Multi-modal Shopper Trajectory Tracking for Brand Strength Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for understanding and influencing brand buying decisions lack insight into the in-store shopping behavior of shoppers, particularly distinguishing between pre-shelf and at-shelf purchase decisions, relying heavily on consumer behavior and sales data which provide limited insight into the decision-making process.
Innovation Solution
A system utilizing cameras and mobile signal sensors to track shopper behavior, forming trajectories, and determining decision factors to differentiate between pre-shelf and at-shelf purchase decisions, aggregating data to analyze brand or category strength.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional consumer behavior studies and sales data are used to understand brand buying decisions, then research budgets can be allocated and brand performance can be tracked, but little to no insight is provided into the actual in-store shopping and buying behavior between these endpoints
Solution Approach 1:
The patent combines multiple data sources including mobile device location data, camera footage, shopper interviews, and sales data into a unified tracking system. This merging of previously separate information streams provides comprehensive in-store behavior insights while managing complexity through integrated data processing.
Solution Approach 2:
The tracking system serves multiple functions: it captures shopper location, monitors product interactions, records purchase decisions, and collects demographic information. This multi-functionality addresses the information loss problem by providing a single system that performs various tracking and analysis tasks simultaneously.
2Measurement precision
If surveys or shopper interviews are used to obtain decision process information, then some insight into buying behavior can be gained, but shopper participation is required which introduces bias and limits sample size
Solution Approach 1:
The system uses mobile devices that shoppers already carry and use voluntarily. The mobile device location data and app interactions provide self-generated information about shopper behavior without requiring active participation in surveys, thereby expanding sample size while maintaining data accuracy through natural behavior tracking.
Solution Approach 2:
The patent replaces manual survey and interview methods with automated electronic tracking systems. Mobile device data collection and camera-based monitoring substitute for human researchers conducting interviews, enabling large-scale data collection without the bias and sample size limitations of voluntary participation methods.
3Reliability
If large budgets are spent on brand marketing and promotion to drive trial and loyalty, then brand performance can be improved, but there is limited ability to measure the direct impact of these investments on at-shelf versus pre-shelf decisions
Solution Approach 1:
The system provides real-time feedback by tracking shopper journey and decision points. It captures when and where purchase decisions are made (pre-shelf versus at-shelf), enabling brands to measure the effectiveness of marketing investments at different stages of the consumer journey and adjust strategies accordingly.
Solution Approach 2:
The patent segments the buying decision process into distinct phases: pre-shelf decisions made before entering the store or aisle, and at-shelf decisions made while viewing products. This segmentation allows for targeted measurement of marketing impact on different decision types, providing more reliable performance metrics.
Data Source
AI summary
A method and system for analyzing product strength or brand strength by determining shopper decision behavior during a shopping trip. Specifically, shopper behavior can be analyzed to determine whether a shopper's decision to purchase an item occurred at-shelf or pre-shelf. Aggregating decision data across many shoppers over time can then be used to generate analytics regarding the strength of a product or brand. The analysis can then be used to make recommendations to manufacturers or retailers about how to strengthen the product or brand. A deployment of cameras and mobile signal sensors can be utilized to recognize shoppers and track their behavior. Demographics information can also be estimated about the tracked shoppers. The visual and mobile signal trajectories can be fused to form a single shopper trajectory, then associated with Point of Sale (PoS) data. This results in a dataset describing the shopping trip for each tracked shopper.