Segment Users of a Shared Mobility App
A shared e-scooter and e-moped app has 900,000 users in 6 cities. Marketing sends the same promotions to everyone and product does not know who to design the new monthly pass for. Nobody has defined segments: they want to discover what types of user really exist based on how they use the service.
Where the money comes from
What to do now
- 1Calculate the margin per trip by zone and hour.
- 2Segment users and name each segment with the business.
- 3Launch the pass and promotions by segment with a control group.
For your committee
One page with the decision, the impact, the risks, the steps and the KPI to track.
The print dialog opens: choose "Save as PDF".
Watch out: more volume is not always more profit
An unlimited pass can trigger low-margin short trips and the cost of charging and repositioning. Design the pass with limits based on the cost per trip of each segment.
KPI for the committee
Margin per trip and per segment.
Detail for your data team
Proposed technique: K-Means Clustering
Why: There is no label to predict: the goal is to discover structure. K-Means groups users with similar behaviour at scale, and the centroids are easy to interpret ('the average user in this group makes 9 short trips at rush hour').
Cost of getting it wrong: Segments without differentiated action add nothing; too many segments are impossible for marketing to manage.
Data needed: Trips: time, day, duration, distance, origin and destination (zones).; Payments: type of pass, monthly spend, use of promotions.; App: opening frequency, cancelled bookings, ratings.