Current Projects – Cycle Two

Project Charter: Big Data Analysis for Plant and Commercial Optimization
Principal Investigator: Prof. Cynthia Rudin, MIT
Research Stream: Big Data
Objectives/Purpose of Study:

    In Renewables, there exists an enormous amount of real-time data related to plants operations, weather conditions and electricity markets that can be integrated and leveraged to better:
  • Predict the performance and risks of the Renewables fleet, preventing faults and performance losses
  • Predict power supply vs. demand
  • Optimize the decision policies to maximize overall global quality (including cost) of the combined network of renewable energy plants
    Our goal is to create a foundation for solving this challenging and important problem and test our methods on data from the Partner Company.


Project Charter: Learning and Optimization in Revenue Management
Principal Investigator: Prof. David Simchi-Levi, MIT
Research Stream: Big Data
Objectives/Purpose of Study:

    The study will seek to develop Big Data-ready techniques capable of optimizing business decisions at a product and/or customer level. Techniques will also be developed in order to optimize a set of decisions to maximize business objectives under multiple constraints. A key factor in this problem setting is the exploration-exploitation tradeoff, a time tradeoff between gathering more information to learn about unknown customer demand and then optimizing the price to maximize revenue given what was learned about demand.


Project Charter: Reducing False Positives in Fraud Prevention and Detection
Principal Investigator: Prof. John Williams, MIT
Research Stream: Big Data
Objectives/Purpose of Study:

    To reduce the number of false positives in present fraud detection systems this project will focus on developing robust analytical techniques with tunable filters capable of focusing on high probability fraudulent events. We will develop visualization tools that give a more holistic understanding of fraud and fraud patterns and can be used to anticipate fraudulent exploits rather than to react to them. Present fraud detection systems use rule-based techniques. While these can reduce an organization’s attack surface, more sophisticated and computationally intelligent approaches are necessary to avoid the false positive dilemma. Aggregate behavior models, which identify hidden relationships between people, organizations, and events will be employed.
    This project will develop 1) advanced analytical techniques to reduce the number of false positives, while preserving high probability fraud events, 2) visualization techniques that provide human operators a holistic view of fraud patterns to further improve the algorithms e.g. by using aggregate behavior models.


Project Charter: Improving the Performance of Unconventional Drilling
Principal Investigator: Prof. Robert Armstrong, MIT
Research Stream: Big Data
Objectives/Purpose of Study:

  • To develop data sets, algorithms, visualisation techniques that pull together the disparate data sources from the rig, the equipment, the material movements and the operating and risk parameters in a way that support more effective decision making during the execution of the drilling program
  • This research would include the concept of remote drilling operations centres and how the value of these centres can be maximised as well as how to make the most of the new rig technology and the accompany sensors/volumes of data
  • We would also consider the increased requirement for collecting and reporting environmental data- noise, emissions, waste- and improving the environmental footprint