# US 2021/0065207 A1 · Validation of models and data for compliance with laws

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

- Number: US 2021/0065207 A1
- Document ID: US20210065207A1
- Status: Published application
- Kind: A1
- Application number: 17/020,094
- Filed: 2020-09-14
- Published: 2021-03-04
- Earliest claimed: 2019-08-12
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Jeremy Edward GOODSITT; Austin Grant WALTERS; Fardin ABDI TAGHI ABAD; Vincent PHAM; Anh TRUONG; Reza FARIVAR; Kate KEY
- Web page: https://patentgrep.com/patent/US20210065207A1

## CPC

- G06Q 30/018: Certifying business or products
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/08: Learning methods
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 7/046: {Implementation by means of a neural network (neural networks using fuzzy logic G06N3/043)}
- H04L 1/002: {Algorithms with memory of the previous states, e.g. Markovian models}
- G06N 5/048: Fuzzy inferencing
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

The present disclosure provides computing systems and techniques for validating a decision model against a cannon of regulation. A server can deconstruct a decision model into a number of branching decisions and also generate a Markov chain comprising a number of sequences from a cannon of regulation. The server can compare the branching decisions to the sequences and can validate the decision model with the cannon of regulation based on the comparison.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

An apparatus, comprising:
a processor; and
a memory coupled to the processor, the memory comprising instructions that when executed by the processor cause the processor to:
identify a lineage of a set of input data, the set of input data associated with a decision model, wherein the decision model is arranged to generate at least one output from the set of inputs;
receive an information element comprising indications of a canon of regulation, the canon of regulation comprising a plurality of requirements and a plurality of prohibitions;
recognize text and syntax from the canon of regulation;
generate a Markov chain comprising a plurality of sequences, wherein ones of the plurality of sequences of the Markov chain correspond to the plurality of requirements and other ones of the plurality of sequences of the Markov chain correspond to the plurality of prohibitions; and
determine whether the decision model infringes the canon or regulation based on the lineage of the set of input data and the plurality of sequences of the Markov chain.

### Claim 22 (depends on 21)

The apparatus of claim 21, the memory further comprising instructions that when executed by the processor cause the processor to:
determine whether the lineage of the set of input data matches at least one of the plurality of sequences of the Markov chain; and
determine that the decision model infringes the canon or regulation based on a determination that the lineage of the set of input data matches at least one of the plurality of sequences of the Markov chain.

### Claim 23 (depends on 21)

The apparatus of claim 21, the memory further comprising instructions that when executed by the processor cause the processor to:
determine whether the lineage of the set of input data matches at least one of the plurality of sequences of the Markov chain; and
determine that the decision model does not infringe the canon or regulation based on a determination that the lineage of the set of input data does not match at least one of the plurality of sequences of the Markov chain.

### Claim 24 (depends on 21)

The apparatus of claim 21, the memory further comprising instructions that when executed by the processor cause the processor to:
deconstruct the decision model into a plurality of branching decisions; and
determine whether the decision model infringes the canon or regulation based on the plurality of branching decisions and the plurality of sequences of the Markov chain.

### Claim 25 (depends on 24)

The apparatus of claim 24, the memory further comprising instructions that when executed by the processor cause the processor to:
determine, for each of the plurality of branching decisions, whether the branching decision matches at least one of the plurality of sequences of the Markov chain; and
determine that the decision model infringes the canon or regulation based on a determination that the plurality of branching decisions matches at least one of the plurality of sequences of the Markov chain; or
determine that the decision model does not infringe the canon or regulation based on a determination that the plurality of branching decisions do not match at least one of the plurality of sequences of the Markov chain.

### Claim 26 (depends on 21)

The apparatus of claim 21, the memory further comprising instructions that when executed by the processor cause the processor to match the lineage of the set of input data to at least one of the plurality of sequences of the Markov chain based on a fuzzy logic algorithm or based on a neural network.

### Claim 27

At least one machine-readable storage medium comprising instructions that when executed by a processor at a computing platform, cause the processor to:
identify a lineage of a set of input data, the set of input data associated with a decision model, wherein the decision model is arranged to generate at least one output from the set of inputs;
receive an information element comprising indications of a canon of regulation, the canon of regulation comprising a plurality of requirements and a plurality of prohibitions;
recognize text and syntax from the canon of regulation;
generate a Markov chain comprising a plurality of sequences, wherein ones of the plurality of sequences of the Markov chain correspond to the plurality of requirements and other ones of the plurality of sequences of the Markov chain correspond to the plurality of prohibitions; and
determine whether the decision model infringes the canon or regulation based on the lineage of the set of input data and the plurality of sequences of the Markov chain.

