3. The Dataset
• 4 million activities collected during three
months (February-April)
• An activity is defined by steps taken, class
(running or walking), duration and location
• The Quantis Cloud service also maintains
information about friendships, awards and
weight measurements
5. 51% female users vs. 22% male users (not all users entered their gender)
6. 0
5
10
15
20
25
30
35
Age 0-9 Age 10-19 Age 20-29 Age 30-39 Age 40-49 Age 50-59 Age 60-69 Age 70-79 Age 80-89
Percentage
Age distribution of users included in dataset
8. 0
5
10
15
20
25
30
35
40
45
BMI 10-14 BMI 15-19 BMI 20-24 BMI 25-29 BMI 30-34 BMI 35-39 BMI 40-44
Percentage
46,7% of the Danish population have BMI>25 (54,2% male and 39,4% female)
9. Clustering of all users vs. loyal users by average daily steps taken
0
5
10
15
20
25
30
35
40
45
<2000 <4000 <6000 <8000 <10000 <12000 <14000 >14000
All Users Loyal Users
18. Observations
• Using a mobile for self-tracking has some
inherent problems
• Award system progression could be
improved
• Weather and especially sunshine affects
users activity level
19. Future Ideas
• Impact of high score rankings and friends
on steps taken
• Long term variations such as seasonal
changes
• Detecting when users are about to loose
motivation