Smart Systems and Real-Time Decision Making
Smart societal systems, such as on-demand transportation, cloud platforms, the smart grid, and financial-processing networks, are revolutionizing all aspects of our economic and social lives. These systems face similar decision-making challenges due to uncertainty, complex state-spaces, combinatorial constraints, and strategic agent behavior.
Siddhartha Banerjee, School of Operations Research and Information Engineering, is developing a unified framework for real-time decision making for smart systems. Banerjee is building the framework around the use of data-driven prediction oracles and non-monetary market mechanisms. Such an approach leads to policies that are easy to interpret and implement in practice. Understanding their performance, however, requires new theoretical and methodological ideas.
Banerjee is developing rigorous frameworks for harnessing prediction oracles as inputs to real-time control policies and for designing non-monetary allocation policies, based on emulating monetary mechanism. An exemplar of the paradigm is the idea of simulation-as-a-service (SaaS), in which complex data-driven simulators are used as inputs for control policies and mechanisms.
Banerjee’s research is coupling advances in machine learning and mechanism design theory with the underlying philosophy of model-predictive control.