Method and system for cleansing training data for predictive models

US10909095B2 · kind B2 · utility

Assignee

• Oracle International Corporation · US

Inventors

• Yaser I. Suleiman · Santa Clara, US
• Michael Zoll · Foster City, US
• Subhransu Basu · Fremont, US
• Angelo Pruscino · Los Angeles, US
• Wolfgang Lohwasser · Munich, DE
• Wataru Miyoshi · Redwood City, US
• Thomas Breidt · Munich, DE
• Thomas Herter · Santa Clara, US
• Klaus Thielen · Munich, DE
• Sahil Kumar · Redwood City, US

Key dates

• Filing date: Sep 18, 2017
• Grant date: Feb 2, 2021
• Expiry date: Aug 8, 2038

Classification

• Technology area (CPC H): Electricity
• CPC primary: H04L43/02
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Described is an improved approach to implement selection of training data for machine learning, by presenting a designated set of specific data indicators where these data indicators correspond to metrics that end users are familiar with and are easily understood by ordinary users and DBAs within their knowledge domain. Selection of these indicators would correlate automatically to selection of a corresponding set of other metrics/signals that are less understandable to an ordinary user. Additional analysis of the selected data can then be performed to identify and correct any statistical problems with the selected training data.