**2026 Update! The competition results have been [open-access published here](https://iopscience.iop.org/article/10.1088/1742-6596/3140/11/112017)! (See also citations section below)**

Urban areas face the growing challenge of noise and heat, which affect our comfort, health, and productivity. Effective management of these factors is crucial as they influence the productivity, satisfaction, and stress levels of people in indoor and outdoor environments.

Knowing and predicting locations with comfortable thermal and acoustic conditions empowers people to find refuge from heat and noise. This knowledge could provide relief from the negative impacts, making the city appear cooler and quieter while still accounting for personal comfort preferences. 

Hence, this competition's goal is to use contextual data to predict noise distraction and thermal preference across a diversity of indoor and outdoor spaces.

This competition includes the city-scale collection of 9,808 smartwatch-driven micro-survey responses that were collected alongside 2,659,764 physiological and environmental measurements from 98 people using the open-source Cozie-Apple platform ([website](https://cozie-apple.app/), [paper](https://arxiv.org/abs/2210.13977)) combined with geolocation-driven urban digital twin metrics from the [Urbanity Python package](https://urbanity.readthedocs.io/en/latest/index.html). Figure 1 shows some of these data spatially distributed across Singapore.

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F8649844%2Fc5df74fe67c96c97027cf5bf63235ff7%2Fcozie-map.png?generation=1699943959047398&alt=media) Figure 1: Micro-survey response example: location context of participants in Singapore
An overview of the input data sources and prediction objectives are outlined in Figure 2. The winning solutions of this competition will provide evidence of the types of pre-processing, modeling, and ensembling methods that provide the most accurate solutions for this context.

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F23583%2F92cbf24951db70c16defd8737d758829%2Fpaper_cozie_3.png?generation=1696826167498337&alt=media) Figure 2: Overview of competition data and structure
## If you have questions or comments, please leave a post on the [Discussion Board](https://www.kaggle.com/competitions/cool-quiet-city-competition/discussion)

The discussion board is also useful for sharing strategies, insights, baselines, etc., that can make the competition richer through sharing. We encourage teams to share exploratory data analysis and other notebooks that could help the community.