Participants will work with time series data from pedestrian counters installed on three streets in Wuerzburg, a historic city known for its lively urban environment. The data includes hourly foot traffic counts, with records dating back to 2019 for the street Schoenbornstrasse (green). Data for the other two streets, Kaiserstrasse (red) and Spiegelstrasse (blue), dates back until September 2022.

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F22956516%2F7890696c3523178e2a61abf3630827ba%2Ftest.png?generation=1737533777094545&alt=media)

The goal of this competition is to develop models that accurately predict the total hourly pedestrian numbers for the next week, as well as how many pedestrians per hour are traveling towards the city center and how many are leaving the city center. Accordingly, three different variables need to be predicted: `n_pedestrians`, `n_pedestrians_towards`, `n_pedestrians_away`

Predictions about the number of pedestrians entering and leaving the city center allow us to model the flow of pedestrians within the city center.

The challenge lies in managing the differences in data length per street and identifying relevant patterns such as seasonal variations, trends, and special events that might influence foot traffic. An additional difficulty is the influence of the coronavirus pandemic. Understanding these factors can help stakeholders such as city planners and businesses optimize their operations, improve resource allocation, and enhance public services.

Participants are encouraged to leverage external data sources—such as local event schedules, or public holidays—that may influence foot traffic. Incorporating these sources could significantly improve forecasting accuracy and provide a competitive edge. However, if external data sources are used as additional feature information, it must be ensured that all data was available before the first date of the test dataset. 

The location of the counters on the three streets is given as a JSON-file. On the [open-data-platform of the city of Wuerzburg](https://opendata.wuerzburg.de/explore/dataset/pedestrians_counter_geojson/map/?location=16,49.79659,9.93497&basemap=jawg.streets), you can find a map with the exact area that is being tracked in each of the three streets.