The data collection process for this competition utilized the open-source [Cozie Apple platform](https://cozie-apple.app/). This mobile and smartwatch application for iOS devices allows people to complete a watch-based micro-survey and provide real-time feedback about environmental conditions via their Apple Watch. It leverages the built-in sensors of the smartwatch to collect physiological (e.g., heart rate, activity), environmental (sound level), and location (latitude and longitude) data. The dataset from this deployment includes micro-survey responses from 98 people, who each provided at least 100 micro-survey responses from October 2022 to August 2023. The micro-survey question flow is seen in Figure 3. For each survey response location, digital-twin-created spatial indicators were calculated using the [Urbanity python package](https://github.com/winstonyym/urbanity). In addition, publicly available weather data is also provided.

The goal of the competition is to predict the values of the columns `q_noise_nearby`, `q_noise_kind`, `q_earphones`, `q_thermal_preference `as well as possible.

## Micro-survey question flow
![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F8649844%2Fa2e63dc3ed89035e7e242230f94b9488%2Fwatch_survey_noise_and_privacy-36fcc4ca7094d37b0f0a79419cd93c4a.png?generation=1699286770839443&alt=media) Figure 3: Micro-survey question flow for this data set. Participants in the study were prompted to answer these questions in a diversity of indoor and outdoor environments over the course of 2-4 weeks. [Click here for a larger image.](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F8649844%2Fa2e63dc3ed89035e7e242230f94b9488%2Fwatch_survey_noise_and_privacy-36fcc4ca7094d37b0f0a79419cd93c4a.png?generation=1699286770839443&alt=media)