Time-Series Forecasting Pipeline with Demand Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing time-series forecasting systems are rigid and closed, limiting the opportunity to specify alternative modeling approaches, and require arduous programming, testing, and implementation of complex commands.
Innovation Solution
A pipeline system for time-series forecasting that includes a graphical user interface (GUI) for building and executing forecasting pipelines, allowing users to drag and drop operations, select model strategies, and automatically add or remove operations, enabling flexible and efficient processing of time-series data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If existing time-series forecasting systems are used, then forecasting can be performed, but the system is rigid and closed, limiting alternative modeling approaches and requiring arduous programming and testing
Solution Approach 1:
The forecasting system is segmented into multiple independent pipeline components that can be selectively assembled. Each pipeline represents a distinct forecasting approach with its own sequence of operations, allowing users to choose and compare different modeling strategies without being constrained by a monolithic rigid system.
Solution Approach 2:
The pipeline framework provides a universal structure that can accommodate multiple forecasting models and approaches within a single system. The same pipeline infrastructure supports diverse modeling techniques, enabling the system to perform multiple forecasting functions through a unified flexible interface.
2Adaptability or versatility
If multiple alternative modeling strategies are implemented, then forecasting flexibility improves, but resource consumption increases
Solution Approach 1:
The system implements multiple modeling strategies but allows users to execute only the necessary subset for each forecasting task. Not all pipelines need to be run simultaneously - users can select and execute only those relevant to their specific forecasting needs, reducing overall resource consumption while maintaining the capability for diverse modeling approaches.
Solution Approach 2:
The system changes the parameter of pipeline execution from always-executing all models to selectively executing based on relevance. By dynamically adjusting which pipelines are activated based on the specific forecasting task, the system maintains modeling strategy variety while optimizing resource usage.
Data Source
AI summary
A pipeline system for time-series data forecasting using a distributed computing environment is disclosed herein. In one example, a pipeline for forecasting time series is generated. The pipeline represents a sequence of operations for processing the time series to produce modeling results such as forecasts of the time series. The pipeline includes a segmentation operation for categorizing the time series into multiple demand classes based on demand characteristics of the time series. The pipeline also includes multiple sub-pipelines corresponding to the multiple demand classes. Each of the sub-pipelines applies a model strategy to the time series in the corresponding demand class. The model strategy is selected from multiple candidate model strategies based on predetermined relationships between the demand classes and the candidate model strategies. The pipeline is executed to determine the modeling results for the time series.