In-Store Consumer Decision Tree Construction via Video Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining consumer decision processes in retail environments are limited, as they often rely on consumer interpretation or human observation, providing a limited understanding of actual behavior and are not effective in capturing hierarchical purchase decisions in physical retail spaces.
Innovation Solution
A system and method using video cameras and proprietary software to capture and analyze in-store purchase behavior, combining behavioral data with transactional data to construct hierarchical decision trees that represent consumer decision processes without consumer involvement, incorporating gaze analysis and eye tracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If consumer interpretation or human observation methods are used to determine purchase decision processes, then consumer insights can be obtained, but the understanding of actual behavior is limited and measurement precision is poor
Solution Approach 1:
The patent replaces manual observation and consumer interpretation methods with an automated video analytics system. The system uses video cameras to capture shopper behavior and employs computer vision algorithms to automatically analyze movement patterns, time spent at product locations, and interaction sequences, thereby substituting mechanical human observation with an automated optical-mechanical system that provides superior measurement precision.
Solution Approach 2:
The patent introduces video analytics technology as an intermediary between the consumer and the researcher. Instead of directly observing or interviewing consumers, the system uses video cameras and image processing algorithms as intermediaries to capture and analyze behavior data, enabling indirect but more precise measurement of actual purchase decision processes without influencing consumer behavior.
2Reliability
If automated video analytics systems are used to capture in-store behavior, then objective and precise measurement of consumer decision processes is achieved, but the system complexity and cost increase
Solution Approach 1:
The patent implements a self-service automated system where the video analytics platform independently captures, processes, and analyzes behavior data without requiring human observers. The system automatically constructs decision trees from raw video data through algorithmic processing, enabling the system to serve itself in collecting and interpreting data, thereby ensuring objectivity while managing complexity through automation.
Solution Approach 2:
The patent incorporates feedback loops where the system continuously refines its analysis by comparing observed behavior patterns against established decision models. The video analytics system processes raw data, generates initial decision path interpretations, validates these against transaction data, and iteratively improves measurement accuracy, thereby enhancing reliability while systematically managing system complexity through controlled feedback mechanisms.
3Loss of information
If detailed behavioral data collection is implemented through video analytics, then hierarchical decision processes can be identified, but the extent of automation and data processing requirements increase
Solution Approach 1:
The patent applies segmentation by breaking down the complex decision process into hierarchical components. The video analytics system separately captures different behavioral dimensions (approach, examination, comparison, selection) and processes them through distinct analytical modules. Each segment of behavior is analyzed independently and then integrated to form the complete hierarchical decision tree, thereby preserving information completeness while managing automation complexity through modular processing.
Solution Approach 2:
The patent transforms two-dimensional video image data into multi-dimensional behavioral insights by analyzing spatial coordinates, temporal sequences, and interaction patterns simultaneously. The system extracts decision process information across multiple dimensions (location, time, duration, sequence) from the visual data, enabling comprehensive capture of hierarchical decision processes while using automated algorithms to efficiently process the multi-dimensional data without overwhelming complexity.
Data Source
AI summary
The present invention is a system and method for determining the hierarchical purchase decision process of consumers in front of a product category. The decision path of consumers is obtained by combining behavior data with the category layout and transaction data based on observed actual in-store purchase behavior using a set of video cameras and software for extracting sequence and timing of each consumer's decision process. A hierarchical decision tree structure comprises nodes and edges, wherein a node represents the state-of-mind of the consumer, the number of nodes is predefined, and an edge represents the transition of the decision. The decisions for each product group are captured down to the product attribute level and analyzed by demographic group. The outcome provides relative importance of each product attribute in the purchase decision process, and helps retailers and manufacturers to evaluate the layout of the category and customize it for key segment.