Scenario Combination Selection for High-Coverage Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing scenario planning methods face difficulties in creating a small number of scenarios that can effectively cover possible future events, leading to an overwhelming number of scenarios that humans cannot understand, making it difficult to create appropriate predictions.
Innovation Solution
An information processing apparatus that generates and determines a combination of scenarios based on evaluation values and the number of scenarios, using a combination of a generating unit and a determining unit to create scenarios including explanatory and objective variables, and optimize the scenario selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If scenarios are increased to cover possible future events with high probability, then the coverage of future events is improved, but the number of scenarios becomes excessive and human understanding becomes difficult
Solution Approach 1:
The patent segments the large set of generated scenarios into multiple groups or clusters. By dividing the scenarios into smaller manageable groups, the system maintains high coverage probability while reducing the complexity for human understanding. Each group can be independently analyzed and understood, solving the contradiction between comprehensive coverage and human comprehensibility.
Solution Approach 2:
The patent extracts and selects only the most representative or critical scenarios from the generated set. By taking out the essential scenarios that provide the majority of coverage value, the system achieves high coverage probability with a reduced number of scenarios, thereby resolving the contradiction between coverage and complexity.
2Ease of operation
If the number of scenarios is reduced for human understanding, then the ease of operation is improved, but the coverage of possible future events decreases
Solution Approach 1:
The patent changes parameters such as the number of scenarios selected, the grouping structure, or the representation format to optimize both human understanding and coverage. By adjusting these parameters, the system finds the optimal balance where a manageable number of scenarios provides sufficient coverage probability, resolving the contradiction between ease of operation and reliability.
3Reliability
If more scenarios are created to cover edge cases, then the reliability of prediction is improved, but the complexity of scenario management increases
Solution Approach 1:
The patent segments scenarios into different categories or priority levels, allowing edge cases to be systematically organized. This segmentation reduces management complexity by providing structured approaches to handling different types of scenarios while maintaining comprehensive coverage for improved prediction accuracy.
Solution Approach 2:
The patent applies partial action by selecting only the most critical edge cases rather than attempting to model every possible scenario. By focusing on the most impactful edge cases, the system achieves sufficient prediction accuracy without the excessive complexity of managing all conceivable scenarios.
Data Source
AI summary
An information processing apparatus of the present disclosure includes: a generating unit that generates, based on case data each including a plurality of sets of explanatory variables and objective variables, a plurality of scenarios each including a pair of a condition of the explanatory variable and a prediction value based on the objective variable of the case data falling under the condition; and a determining unit that determines a combination of the scenarios, based on an evaluation value calculated in accordance with whether the case data falls under the condition of the scenario to be combined and a number of the scenarios to be combined.