Big Data and Predictive Analytics

KBR’s innovative digital technology helps customers tackle mission challenges by identifying ways to reduce capital expenditures, optimize operations, process large datasets, and improve reliability and safety.

KBR creates and uses state-of-the-art machine-learning algorithms to process massive amounts of data, at scale, in order to provide timely intelligence exploitation and analysis to end-users across the globe. Using predictive analytics, artificial intelligence (AI) and cognitive computing, KBR helps clients use their data as an asset for projects, operations and maintenance in order to better achieve business objectives.

“KBR creates and uses state-of-the-art machine-learning algorithms to process massive amounts of data, at scale, in order to provide timely intelligence exploitation and analysis to end-users across the globe.”

KBR’s integration of artificial intelligence into all phases of the Tasking, Collection, Processing, Exploitation, and Dissemination (TCPED) cycle provides new insights from previously intractable datasets as well as rapid visualization of those insights and deployment to the customer. Our cognitive computing methods unlock the potential in  data, making it work together to mitigate project risks, enhance productivity, improve efficiency and support decision-making. With predictive analytics, KBR can make probabilistic predictions about operations, maintenance and project performance by bringing together statistical analysis, predictive modeling, data mining, text analytics, entity analytics, optimization and real-time scoring. When predictive analytics works with machine learning, it becomes a more powerful, dynamic modeling tool that learns from experience and adjusts itself to predict the next best action.

KBR uses mass amounts of data from AI and machine learning to solve diverse problems in earth science, aerospace, and transportation. Examples include the use of neural networks to accelerate the processing of satellite imaging to support rapid response to flooding events; time-series forecasting models of radar sensors in space surveillance networks to detect anomalies and predict future performance; and deep learning techniques to detect pedestrians/bicyclists in front of moving vehicles with real vision data from cameras mounted on car windshields.