We study merchant energy production modeled as a compound switching and timing option. The resulting Markov decision process is intractable. Least squares Monte Carlo combined with information relaxation and duality is a state-of-the-art reinforcement learning methodology to obtain operating...

Least squares Monte Carlo (LSM) is an approximate dynamic programming (ADP) technique commonly used for the valuation of high dimensional financial and real options, but has broader applicability. It is known that the regress-later version of this method is an approximate linear programming...

Merchant energy trading companies manage conversion assets to exploit price differences across time, space, and sources of energy in the face of energy futures term structure risk. Financial hedging of this risk is standard practice. Market incompleteness, such as limited futures liquidity,...

We develop two parsimonious models for pricing multi-name credit derivatives. We derive closed form expression for the loss distribution, which then can be used in determining the prices of tranche and index swaps and more exotic derivatives on these contracts. Our starting point is the model of...

Energy demand response is projected to be critically important in decarbonizing the grids of the future. We propose an agent to communicate ``artificial" price signals (i.e., prices for each hour) to workers as part of an office building demand response program, where workers react to this price...

Approximate linear programs (ALPs) are well-known models based on value function approximations (VFAs) to obtain policies and lower bounds on the optimal policy cost of discounted-cost Markov decision processes (MDPs). Formulating an ALP requires (i) basis functions, the linear combination of...

Prominent hotel chains quote a booking price for a particular type of rooms on each day and dynamically update these prices over time. We present a novel Markov decision process (MDP) formulation that determines the optimal booking price for a single type of rooms under this strategy, while...

Commodity and energy production assets are managed as real options on market uncertainties. Social impacts of plant shutdowns incentivize balancing asset value with shutdown probability. We propose new shutdown-averse policies based on the popular dynamic conditional value-at-risk (CVaR). We...

Stochastic convex optimization problems with expectation constraints (SOECs) are encountered in statistics and machine learning, business, and engineering. In data-rich environments, the SOEC objective and constraints contain expectations defined with respect to large datasets. Therefore,...

Prominent companies have committed to procuring a percentage of their power demand from renewable sources by a future date. Long-term financial contracts with renewable generators, known as corporate power purchase agreements (CPPAs), are popular to meet such a renewable power purchase target...