### Claim 28 (depends on 27)

The at least one machine-readable storage medium of claim 27, comprising instructions that further cause the processor to:
determine whether the lineage of the set of input data matches at least one of the plurality of sequences of the Markov chain; and
determine that the decision model infringes the canon or regulation based on a determination that the lineage of the set of input data matches at least one of the plurality of sequences of the Markov chain.

### Claim 29 (depends on 27)

The at least one machine-readable storage medium of claim 27, comprising instructions that further cause the processor to:
determine whether the lineage of the set of input data matches at least one of the plurality of sequences of the Markov chain; and
determine that the decision model does not infringe the canon or regulation based on a determination that the lineage of the set of input data does not match at least one of the plurality of sequences of the Markov chain.

### Claim 30 (depends on 27)

The at least one machine-readable storage medium of claim 27, comprising instructions that further cause the processor to:
deconstruct the decision model into a plurality of branching decisions; and
determine whether the decision model infringes the canon or regulation based on the plurality of branching decisions and the plurality of sequences of the Markov chain.

### Claim 31 (depends on 30)

The at least one machine-readable storage medium of claim 30, comprising instructions that further cause the processor to:
determine, for each of the plurality of branching decisions, whether the branching decision matches at least one of the plurality of sequences of the Markov chain; and
determine that the decision model infringes the canon or regulation based on a determination that the plurality of branching decisions matches at least one of the plurality of sequences of the Markov chain; or
determine that the decision model does not infringe the canon or regulation based on a determination that the plurality of branching decisions do not match at least one of the plurality of sequences of the Markov chain.

### Claim 32 (depends on 27)

The at least one machine-readable storage medium of claim 27, comprising instructions that further cause the processor to match the lineage of the set of input data to at least one of the plurality of sequences of the Markov chain based on a fuzzy logic algorithm or based on a neural network.

### Claim 33 (depends on 27)

The at least one machine-readable storage medium of claim 27, comprising instructions that further cause the processor to input the recognized text and syntax to a recursive neural network (RNN) to generate the Markov chain comprising the plurality of sequences.

### Claim 34

A computer implemented method, comprising:
identifying a lineage of a set of input data, the set of input data associated with a decision model, wherein the decision model is arranged to generate at least one output from the set of inputs;
receiving an information element comprising indications of a canon of regulation, the canon of regulation comprising a plurality of requirements and a plurality of prohibitions;
recognizing text and syntax from the canon of regulation;
generating a Markov chain comprising a plurality of sequences, wherein ones of the plurality of sequences of the Markov chain correspond to the plurality of requirements and other ones of the plurality of sequences of the Markov chain correspond to the plurality of prohibitions; and
determining whether the decision model infringes the canon or regulation based on the lineage of the set of input data and the plurality of sequences of the Markov chain.

### Claim 35 (depends on 34)

The computer implemented method of claim 34, determining whether that the decision model infringes the canon or regulation based on the lineage of the set of input data and the plurality of sequences of the Markov chain comprising:
determining whether the lineage of the set of input data matches at least one of the plurality of sequences of the Markov chain; and
determining that the decision model infringes the canon or regulation based on a determination that the lineage of the set of input data matches at least one of the plurality of sequences of the Markov chain.

### Claim 36 (depends on 34)

The computer implemented method of claim 34, determining whether the decision model infringes the canon or regulation based on the lineage of the set of input data and the plurality of sequences of the Markov chain comprising:
determining whether the lineage of the set of input data matches at least one of the plurality of sequences of the Markov chain; and
determining that the decision model does not infringe the canon or regulation based on a determination that the lineage of the set of input data does not match at least one of the plurality of sequences of the Markov chain.

### Claim 37 (depends on 34)

The computer implemented method of claim 34, comprising:
deconstructing the decision model into a plurality of branching decisions; and
determining that the decision model infringes the canon or regulation based on the plurality of branching decisions and the plurality of sequences of the Markov chain.

### Claim 38 (depends on 37)

The computer implemented method of claim 37, determining whether that the decision model infringes the canon or regulation based on the plurality of branching decisions and the plurality of sequences of the Markov chain comprising:
determining, for each of the plurality of branching decisions, whether the branching decision matches at least one of the plurality of sequences of the Markov chain; and
determining that the decision model infringes the canon or regulation based on a determination that the plurality of branching decisions matches at least one of the plurality of sequences of the Markov chain; or
determining that the decision model does not infringe the canon or regulation based on a determination that the plurality of branching decisions do not match at least one of the plurality of sequences of the Markov chain.

### Claim 39 (depends on 34)

The computer implemented method of claim 34, wherein the decision model is a customer engagement model, a targeted advertising model, a business forecasting model, or a loan scoring model.

### Claim 40 (depends on 34)

The computer implemented method of claim 34, comprising inputting the recognized text and syntax to a recursive neural network (RNN) to generate the Markov chain comprising the plurality of sequences.
