk data comprises the risk value and the risk factor.
