Automatic model selection for a time series

US11789915B2 · kind B2 · utility

Assignee

• CAPITAL ONE SERVICES, LLC · US

Inventors

• Vannia Gonzalez Macias · McLean, US
• Talha Koc · McLean, US
• Mark Davis · Menlo Park, US
• Prarthana Bhattarai · Quincy, US
• Mark Roberts · McLean, US
• Alan Rozet · McLean, US
• Mengfei Shao · McLean, US

Key dates

• Filing date: Apr 23, 2021
• Grant date: Oct 17, 2023
• Expiry date: Jun 20, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06F16/211
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Methods and systems are described herein for improving anomaly detection in timeseries datasets. Different machine learning models may be trained to process specific types of timeseries data efficiently and accurately. Thus, selecting a proper machine learning model for identifying anomalies in a specific set of timeseries data may greatly improve accuracy and efficiency of anomaly detection. Another way to improve anomaly detection is to process a multitude of timeseries datasets for a time period (e.g., 90 days) to detect anomalies from those timeseries datasets and then correlate those detected anomalies by generating an anomaly timeseries dataset and identifying anomalies within the anomaly timeseries dataset. Yet another way to improve anomaly detection is to divide a dataset into multiple datasets based on a type of anomaly detection requested.