Data science

Highly structured data science on consumer taste and entity attributes across entertainment, culture, and consumer products.

Machine learning

To process the data in real-time, Qloo uses proprietary machine learning algorithms that utilize leading statistical methodologies, rooted in the latest research in the emerging field of Neuroaesthetics — these include: deep learning methods, Bayesian statistics, neural networks, and proprietary NLP algorithms. We optimize for correlations that are meaningful and uniquely correlated (known as “anomalous co-occurrences”). Proprietary recursive training models are used to validate insights, properly partitioning all training data to avoid overfitting. Qloo connects over a dozen data domains in search of uniquely relevant insights to drive true excellence in programmatic cultural intelligence.

Qloo Data Stack Our Deep Learning data science works across three distinct layers
Description
Data Type
Totals
Entity database
Items and attributes
150+ million
API
Taste signals
5.2 billion signals
Deep learning
Specific to model
Contact sales
Layer 1

The Cultural Database

Qloo maintains a database of cultural entities—including important attributes pertaining to each one. Qloo’s AI currently services more than 150 million primary entities. These primary entities are available turn-key as input signals into the Qloo API.

Data Catalog Category coverage and corresponding total entity count
Music Artist, Albums, Songs
31,500,00+
Film Movies, Actors, Directors
2,500,00+
Music Artist, Albums, Songs
31,500,00+
Television Series, Personalities, Networks
850,000+
Books Titles, Authors, Publishers
18,500,000+
Media Apps, Games, Podcasts
1,100,000+
Dining Restaurants, Cafes, Eateries
31,500,00+
Nightlife Bars, Clubs, Venues
900,000+
Travel Hotels, Destinations, Attractions
4,700,000+
Fashion Designers, Labels, Stores
550,000+
People Public Figures, Influencers
175,000+
Sports Public Figures, Influencers
25,000+

Content based structured data

For every entity, Qloo maps a rigorous ontology of its most salient attributes, and cross references this to all other entities within the domain and even across domains.

Music

Music Artist

  • Parent Genre
  • Sub-Genres
  • Band Members
  • Discography
  • Record Label
  • Track Names
  • Instruments
  • Biographical Details
  • Live Performances
  • Influencers
  • Chart Statistics
  • Influenced
  • Collaborators
Dining

Restaurant

  • Cuisine
  • Address
  • Hours of Operation
  • All Menu Items
  • Business Attributes
  • Ambience
  • Dietary Details
  • Dress Code
  • Owner
  • Review Highlights
  • Price Levels
  • Noise Levels
  • Similar To
Layer 2

Taste Signals

Deep insights

Qloo develops custom routes for enterprises to address specific value-adds. These models will typically combine primary taste signals with Layer 1 attributes to create models that address unique use-cases.

Some examples of models that have been developed for clients include the following routes:

Entities
Entities

Input signal into Qloo’s API can be any of the 150+ million entities pre-mapped, and can also be attributes. Examples of raw signals include:

  • Unique Items Fashion Brand, Music, Artist, Hotel Name
  • Meta-Level Classifications Movie, Genre, Book Genre, Restaurant Cuisine
  • Demographic Endpoints and Custom, Personas Gender, Age
  • Lifestyle Traits
  • Custom Endpoints
Response
Response

Desired response is delivered in less than 50 milliseconds on average along with any delimiting fields, appended attributes and parameters.

Model training
Model training

Qloo then retrains models for subsequent calls based on batch anonymized input signals. Primary machine learning involves proprietary neural nets.

Layer 3

Deep learning

Deep insights

Qloo develops custom routes for enterprises to address specific value-adds. These models will typically combine primary taste signals with Layer 1 attributes to create models that address unique use-cases.

Some examples of models that have been developed for clients include the following routes:

Content Themes
Mainstream/Novelty
Introversion/Extraversion
Vanity
Political Leanings
Social issues
Travel preferences
Price sensitivity
Lifestyle preferences
Irony/Sincerity
General Affinity
Lifestyle preferences
Genre preferences
Propensity to Consume
Media Preferences

Further reading