Lifestyle Insights
Learn real-world behaviors, habits, and lifestyles to power hyper-personalized experiences.
This feature is currently in Early Access and is still under active development
Introduction to Lifestyle Insights



With Lifestyle insights you will gain a deeper understanding of your users by identifying the places they frequently visit such as home, work, and favorite venue types. These insights reveal daily routines, habits, and preferences.
We also provide Semantic Time, which categorizes activities based on a user’s personal timeline (e.g., morning, afternoon, evening). This helps you understand not just where users go, but when and how they structure their day.
Together, these insights enable personalized and relevant user engagement. The insights can be grouped in the topics below
Features Overview
Lifestyle Profiling
Lifestyle Profiling segments users into different lifestyle profiles. Segments are actionable labels assigned to users based on long-term behavioral patterns.
They describe lifestyle characteristics such as:
Commuting behavior
Geographic living area
Driving style
Social activity level
These segments help you tailor experiences and build more relevant and better user experience. The segments can be divided into these sub-categories:
Profiles
Profiles are a special type of Segment that apply to every user. Unlike regular segments (which a user may or may not belong to), every user always has a Profile. Each Profile has a level that indicates the degree to which it applies to that user:
LIMITED
MODERATE
HIGH
Physical Activity
evaluates how much the user is involved in physical activities
Mobility
evaluates how much the user is on the move
Social Activity
evaluates how much the user is involved in social engagement
Leisure
Bar goer
enjoys evenings out at a pub or bar
Fresh food enthousiast
shops for food often
Healthy biker
frequently bikes for long distances
Healthy walker
frequently walks for long distances
Nature lover
likes to go out to a park, public garden, zoo or nature reserve
Resto lover
likes eating out
Shopaholic
shops a lot
Sportive
sports regularly
Mobility
Die hard driver
uses the car for almost every trip
Easy commuter
has an easy commute to/from work
Frequent flyer
frequently flies
Green commuter
mostly sticks to walking and biking for commutes
Heavy commuter
has a heavy commute to/from work
Long commuter
lives far from their work location
Normal commuter
has an average commute time and distance
Public transports user
often travels with public transports
Public transports commuter
often commutes with public transports
Short commuter
lives close to their work location
Work life
Early bird
whose first morning activity is earlier than average
Fulltime worker
works full-time
Home bound
does not leave the house very often or travels very far
Homebody
prefers to stay at home on weekends and outside business hours
Homeworker
works from home or who is unemployed
Late worker
works until late
Night owl
whose last evening activity is later than average
Nightworker
works at night
Parttime worker
works part-time
Sleep deprived
sleeps very little
Student or teacher
a student or teacher
Uber parent
a parent who drives his/her kids to school, kindergarten or day care
Work life balancce
has a good balance between work and home life
Work traveller
works a lot remotely (travelling or in remote environments)
Workaholic
works more than average
Venue Type Detection
Detects the type of place that the user has visited (e.g., drinks, sports, education, shopping) based on location context, time of day and users mobility behavior. Below is a list of the venue types that can be detected.
Venues
UNKNOWN
Unknown venue
DRINK_DAY
Cafes, coffee bars, tea rooms, etc
DRINK_EVENING
Bars, pubs and in general places where one goes for drinks in evenings.
EDUCATION_INDEPENDENT
Educational institutions visited by the user on his own for their own studies. High schools, universities, colleges, etc.
EDUCATION_PARENTS
Schools and kindergartens visited by parents.
HEALTH
Hospitals, clinics, emergency rooms.
INDUSTRIAL
Buildings tagged as “industrial” on OSM, built for some manufacturing process.
LEISURE_BEACH
Beaches, resorts and swimming areas.
LEISURE_DAY
Bowling, billiards and other entertainment places.
LEISURE_EVENING
Cinemas, theatres and music halls.
LEISURE_MUSEUM
Museums
LEISURE_NATURE
Forests, lakes, national parks, etc.
LEISURE_PARK
City parks, gardens, zoos.
OFFICE
Office buildings. For example, of private lawyers, notaries or company representatives.
RELIGION
Churches, mosques and other religion related buildings.
RESIDENTIAL
Apartment blocks, houses.
RESTO_MID
Food courts, restaurants, snack bars.
RESTO_SHORT
Ice cream, fast food, donut stores.
SHOP_LONG
Supermarkets, malls, wholesales, shopping centres.
SHOP_SHORT
Small grocery stores, butchers, bakers.
SPORT
Gyms, sport centres. Venues visited to exercise.
SPORT_ATTEND
Stadiums. Venues visited to attend a sport event.
TRAVEL_BUS
Bus stops.
TRAVEL_CONFERENCE
Conference, convention, exhibition centres.
TRAVEL_FILL
Gas stations.
TRAVEL_HOTEL
travel_hotel- Hotels, motels, guest rooms, etc.
TRAVEL_LONG
Airports
TRAVEL_SHORT
Public transport stations, railway stations.
Home & Work Detection
Automatically identifies home and work locations based on the user’s behavioral patterns. These locations are typically detected during the first week of using Sentiance.
The detected location will seamlessly addapt when a user moves from the original home or changes jobs
This includdes the detection of when the user enters and exists these locations.
Physical Activity
Physical Activity segments users into activity levels based on detected behaviors such as walking, cycling, and gym visits.
Users are categorized into one of the following activity levels:
Low
Moderate
High
These levels represent the user’s overall physical activity based on their detected behavior patterns.
Privacy by Design
We do not expose exact locations. Instead, we provide venue types to preserve user privacy. This approach is often more accurate for example, confidently identifying that a user is at a bar without pinpointing which specific one.
Last updated