IP Library › Granted Patent US 10,740,681

Granted Patent B2

US 10,740,681 · App. 15/001,952 · Granted Aug 11, 2020

Predictive modeling for adjusting initial values

Inventors: James S. Burroughs (Huntersville, NC); Mark Potts (Cherry Hills Village, CO); Sheethal Kumar (Chicago, IL); David B. Treat (Chicago, IL); Velayudhan Pillai (Chicago, IL); Vivek Kayarat (Ottapalam, IN)

Assignee: Accenture Global Solutions Limited

G06N5/04 G06N7/005 G06Q40/06 G06N20/00

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 10,740,681
App. No.: 15/001,952
Granted: Aug 11, 2020
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predictive modeling for adjusting initial values are disclosed. In one aspect, a method includes the actions of accessing transaction history data that indicates one or more transaction details associated with the transaction, a predicted value, and a final value. The actions further include determining a difference value between the predicted value and the final value. The actions further include generating a predictive model that is trained to estimate. The actions further include receiving one or more transaction details and a predicted value associated with a subsequently received transaction. The actions further include providing the one or more transaction details as input to the predictive model. The actions further include receiving an adjustment value to apply to the predicted value. The actions further include providing, for output, data indicating the adjustment value.

Claims (91)

1. A computer-implemented method comprising:

accessing transaction history data that, for each of one or more past transactions, indicates past transaction details associated with the past transaction, a past predicted value, and a past final value, wherein the past transaction details include a past sentiment associated with a past requesting entity requesting the past transaction, a past value sensitivity of the past requesting entity, and a past relationship between the past requesting entity requesting the past transaction and a past processing entity processing the past transaction;

for each of the one or more past transactions, determining a past difference value between the past predicted value and the past final value;

training, using machine learning and the past transaction details and the past difference value, a predictive model that is configured to receive a given sentiment associated with a given requesting entity requesting a given transaction, a given value sensitivity of the given requesting entity, a given relationship between the given requesting entity and a given processing entity processing the given transaction, and a given predicted value associated with the given transaction and output a given difference value to apply to the given predicted value;

receiving a sentiment associated with a requesting entity requesting a transaction, a value sensitivity of the requesting entity, a relationship between the requesting entity and a processing entity processing the transaction, and a predicted value associated with the transaction;

providing the sentiment associated with the requesting entity requesting the transaction, the value sensitivity of the requesting entity, the relationship between the requesting entity and the processing entity processing the transaction, and the predicted value associated with the transaction as input to the predictive model;

in response to providing the sentiment associated with the requesting entity requesting the transaction, the value sensitivity of the requesting entity, the relationship between the requesting entity and the processing entity processing the transaction, and the predicted value associated with the transaction as input to the predictive model, receiving, from the predictive model, an adjustment value to apply to the predicted value; and

providing, for output, data indicating the adjustment value.

2. The method of claim 1 , wherein:

the past sentiment associated with the past requesting entity is a past real-time sentiment that is based on past real-time data associated with the past requesting entity,

the given sentiment associated with the given requesting entity is a given real-time sentiment that is based on given real-time data associated with the given requesting entity, and

the sentiment associated with the requesting entity is a real-time sentiment that is based on real-time data associated with the requesting entity.

3. The method of claim 1 , wherein:

the past relationship between the past requesting entity requesting the past transaction and the past processing entity processing the past transaction is based on past real-time data associated with the past requesting entity and the past processing entity,

the given relationship between the given requesting entity requesting the given transaction and the given processing entity processing the given transaction is based on given real-time data associated with the given requesting entity and the given processing entity, and

the relationship between the requesting entity requesting the transaction and the processing entity processing the transaction is based on real-time data associated with the requesting entity and the processing entity.

4. The method of claim 1 , wherein:

the past sentiment associated with the past requesting entity requesting the past transaction is based on an analysis of past media that includes past references to the past requesting entity requesting the past transaction and contexts of the past references,

the given sentiment associated with the given requesting entity requesting the given transaction is based on an analysis of given media that includes given references to the given requesting entity requesting the given transaction and contexts of the given references, and

the sentiment associated with the requesting entity requesting the transaction is based on an analysis of media that includes references to the requesting entity requesting the transaction and contexts of the references.

