Anomaly Detection in Split Timeseries Datasets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for selecting appropriate machine learning models for anomaly detection in timeseries data are inefficient and often lead to inaccurate results, particularly in real-time applications like cybersecurity and fraud detection, due to manual or brute force approaches that require significant time and resources.
Innovation Solution
An automated model selection system that identifies temporal traits in timeseries datasets, such as trend, heteroskedasticity, or seasonality, to select and adjust appropriate anomaly detection models, optimizing model execution parameters based on the data characteristics and generating alerts for detected anomalies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual model selection is used to identify the best model for timeseries data, then model selection accuracy may be improved, but time consumption and resource usage increase significantly
Solution Approach 1:
The system enables automatic model selection through self-service mechanisms where the computer automatically evaluates multiple machine learning models against the timeseries data and selects the optimal model without human intervention, thereby resolving the contradiction between accuracy and time consumption
Solution Approach 2:
The patent replaces the manual mechanical process of model selection with an automated computational system that uses algorithms to evaluate models and select the best fit, eliminating human time investment while maintaining or improving selection accuracy
2Reliability
If brute force approach is used to run data through every model, then comprehensive model evaluation is achieved, but computing resources and time requirements become unacceptable
Solution Approach 1:
The patent segments the model evaluation process by categorizing models based on timeseries data traits (trend, seasonality, heteroskedasticity) and only evaluating relevant models for each data type, thereby maintaining comprehensive evaluation while reducing the number of models processed
Solution Approach 2:
The system performs preliminary analysis of the timeseries data to identify its traits before model evaluation begins, allowing the system to pre-filter suitable models and avoid running unnecessary evaluations, thus improving processing speed while maintaining evaluation completeness
3Measurement precision
If multiple models are evaluated to ensure accurate anomaly detection, then detection accuracy improves, but the process becomes unacceptable for real-time applications
Solution Approach 1:
The patent performs preliminary identification of timeseries data traits and pre-selection of suitable models before the actual anomaly detection process, enabling fast real-time detection while maintaining accuracy by ensuring the right model is chosen in advance
Solution Approach 2:
The system changes the parameter of model selection by adapting model choice to the specific traits of the timeseries data (trend, seasonality, heteroskedasticity), allowing accurate detection with a single optimized model rather than requiring multiple model evaluations
Data Source
AI summary
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.