William E Fitzgerald

US Patent:

20170270526, Sep 21, 2017

Filed:

Mar 15, 2016

Appl. No.:

15/070138

Inventors:

- Las Vegas NV, US
William Fitzgerald - Overland Park KS, US

International Classification:

G06Q 20/40
G06Q 40/00
G06N 99/00

Abstract:

System, method and media for detecting fraud in submissions of tax return data. Machine learning techniques including cluster analysis and tree-based classifiers are used to analyze large volumes of previously submitted tax returns based on tax data and submission-related data to detect patterns in genuine and fraudulent returns. These patters are then used to generate rules that can be installed in fraud detection systems in real time to prevent the submission of fraudulent returns. Previous classifications and fraud scores of submitted returns can be updated based on new rules or external indications of fraud.

US Patent:

20170270629, Sep 21, 2017

Filed:

Mar 15, 2016

Appl. No.:

15/070200

Inventors:

- Las Vegas NV, US
William Fitzgerald - Overland Park KS, US

International Classification:

G06Q 50/26
G06Q 40/00

Abstract:

A refinement verification engine authenticates a user submitting a subject tax return. The user is associated with an initial taxpayer identity confidence score in an intermediate range, such that the authenticity of the user is uncertain. The refinement verification engine is configured to perform the following steps: receiving tax information associated with the subject tax return for a subject taxpayer; acquiring an initial taxpayer identity confidence score that is indicative of a likelihood that the user is genuine; determining that the initial taxpayer identity confidence score falls into a predetermined range; identifying a verifiable data set within the taxpayer information; accessing an external data store containing information related to the verifiable data set; and determining whether information indicative of the verifiable data set is present in the external data store.