Many habits. One living network.

The Health Habit Hub helps people build healthier habits, and helps researchers understand how that actually happens. Both live in one place: an app for taking part, and a portal for running the study.

I want to take partI do research
  • Available on iOS & Android
  • Data stays in Europe, under GDPR
  • Open and transparent
A living knowledge graph

Each shared habit becomes a node in a growing knowledge graph. As contributions accumulate, habits link through shared concepts, self-organizing into clusters that reveal how real habits connect.

Drag a point to move it.

Illustrative rendering of the graph.

The idea behind it

One platform, two points of view.

Most health apps collect data that no one ever learns from. And most behaviour research never reaches a real app. The Health Habit Hub connects the two. Participants get a simple tool to track their habits. Researchers get cleanly collected, anonymised data to understand what genuinely helps. Each side makes the other better.12

For participants

a calm, everyday tool instead of yet another noisy app.

→

For researchers

real behaviour from daily life, not just from the lab.

→
The shared body of knowledge

Many habits become one network.

Participants can share their habits anonymously. Bit by bit that builds a graph of thousands of real behaviours, where related habits move closer together. For researchers it is a map of human behaviour. For participants it is a place to see that they are not alone.3

This is how many individual contributions become a learning system.

Share
Knowledge graph
Recommender
Recommendation
1

Share

In the app, participants decide for themselves which habit to share anonymously.

2

Knowledge graph

Each contribution links up with related habits, growing a shared network.

3

Recommender

A model learns from the real, aggregated behaviour of thousands of people, not assumptions.45

4

Recommendation

Participants get suggestions grounded in real patterns, and the loop begins again.

How the data is collected: in the app, participants choose for themselves whether to release a habit anonymously for research. Released entries are separated from personal details, grouped by theme, and stored only as an aggregate graph. That makes it much harder to trace entries back to individuals, who can often be re-identified from detailed data even without a name.67

Where do you start?

Are you here to take part, or to do research?

Both paths start here. What waits behind each is made for you.

You want to manage your habits

For participants

Get the app, track your habits and stay in control of your data. Along the way you contribute to research, entirely by choice.

Go to take part →
You plan or run a study

For researchers

Design studies, guide cohorts and analyse data in a privacy-compliant way, without ever touching a database by hand.

Go to research →

Sources

  1. 1Reinsch, F., Sitzberger, M. L., Kählig, M., & Stark, J. (2026). Built for sprints, needed for marathons: Mapping the gap between science, users, and implementation in digital habit formation apps. In ECIS 2026 Proceedings. Association for Information Systems. https://aisel.aisnet.org/ecis2026/hit/hit/14
  2. 2Middelweerd, A., Mollee, J. S., van der Wal, C. N., Brug, J., & te Velde, S. J. (2014). Apps to promote physical activity among adults: A review and content analysis. International Journal of Behavioral Nutrition and Physical Activity, 11(1), Article 97. https://doi.org/10.1186/s12966-014-0097-9
  3. 3Noble, N., Paul, C., Turon, H., & Oldmeadow, C. (2015). Which modifiable health risk behaviours are related? A systematic review of the clustering of smoking, nutrition, alcohol and physical activity (‘SNAP’) health risk factors. Preventive Medicine, 81, 16–41. https://doi.org/10.1016/j.ypmed.2015.07.003
  4. 4Reinsch, F., Weimann, T., & Stark, J. (2024). Tailoring health: Contextual variables in health recommender systems. In Proceedings of the 6th International Workshop on Health Recommender Systems (HealthRecSys 2024) (CEUR Workshop Proceedings, Vol. 3823, pp. 2–15). CEUR-WS.org. https://ceur-ws.org/Vol-3823/1_Reinsch_tailoring_159.pdf
  5. 5De Croon, R., Van Houdt, L., Htun, N. N., Štiglic, G., Vanden Abeele, V., & Verbert, K. (2021). Health recommender systems: Systematic review. Journal of Medical Internet Research, 23(6), Article e18035. https://doi.org/10.2196/18035
  6. 6Rocher, L., Hendrickx, J. M., & de Montjoye, Y.-A. (2019). Estimating the success of re-identifications in incomplete datasets using generative models. Nature Communications, 10(1), Article 3069. https://doi.org/10.1038/s41467-019-10933-3
  7. 7Sweeney, L. (2002). k-Anonymity: A model for protecting privacy. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 10(5), 557–570. https://doi.org/10.1142/S0218488502001648