For months now, we were told to stay at home for our own safety, to travel as little as possible and to avoid social contact. In view of these new sensibilities, it is very likely that people, fearing close contacts and crowded places, will be wary of public transport and will increasingly use private transport. This will have repercussions on traffic, causing serious inconvenience to people, impact on the environment and accentuating social differences. Moreover, in a recovery phase, the crowded trams and busses during rush hour can become a favorable ground for the spread of the virus.

Our solution

Our idea is to create an application that allows everybody to find the best route to their destination with respect to two factors:

  • Time efficiency
  • Least Social Contact (= Lowest infection risk)

Our application will help you find the route which meets the above criteria best. The user can provide a time window in which he/she would like to arrive and the application will tell the optimal departure time and travel route. Of course, the user can modify his/her priorities if not all criteria can be met at once.

The calculations are based on historical and realtime public transport data, the google maps APIs for route finding and a machine learning algorithm that estimates the percentage of occupied vehicles on all transit modes at each intermediate step.

This mechanism brings several more advantages with it which are not all connected to Corona, such as

  • Enabling an earlier transition from private transport back to public transport
  • Redistributing passengers from peak hours to a larger time window, relieving public transport during rush hour.
  • Raising awareness for ecological efficiency

This platform especially targets public transport users who have a smart phone and have flexible arrival time (such as students, people who can work from home...), we believe that this segment of the population will grow, because many people got used to the smart working. However, since it also gives the route with "least social contacts" for a given time (i.e. time flexibility = 0), it is in principle to any public transport users who have a smart phone. Disposing of the necessary data, this project is easily scalable.

How is it different

Our idea differs from existing mobility platforms in three ways

  1. The optimisation according to "least social contacts". In fact, many mobility platforms nowadays, warn you of the occupancy rate (usually from a scale 1 to 4, not very accurate) but do not actively suggest the emptiest routes.
  2. The time span. Mobility platforms nowadays only optimise the route, not the departure nor arrival time.
  3. Integration in different platforms. We are not thinking of a stand alone app but of a wide label. By combining, existing and widespread technologies we want to offer an original solution in a short time.


We build a working python Prototype with 3 Stages: the SlackBot, the Route-Planner and the Prediction-Model. The program runs on a rented Amazon AWS server and is currently functional for routes in Zurich.

  • SlackBot: With the help of the Slack API we build a ChatBot with whom one can interact via Slack (picture). The Bot asks the user questions like: From, To,Time and Time flexibilty. It then waits for the calculations of the other parts to finish and returns the best (least infectious) route to the user.

  • Route-Planner: With the Google Maps Direction API and we calculate several possible fast routes during the specified time span.

  • Prediction-Model: This part then predicts for every route the occupancies of the vehicles via machine learning. To train the model we used accessible ZVV Zurich passenger data.

User survey

This week end we identified the user needs with a study of 160 participants. It turned out that 60% of them are afraid to use public transport right now because of how crowded it might be. 70% said they would trade off travel time for less crowds. Interestingly, 75% of the participants in the survey are less than 25 years old, hence are not in the most endangered layer of the population. The results of this survey validates our assumption, that there is an urgent need for a tool that allows people to social distance themselves on public transport.

What we have done during the weekend

  • Prototype code refactoring, developing and testing
  • Slack Bot interactions with Google Maps links for better visualitazion (picture)
  • Working out Business Model and targeted user groups
  • Surveys for identifying problems and need in public transport during corona times (picture)

What's next for "HealthyWays"

  • We need to validate different ways to gather live data, for example through user feedback and though a partnership with transport companies. We are already in contact with the public transport company of Zurich VBZ, which show interest in the HealthyWays platform.
  • We need to make a more accurate user study with a bigger pool of participants
  • integrate additional services such as reminders on recommended routes, ability to save routes and locations
  • integration in different platforms like calender, etc ..
Share this project: