Understanding Consumer Taste Through Data Patterns

Qloo’s AI-powered insights are built on billions of anonymized consumer interactions, capturing cross-category relationships that drive taste-based personalization. By analyzing co-occurrence signals, Qloo uncovers meaningful connections between music, film, TV, brands, dining, travel, sports, and more.

This page presents real-world representative data patterns, demonstrating how different entities are associated based on observed behaviors. These examples illustrate the breadth and depth of Qloo’s dataset and how it enables cultural intelligence at scale.

Core Concepts

• Pairwise Category Signals: A dataset capturing the strength of co-occurrences between entities from different categories (e.g., how often a movie preference aligns with a particular fashion brand).
• Cross-Category Correlations: Insights derived from Qloo’s AI models, showing how preferences in one category (e.g., dining) relate to another (e.g., music).

Pairwise Category Signals and Cross-Category Correlations

This section examines how different categories interact within Qloo’s dataset, revealing meaningful relationships between consumer preferences.

Cross-Category Transaction Examples

The examples below illustrate how single events containing cross-category entity co-occurrences contribute to Qloo’s understanding of cultural correlations:

Pairwise Co-Occurrence Matrix

The matrix below displays the co-occurring signal count for pairwise cross-category relationships, highlighting consumer taste overlaps across music, film, TV, brands, dining, and more: