Factori US Mobility Data | AI & ML Location Intelligence | 1-Year Hist

Mobility and location data is gathered from location-aware mobile apps via SDK-based implementation, with all users explicitly consenting to location data sharing through a clear opt-in process and given opt-out options at any time. Factori ingests, cleans, validates, and exports all location signals to ensure only the highest quality data is available for analysis and model training. The dataset spans 90 billion+ records captured once per event, updated daily, making it suitable for time-series modeling, behavioral feature construction, and geospatial ML pipelines.

Device & Identity: maid, id_type, ipv4, ipv6, user_agent, carrier

Geospatial: latitude, longitude, horizontal_accuracy, geohash, hex8, hex9

Administrative Geography: country, state_hasc, city_hasc, postcode

Temporal: timestamp

maid
latitude
longitude
horizontal_accuracy
timestamp
id_type
ipv4
ipv6
user_agent
country
state_hasc
city_hasc
postcode
geohash
hex8
hex9
carrier

Geospatial Feature Engineering — Derive movement pattern features from latitude, longitude, geohash, and hex8/hex9 fields to enrich user-level ML models with spatial behavioral signals.

Consumer Behavior & Trend Prediction — Apply time-series analysis on timestamped mobility sequences to identify behavioral changes, movement trends, and predictive signals for business outcome modeling.

Market Intelligence & Competitive Landscape Modeling — Aggregate location pings across market areas and points of interest to study competitive proximity, catchment zones, and regional demand patterns.

Audience Modeling & Segmentation — Construct behavioral audience segments by analyzing mobility patterns across country, city_hasc, and postcode to support interest and intent-based targeting models.

**Retail Footfall & Proximity Analysis **— Use location pings and geohash clustering to model footfall trends, point-of-interest proximity, and physical visit frequency for retail analytics applications.

Fraud Detection & Identity Verification — Cross-reference maid, ipv4, ipv6, and user_agent against location consistency signals to train anomaly detection models flagging suspicious device or identity behavior. Identity Graph Construction — Link maid, ipv4, ipv6, and carrier fields across mobility events to support cross-device entity resolution and unified identity graph development.

Record volume: 90 billion+ records

Capture frequency: Once per event

Delivery frequency: Once per day

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

Data reach attributes: Country location, MAU, DAU, and Monthly Location Pings

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

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

Dataset documentation: https://docs.factori.ai/docs/mobility?utm_source=direct&utm_medium=referral&utm_campaign=opendatabay