![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F23583%2F92cbf24951db70c16defd8737d758829%2Fpaper_cozie_3.png?generation=1696826167498337&alt=media)

The data collection process for this competition utilizes 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 deployment for this work includes watch survey responses from 106 people, who each provided at least 100 micro-survey responses from October 2022 to August 2023. For each survey response location, digital-twin-created spatial indicators were calculated using the [Urbanity python package](https://github.com/winstonyym/urbanity).

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.