Automated systems for reducing computational loads in the mass execution of analytical models using scale-out computing

Patent metadata

Field	Value
Publication number	US-9965741-B2
Application number	US-201615381906-A
Country	US
Kind code	B2
Filing date	Dec 16, 2016
Priority date	Dec 18, 2015
Publication date	May 8, 2018
Grant date	May 8, 2018

Abstract

Disclosed embodiments provide systems and techniques for mass execution of analytical models across multiple dimensions of client, collateral, deal structure, third party, and other data relevant to predicting optimal decisions in real-time. In some embodiments, disclosed systems and techniques increase decisioning speed through the reduction of computational loads on disclosed decisioning systems. Further disclosed systems and techniques may scale-out analytical modeling computations through, among other technological solutions, advanced execution environments that are asynchronous and non-blocking in nature so as to allow the execution of a plurality of analytical models in parallel and optimizing the results.

First claim

What is claimed is:

1. A system for reducing computational loads associated with predicting transactions using scale-out computing of analytical models, comprising:
a memory storing instructions; and
one or more processors configured to execute the instructions to perform operations comprising:
receiving, via an Application Programming Interface (API), a transaction proposal including a first plurality of transaction parameters;
iteratively verifying, via an actor pool associated with a data interface module, a plurality of data sources identified based on the transaction proposal;
generating, via a minimally viable transaction (MVT) generator, an MVT including a second plurality of transaction parameters, based on the transaction proposal;
generating, via an actor pool associated with a transaction generator, a plurality of transaction options based on the transaction proposal and the MVT;
scoring, via an actor pool associated with a scoring engine, at least one of the transaction options using the at least one analytical model;
verifying, via an actor pool associated with a policy calculator, that the transaction options comply with a transaction policy based on the scoring;
optimizing, via an actor pool associated with a transaction optimizer, the transaction options based on at least one preference; and
transmitting, via the API, at least one transaction offer based on the optimized transaction options.

2. The system of claim 1 , wherein at least one of the API, the data interface module, the MVT generator, the transaction generator, the scoring engine, the policy calculator, or the transaction optimizer comprise software modules.

3. The system of claim 2 , wherein the software modules are operated on a remote system.

4. The system of claim 1 , wherein the MVT represents a maximum extent for varying the first plurality of transaction parameters.

5. The system of claim 1 , wherein:
the scoring engine comprises instructions that cause the one or more processors to score the MVT using at least one analytical model;
the policy calculator comprises instructions that cause the one or more processors to determine that the MVT does not comply with a transaction policy, based on the scoring; and
wherein transmitting further comprises rejecting the transaction proposal.

6. The system of claim 1 , wherein the MVT generator comprises instructions that cause the one or more processors to:
identify at least one variation increment for each of the first plurality of transaction parameters; and
determine a plurality of transaction parameter variations between the first plurality of transaction parameters and second plurality of transaction parameters according to the at least one variation increment.

7. The system of claim 1 , wherein:
the transaction proposal indicates an inventory item;
the MVT generator is configured to cause the one or more processors to:
access an inventory database to identify a plurality of additional inventory items; and
generate inventory MVTs for at least one of the additional inventory items;

the transaction generator is further configured to cause the one or more processors to generate, via the actor pool associated with the transaction generator, a second plurality of transaction options based on the transaction proposal and the inventory MVTs;
the scoring engine is further configured to cause the one or more processors to score, via the actor pool associated with the scoring engine, at least one of the second plurality of transaction options using the at least one analytical model; and
the policy calculator is further configured to cause the one or more processors to verify, via the actor pool associated with the policy calculator, that at least one of the second plurality of transaction options complies with the transaction policy based on the scoring.

8. The system of claim 7 , further comprising:
a transaction optimizer configured to cause the one or more processors to optimizing, via an actor pool associated with the transaction optimizer, the plurality of transaction options and second plurality of transaction options based on the at least one preference; and
wherein the API is further configured to cause the one or more processors to transmit the at least one transaction offer based on the optimized plurality of transaction options and optimized second plurality of transaction options.

9. The system of claim 1 , wherein the at least one analytical model includes at least at applicant rating (AR) model and structure rating (SR) model.

10. The system of claim 1 , wherein the data interface module, the transaction generator, the scoring engine, the policy calculator, and the transaction optimizer comprise fault-tolerant and scalable applications.

11. The system of claim 1 , wherein the data interface module, the transaction generator, the scoring engine, the policy calculator, and the transaction optimizer are implemented in at least one of a big data, actor, message bus, or Lambda-based architecture.

12. The system of claim 1 , wherein one or more the operations are performed in parallel.

13. The system of claim 1 , wherein at least one actor pool is configured to expand or contract based on a computational load associated with the operations performed by said at least one actor pool.

14. A method for reducing computational loads associated with predicting optimal transactions using scale-out computing of analytical models, comprising:
receiving, via an Application Programming Interface (API), a transaction proposal including a first plurality of transaction parameters;
iteratively verifying a plurality of data sources identified based on the transaction proposal;
generating a minimally viable transaction (MVT) including a second plurality of transaction parameters, based on the transaction proposal;
generating a plurality of transaction options based on the transaction proposal and the MVT;
scoring at least one of the transaction options using the at least one analytical model;
verifying that the transaction options comply with a transaction policy based on the scoring;
optimizing the transaction options based on at least one preference; and
transmitting, via the API, at least one transaction offer based on the optimized transaction options.

15. The method of claim 14 , wherein at least one first operation is performed on a first system and at least one second operation is performed on a second system.

16. The method of claim 14 , wherein one or more the operations are performed in parallel.

17. The method of claim 14 , wherein at least one of the operations is performed by at least one actor pool configured to expand or contract based on a computational load associated with the operations performed by said at least one actor pool.

18. The method of claim 14 , wherein the MVT represents a maximum extent for varying the first plurality of transaction parameters.

19. The method of claim 14 , wherein the transaction proposal indicates an inventory item, and wherein the method further comprises:
accessing an inventory database to identify a plurality of additional inventory items;
generating inventory MVTs for at least one of the additional inventory items;
generating a second plurality of transaction options based on the transaction proposal and the inventory MVTs;
scoring at least one of the second plurality of transaction options using the at least one analytical model; and
verifying that at least one of the second plurality of transaction options complies with t

Assignees

• Capital One Services Llc

Inventors

• Dhandapani Chandra
• Bajaj Raman
• Singh Gurmeet
• Karuthakantakath Ajmal
• Crable Fred
• Dolle Nicholas
• Repaka Vikramaditya
• Yajnik Sanjiv

Classifications

• G06Q40/03

  Credit; Loans; Processing thereof · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q10/087 Primary

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title

• G06N5/045

  Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence · CPC title

• G06F30/20

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title