Yellow Submarine reveals Heimdall for Fire Risk Prediction

June 19, 2019

Using our unsupervised machine learning models we take smart data from oodles of big data. Additionally since our algorithms are all open box there is no discrimination or bias. Our Fire Risk models have been built on pure time series information and give highly accurate results on unseen data. Not only can our fire risk modelling software be used by the fire brigade it can also be used by the ambulance service to ensure resources are deployed to areas where fires that will result in medical attention being needed. Our platform is very simple to use, simple upload a CSV file and a model will then be built. New inferences are calculated when a new data instance is presented to the already built model, and a propensity is returned through the API. Weightings for each part of the model can easily be understood through either the API or our Magic Donut visualisation.

Predictive Crime product launched
New product release - Heimdall