Consumer Surplus Factor Computation System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining the Consumer Surplus Factor (CSF) in pricing and market share analysis are inadequate due to issues like multicollinearity, promotional activity spikes, and the inability to select the best models or explanatory variables, leading to inaccurate computations and data inefficiencies.
Innovation Solution
A system and method that combines data smoothing, regression, orthogonalization, and regularization techniques to create a super set of models and predictor variables, using Seemingly Unrelated Regression to remove correlations and normalize data, ultimately determining the Consumer Surplus Factor through statistical computation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If standard regression techniques are used to compute Consumer Surplus Factor, then the computation process is simple, but the results are inaccurate due to multicollinearity and promotional activity spikes
Solution Approach 1:
The patent segments the data processing into multiple distinct modules: data smoothening module to handle promotional spikes, multicollinearity removal module to address variable correlations, model creation module to generate candidate models, and regularization module to select optimal models. This segmentation allows each module to address specific data quality issues independently, improving overall computation accuracy while maintaining manageable system complexity through modular design.
Solution Approach 2:
The patent applies preliminary actions by performing data smoothening and multicollinearity removal before the actual Consumer Surplus Factor computation. The data is preprocessed to eliminate promotional activity spikes and correlated variables ahead of time, ensuring that the subsequent regression analysis operates on clean, independent data, thereby improving measurement precision without requiring complex real-time processing.
2Reliability
If all possible models and predictor variables are considered, then the analysis is comprehensive, but the computational complexity increases exponentially
Solution Approach 1:
The patent extracts only the most relevant predictor variables and models from the complete set of possibilities. The regularization techniques identify and extract the subset of variables with the strongest predictive power while removing redundant or correlated variables. This extraction process maintains analytical completeness by focusing on the most significant factors, thereby reducing computational complexity from exponential to manageable levels.
Solution Approach 2:
The patent changes parameters by transforming predictor variables into different forms and applying regularization penalties. By modifying the parameter representation and applying constraints, the system evaluates models more efficiently, comparing a manageable subset of transformed variables rather than exhaustively analyzing all possible combinations, thus maintaining reliability while reducing computational burden.
3Loss of information
If consumer surveys are used to capture consumer intent, then consumer perspective is obtained, but the intent does not translate to actual purchase/sales
Solution Approach 1:
The patent creates a computational copy of consumer behavior patterns through statistical modeling. Instead of relying on self-reported survey intent, the system builds regression models that copy and replicate actual purchase patterns from historical sales data. This computational copy captures the true relationship between pricing, promotions, and actual sales outcomes, eliminating the gap between stated intent and actual behavior while preserving consumer perspective information.
Data Source
AI summary
The present disclosure presents a system and method for determining Consumer Surplus Factor for a brand. The disclosed system and methods uses various techniques to counter the effect of spikes in data due to promotional activities, effects of multicollinearity among other things and also discloses a means for automatically determining the best possible models for computing Consumer Surplus Factor. The disclosed system and method use novel means of combining few known techniques which have been modified and integrated with additional novel steps to determine Consumer Surplus Factor. Beneficially, Consumer Surplus Factor can help in determining, without limitation, a pricing head room, maximum price a brand can charge, the optimal price to be charged and market share potential.