New Member: Tangent Works

Tangent Works was founded in 2014 by a team of data scientists and mathematicians who believed in the power of predictive modeling for optimizing operations and reducing costs, but found that the existing methods were far too complex for broad adoption.

Building and refining accurate predictive models was a laborious, iterative task that required a combination of domain and data science expertise and weeks/months of effort. There just aren’t enough data scientists in the world to meet the demands of a broad range of industries for which accurate and timely forecasts are essential to their competitiveness.

The founders’ original concept was simple- what if we could build the model automatically by analyzing historical time-series data, including all the possible influencers, and figure out which data is relevant to the predicted output, in what combinations, over which time intervals. From that vision and a breakthrough architecture based on a field of mathematics known as “information geometry”, the Tangent Information Modeler, TIM, was born.

TIM has since been recognized as a winner in multiple competitions, including the Global Energy Forecasting Competition, GEFCom 2017, and the 2017 ANDRITZ Hackathon, which was focused on optimization and predictive maintenance for IoT applications.

The Mission of Tangent Works

TIM’s mission is to de-mystify predictive modeling and anomaly detection and make them accessible and productive for a broad range of users and use cases.

TIM’s initial focus has been on the energy and utilities industry where the software has been used extensively to forecast energy supply and demand
and help companies reduce imbalance costs. More recently TIM has been applied to manufacturing for anomaly detection and predictive maintenance.
Moving forward, TIM will be extended to many other industries, including traffic management, logistics, agriculture, retail, finance and others since its
underlying technology can benefit any application with time series data.