This article describes the specific procedures and techniques used to identify, process, and analyze data within Cohort Insights.
Cohort Insights compares buildings based on how efficient they are. There are numerous ways of comparing buildings against each other. At Measurabl, we have developed a proprietary efficiency metric based on each building’s consumption compared to a baseline consumption. This baseline is generated using machine learning models trained on Measurabl’s database of real estate utility data covering more than 10B square feet. It represents the expectation of how much energy or water a building of certain use type and size, in a certain weather zone, should consume at a certain time of the year, and how much carbon it should produce.
How we calculate the expected usage:
- Measurabl’s database includes time series usage records for tens of thousands of buildings across more than 100 primary use types. Because we have so much utility data, we are able to accurately predict what a building should consume based on all of the buildings in our database (across multiple owners, operators, locations, etc.).
- Expected usages for these buildings are calculated through machine learning models. These are models trained to recognize patterns, like patterns in utility consumption. The patterns in our data emerge across different building types, sizes, and climate zones.
- The output of these machine learning models is the expected usage for a building which we compare to its actual, tracked utility consumption. The ratio of these two metrics is how we determine the efficiency of a building, and this is ultimately how we rank buildings against one another.
The ‘Efficiency Percentile’:
The end result of this analysis (actual vs expected, comparing buildings based on efficiency) is represented by a single number - the Measurabl Efficiency Percentile.
- The Efficiency Percentile is normalized for all of the data points we use in our estimated usage calculation - property use type, weather, who pays the bills, the month and the year - which goes far beyond traditional usage intensity comparisons (i.e. EUI).
- Depending on what characteristics you choose for your cohort, your ranking will change, and in turn, it will change your Efficiency Percentile.
Key Takeaways:
- Cohort Insights benchmarks buildings based on how efficient they are.
- Measurabl has their own, proprietary efficiency calculation: we look at a buildings’ property use type, weather, who pays the bills, the month and the year and come up with what we think that building should consume based on 10B+ SqFt of building utility data, and compare it to what it’s actually consuming.
- The Efficiency Percentile you receive will change based on who you compare yourself to (i.e. how you filter your cohort).
- The Measurabl Efficiency Percentile is something you cannot find anywhere else - it’s calculation is proprietary to Measurabl and is built upon one of the largest, freshest datasets in the market today.
Please review this guide on how to navigate the Cohort Insights.
For FAQs & Additional Information on Cohort Insights, refer to this article.
For a deeper dive and a more technical version of our Cohort Insights methodology, please contact your Customer Success Manager. Any other questions? Please reach out to our Support Team!