BuildFax started in 2008 by aggregating dispersed building permit data from across the United States and providing it to other businesses, such as insurance companies, building inspectors, and economic analysts. Today it provides solutions tailored to those professions along with a variety of services, including indices that track trends like housing remodels and new commercial construction. The company is based in Asheville, N.C.
- BuildFax’s core customer base is insurance companies, which spend billions of dollars annually on roof losses. The company provides estimates on the age and condition of roofs to help its customers establish policies and premiums.
- BuildFax initially built predictive models based on ZIP codes and other general data using Python and R languages, but building the models was complex and the results did not provide enough differentiators to boost the business.
- BuildFax needed a solution that was easier to use and would support faster, more accurate modeling for property-specific estimates.
- Turned to Amazon Machine Learning for predictive modeling.
- Uses Amazon Machine Learning to provide
roof-age and job-cost estimations for insurers and builders, with property-specific values that don’t need to rely on broad, ZIP code-level estimates. - Uses data sets from public sources and from customers to build models.
The image above shows the machine-learning process used by BuildFax. It feeds known roof age and property characteristic data of buildings into Amazon Machine Learning to train machine-learning models that predict roof age. Amazon ML’s real-time prediction engine then takes in property characteristics for buildings for which roof age is not known and makes roof-age predictions based on the models. BuildFax provides these age predictions to its customers through the BuildFax API. These predictions inform their customers’ insurance policies and other decision making processes.
- The best practices and ease of use built into Amazon Machine Learning dramatically streamline the process of building predictive models.
- Models that previously took six months or longer to create are now complete in four weeks or less.
- BuildFax can provide customers with easy, programmatic access to predictions through APIs.
- Creates opportunities for new data analytics services that BuildFax can offer to customers, such as text analysis in Amazon ML to estimate job costs with 80 percent accuracy.
Learn more about performing predictive analytics with Amazon Machine Learning.