FICO, a predictive analytics and decision management software company, yesterday released FICO Model Builder for Big Data, the latest release of its analytics tool.
Model Builder for Big Data enables data scientists to discover, design, and deploy predictive analytics models that find signals in unstructured and massive data sets and turn those signals into actionable insights.
Model Builder for Big Data brings machine learning and statistical data mining to big data. Its text mining capabilities, unique Semantic Scorecard formulation, and embedded Lucene and Tika indexing and extraction libraries mine text from a wide variety of document types and boost the predictive strength of its scoring formulas. Model Builder for Big Data also integrates Apache Hadoop, the open-source framework for distributed computing and storage, and works with Cloudera's Hadoop distribution. It also supports R language for statistical computing and graphics.
"Modeling massive data sets can be challenging, because most traditional data analysis tools have been built for the 'small data' world, with highly structured, mostly numerical data," said Stuart Wells, chief technology officer at FICO, in a statement. "Today, data volumes are orders of magnitude larger, they defy a simple 'rows and columns' structure, and they're mostly made up of messy, unstructured information like text, voice and even video. We have built Model Builder for Big Data to cope with this kind of unwieldy raw information and make it into something meaningful and valuable."
FICO Model Builder for Big Data is part of the FICO Decision Management Platform, and is available on-premise and is expected to be available via the FICO Analytic Cloud.