Service Demand Prediction Using Competitor Relative Indices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing service demand prediction techniques fail to consider information from competing companies, limiting their accuracy in forecasting service demand potential across different areas.
Innovation Solution
A service demand potential prediction device that acquires and calculates relative indices between own-company and competitor service provision data, selects dominant areas, constructs machine learning models using area characteristics, and predicts demand in non-dominant areas by inputting those characteristics into the model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only own-company service provision information is used for prediction, then the prediction process is simple, but the prediction accuracy is insufficient due to ignoring competitor information
Solution Approach 1:
The patent segments the prediction process into distinct functional units: an acquisition unit that collects both own-company and competitor service provision information, a calculation unit that computes relative indices, a selection unit that identifies dominant areas, and a construction unit that builds machine learning models. This segmentation allows the system to handle complex multi-source data processing while maintaining organizational clarity and manageable complexity.
Solution Approach 2:
The patent introduces a relative index as an intermediary metric that quantifies the relationship between own-company and competitor service provision. This relative index serves as a mediator that transforms raw competitor data into a comparable format, enabling accurate prediction without directly comparing heterogeneous data sources. The intermediary simplifies the integration of competitor information into the prediction framework.
2Measurement precision
If extensive detailed data is collected for prediction, then prediction accuracy improves, but data processing complexity and resource requirements increase
Solution Approach 1:
The patent extracts only the essential features needed for prediction: the number of service provision results from own-company and competitor services, and basic area characteristics. By extracting only these critical elements rather than processing all available detailed data, the system achieves accurate prediction while minimizing data processing complexity and resource requirements.
Solution Approach 2:
The patent transforms raw service provision data into a relative index parameter that captures the competitive relationship between own-company and competitor services. This parameter transformation converts complex multi-dimensional data into a simplified metric that retains predictive power while reducing processing requirements. The machine learning model then operates on these transformed parameters rather than raw detailed data.
Data Source
AI summary
A service demand potential prediction device (10) includes: an acquisition unit (11) for acquiring the number of service provision results for own-company service and other-company service for each area; a calculation unit (12) for calculating a relative index of the own-company service to the other-company service for each area; a selection unit (13) for selecting a dominant area where the own-company service is dominant; a construction unit (14) for constructing a model (M) by performing machine learning using a characteristic amount of the dominant area as an explanatory variable and the number of service provision results of the own-company service as an objective variable; and a prediction unit (15) for predicting a service demand potential of the own-company service when the non-dominant area is assumed to be a dominant area by inputting the characteristic amount of the non-dominant area into the model (M).