Time-Series Predictive Modeling with Skip-Range Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional predictive modeling approaches are inefficient and costly, often exploring only a small portion of the vast predictive modeling space, leading to suboptimal results and high resource consumption.
Innovation Solution
A systematic method for rigorously and efficiently exploring the time-series modeling search space by parametrizing aspects such as training and testing data intervals, skip and forecast ranges, and using feature importance metrics to guide resource allocation and model blending.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional predictive modeling approaches are used, then resource consumption is reduced, but model accuracy and performance deteriorate due to exploring only a small portion of the predictive modeling space
Solution Approach 1:
The patent segments the vast predictive modeling space into manageable subsets using systematic parametrization of training/testing data intervals, skip ranges, and forecast ranges. This segmentation allows thorough exploration of the modeling space without requiring exhaustive search of all possible configurations, thereby improving model accuracy while controlling resource consumption.
Solution Approach 2:
The patent employs feature importance metrics to perform preliminary analysis and identify the most influential features before building predictive models. This preliminary action guides resource allocation to the most promising model configurations and features, enabling more accurate models to be developed with fewer computational resources.
2Measurement precision
If exhaustive exploration of the predictive modeling space is performed, then model accuracy improves, but time and computational resources increase significantly
Solution Approach 1:
The patent implements dynamic resource allocation that adapts based on feature importance metrics and intermediate modeling results. The system dynamically adjusts the extent of exploration for different feature subsets and model configurations, intensifying search in promising areas while reducing effort in less promising areas, thereby achieving high accuracy without exhaustive time-consuming search.
Solution Approach 2:
The patent systematically varies key parameters such as training data intervals, testing data intervals, skip ranges, and forecast ranges to explore the predictive modeling space. By changing these parameters in a structured manner rather than exhaustively, the method achieves thorough exploration efficiency, improving model accuracy while limiting time loss.
3Productivity
If systematic exploration of the modeling space is implemented, then resource utilization efficiency improves, but system complexity increases due to multiple parameters and metrics
Solution Approach 1:
The patent develops a unified systematic framework that simultaneously handles multiple parameters (training intervals, testing intervals, skip ranges, forecast ranges) and feature importance metrics through integrated computational procedures. This universal approach consolidates what would otherwise be separate complex analyses into a cohesive system, improving resource utilization efficiency while managing overall system complexity through integration rather than multiplication of separate components.
Data Source
AI summary
A predictive modeling method may include determining a time interval of time-series data; identifying one or more variables of the data as targets; determining a forecast range and a skip range associated with a prediction problem represented by the data; generating training data and testing data from the time-series data; fitting a predictive model to the training data; and testing the fitted model on the testing data. The forecast range may indicate a duration of a period for which values of the targets are to be predicted. The skip range may indicate a temporal lag between the time period corresponding to the data used to make predictions and the time period corresponding to the predictions. The skip range may separate input data subsets representing model inputs from subsets representing model outputs, and separate test data subsets representing model inputs from subsets representing validation data.