ARIMA Hyperparameter Tuning With Derivative-Free Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for estimating hyperparameters in ARIMA models are insufficient, complicating the model configuration and affecting the quality of predictions.
Innovation Solution
A method for tuning ARIMA model hyperparameters using a derivative-free approach, involving the determination of initial values, fitting the model, selecting a tuning method, computing objective function values, and updating hyperparameters until a stopping criterion is reached, to output tuned hyperparameter values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing techniques are used for estimating hyperparameters in ARIMA models, then the model configuration process is simplified, but the prediction quality deteriorates due to insufficient hyperparameter estimation
Solution Approach 1:
The system performs self-service by automatically determining initial hyperparameter values and conducting the entire tuning process without manual intervention. The processor autonomously executes the methodology to optimize hyperparameters, eliminating the need for expert manual configuration while achieving high estimation accuracy.
Solution Approach 2:
The system performs preliminary action by automatically determining initial hyperparameter values before the actual model training and tuning process. This preliminary step establishes a strong foundation for subsequent optimization, reducing the overall complexity of model configuration while ensuring high initial estimation accuracy.
2Measurement precision
If manual hyperparameter tuning is performed to improve prediction accuracy, then the prediction quality improves, but the time and computational resources required increase significantly
Solution Approach 1:
The system replaces manual mechanical tuning processes with an automated computational methodology. The processor executes the tuning algorithm, substituting human expert manual adjustment with an efficient automated system that achieves the same or better accuracy while significantly reducing the time and computational resources required.
Solution Approach 2:
The system efficiently explores hyperparameter space by systematically changing parameters according to the tuning methodology. This structured approach to parameter changes allows the system to find optimal values quickly without exhaustive search, balancing prediction accuracy with computational efficiency and time constraints.
3Reliability
If comprehensive hyperparameter estimation is performed to improve model quality, then the prediction reliability improves, but the computational complexity and resource requirements worsen
Solution Approach 1:
The system segments the hyperparameter estimation process into distinct phases: determining initial values, fitting the model, selecting tuning methods, computing objective function values, and updating parameters. This segmentation allows each phase to be optimized independently, achieving high prediction reliability while managing computational complexity through structured modular processing.
Solution Approach 2:
The system implements feedback mechanisms by computing objective function values based on time-series data and using these results to guide subsequent hyperparameter updates. This feedback loop ensures that the tuning process systematically improves prediction reliability while avoiding unnecessary computational complexity through data-driven decision making.
Data Source
AI summary
A system and method include tuning hyperparameters for an ARIMA model using a derivative free approach by determining a set of initial hyperparameter values, fitting an ARIMA model to the set of initial hyperparameter values, selecting a tuning method for the set of hyperparameters, responsive to selecting a single-objective method, computing a first objective function value from time-series data applied to the ARIMA model based on the set of initial hyperparameter values, or responsive to selecting a multi-objective method, computing at least a second objective function value and a third objective function value from the time-series data applied to the ARIMA model based on the set of initial hyperparameter values, determining whether a stopping criterion for tuning the set of hyperparameters has reached, responsive to determining that the stopping criteria has reached, outputting a set of tuned hyperparameter values.