5. The method of claim 1 , wherein:

the past value sensitivity of the past requesting entity requesting the past transaction is based on a past likelihood of the past requesting entity requesting an adjustment to the past predicted value,

the given value sensitivity of the given requesting entity requesting the given transaction is based on a given likelihood of the given requesting entity requesting an adjustment to the given predicted value, and

the value sensitivity of the requesting entity requesting the transaction is based on a likelihood of the requesting entity requesting an adjustment to the predicted value.

6. The method of claim 1 , wherein:

the transaction is a stock trade,

the predicted value is a predicted price per share, and

the adjustment value is an adjustment to the predicted price per share.

7. The method of claim 1 , wherein:

the past relationship between the past requesting entity requesting the past transaction and the past processing entity processing the past transaction is based on a past profitability realized by the past processing entity processing the past transaction in providing past services to the past requesting entity requesting the past transaction,

the given relationship between the given requesting entity requesting the given transaction and the given processing entity processing the given transaction is based on a given profitability realized by the given processing entity processing the given transaction in providing given services to the given requesting entity requesting the given transaction, and

the relationship between the requesting entity requesting the transaction and the processing entity processing the transaction is based on a profitability realized by the processing entity processing the transaction in providing services to the requesting entity requesting the transaction.

8. The method of claim 1 , comprising:

receiving data indicating an instruction to apply the adjustment value to the predicted value; and

executing the transaction with the predicted value adjusted by the adjustment value.

9. The method of claim 1 , wherein:

the past relationship between the past requesting entity requesting the past transaction and the past processing entity processing the past transaction is based on a number of changes the past requesting entity requesting the past transaction has requested for past previous transactions with the past processing entity,

the given relationship between the given requesting entity requesting the given transaction and the given processing entity processing the given transaction is based on a number of changes the given requesting entity requesting the given transaction has requested for given previous transactions with the given processing entity, and

the relationship between the requesting entity requesting the transaction and the processing entity processing the transaction is based on a number of changes the requesting entity requesting the transaction has requested for previous transactions with the processing entity.

10. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

for each of the one or more past transactions, determining a past difference value between the past predicted value and the past final value;

providing, for output, data indicating the adjustment value.

11. The system of claim 10 , wherein:

12. The system of claim 10 , wherein:

the value sensitivity of the requesting entity requesting the transaction is based on a likelihood of the requesting entity requesting an adjustment to the predicted value.

13. The system of claim 10 , wherein:

the transaction is a stock trade,

the predicted value is a predicted price per share, and

the adjustment value is an adjustment to the predicted price per share.

14. The system of claim 10 , wherein:

15. The system of claim 10 , wherein:

16. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

for each of the one or more past transactions, determining a past difference value between the past predicted value and the past final value;

providing, for output, data indicating the adjustment value.

17. The medium of claim 16 , wherein:

the past sentiment associated with the past requesting entity is a past real-time sentiment that is based on past real-time data associated with the past requesting entity,

the given sentiment associated with the given requesting entity is a given real-time sentiment that is based on given real-time data associated with the given requesting entity, and

the sentiment associated with the requesting entity is a real-time sentiment that is based on real-time data associated with the requesting entity.

18. The medium of claim 16 , wherein:

19. The medium of claim 16 , wherein the operations further comprise:

receiving data indicating an instruction to apply the adjustment value to the predicted value; and

executing the transaction with the predicted value adjusted by the adjustment value.

20. The medium of claim 16 , wherein:

Assignments (1)

ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 15, 2016

From: BURROUGHS, JAMES S.; POTTS, MARK; KUMAR, SHEETHAL; TREAT, DAVID B.; PILLAI, VELAYUDHAN; KAYARAT, VIVEK

To: ACCENTURE GLOBAL SOLUTIONS LIMITED

Reel/Frame 038295/0458 →

Priority Claims (1)

IN 6039/CHE/2015 · Nov 9, 2015 · national

Continuity (1)

Related Publication 20170132520A1 · May 11, 2017