The goal of the challenge is to visually map out, according to various data sets, where BrainBox AI’s solution can have the greatest impact on reducing CO2 emissions.
BrainBox AI is a fully autonomous artificial intelligence-driven HVAC solution designed to optimize energy consumption, resulting in impactful carbon footprint reductions (20-40%). Since launching in May 2019, the company has experienced rapid global adoption with over 100 million square feet in installed and committed real estate space. Our goal is to continue to expand that adoption to have the greatest positive impact on climate change. With this in mind, BrainBox AI would like to identify the areas in North America where it would have the greatest influence and we want you to be a part of it. How? The challenge we put forth to you is one that involves data mining and data visualization with the possibility to experiment with machine learning.
You will be provided with access to relevant data that you can use for the deliverable. This will include grid cleanliness, population densities in cities, and other relevant data. Teams will also be provided with the types of buildings that fit our solution and the necessary information about our solution.
We ask you to think of our challenge as a combination of data visualization and a competition to include the most useful (and pertinent) data within that visualization. We encourage participants to go beyond the data we provide and leverage the resources they have at their personal disposal. The deliverable should be presented through data visualization in the form of a map. Provided with an evaluation grid, teams will have the liberty to choose how they layer these maps, the amount of data and what data they represent, as well as any additions to the deliverable they see fit. In this data visualization we are looking for explanations for your choices, an estimation of the amount of CO2 emission reduction possible with our solution in the next 5-10 years, and possibly an adaptable platform (through machine learning) to keep these predictions accurate as time transpires.