Factori People Data For AI & ML Engines | USA | 200M+

Consumer graph data is gathered and dynamically collected to help AI and ML teams enrich existing databases or identify new customer profiles with similar interests to current customers. Factori's consumer data graph spans 900 million records captured once per event, updated monthly, making it suitable for behavioral feature construction, audience segmentation, and consumer-level ML pipelines. The dataset covers user demographics, MAID, device details, location, affluence, interests, and traveled countries across 100+ attributes.

Identity & Device: Anonymous_id, id_type, carrier, make, model, os, os_version, device_price, device_age

Demographics: gender, age

Geospatial & Behavioral: home_country, home_geohash, work_geohash, geo_behaviour, travelled_countries

Affluence & Commerce: affluence, brands_visited, place_categories

Interests: interests

Anonymous id
id_type
gender
age
carrier
make
model
os
os_version
home_country
home_geohash
work_geohash
device_price
device_age
affluence
brands_visited
place_categories
geo_behaviour
interests
travelled_countries

Consumer Behavior & Trend Prediction — Apply behavioral signals from geo_behaviour, interests, and place_categories to train models that detect behavioral changes, assess patterns, and forecast business outcomes.

Data Enrichment & Customer 360 — Leverage online-to-offline consumer profiles across demographics, device, and location attributes to build holistic audience segments for enriched ML model inputs.

Audience Modeling & Segmentation — Construct high-resolution consumer segments using affluence, brands_visited, interests, and travelled_countries to support interest and intent-based targeting models.

Sales Forecasting — Analyze consumer behavior signals across device, location, and interest fields to train propensity and sales prediction models and monitor investment performance.

Retail Footfall & Persona Modeling — Use home_geohash, work_geohash, and place_categories to model footfall trends, customer personas, and physical visit patterns for retail analytics applications.

Feature Engineering for Recommendation Systems — Combine interests, brands_visited, and place_categories fields to build user-level feature vectors for collaborative filtering and content-based recommendation models.

Identity Graph Construction — Link Anonymous_id, id_type, carrier, and device fields across consumer records to support cross-device entity resolution and unified identity graph development.

Record volume: 900 million records

Capture frequency: Once per event

Delivery frequency: Once per month

Update cadence: Monthly; export intervals available at daily, weekly, monthly, or quarterly depending on use case requirements

Data reach attributes: User demographics, MAID, device details, location, affluence, interests, and traveled countries

Collection methodology: Dynamic ingestion; each export reflects the most current validated data

Dataset documentation: https://docs.factori.ai/docs/consumer-data-1?utm_source=direct&utm_medium=referral&utm_campaign=opendatabay

Talk to an expert: https://www.factori.ai/talk-to-expert/?utm_source=direct&utm_medium=referral&utm_campaign=opendatabay