Panel Title

Mid-morning Break and Poster Sessions

Location

The Mirage Hotel & Casino, Las Vegas, Nevada

Start Date

8-6-2016 10:00 AM

End Date

8-6-2016 10:30 AM

Abstract

Modeling and optimizing the performance of a mix of slot machines on a gaming floor can be addressed at various levels of coarseness, and may or may not consider time-dependent trends. For example, a model might consider only time-averaged, aggregate data for all machines of a given type; time-dependent aggregate data; time-averaged data for individual machines; or fully time dependent data for individual machines. Fine-grained, time-dependent data for individual machines offers the most potential for detailed analysis and improvements to the casino floor performance, but also suffers the greatest amount of statistical noise. We present a theoretical analysis of single and multi-objective optimization methods that address the casino floor optimization problem at all levels of coarseness, considering both linear and non-linear formulations of the problem. We also address the impact of statistical noise and time-dependent trends on solutions, using both Gaussian and non-Gaussian distributions to model the performance of individual machines. We show that advanced methods from evolutionary computing can track trends in performance and continually adjust the optimal mix of machines, potentially allowing an operator to respond rapidly to customer preferences, and allowing a property to operate continuously near the optimal mix.

Keywords

multi-objective optimization; casino floor optimization; non-linear data modeling; evolutionary computing

Disciplines

Artificial Intelligence and Robotics | Gaming and Casino Operations Management | Hospitality Administration and Management | Numerical Analysis and Computation | Numerical Analysis and Scientific Computing | Other Applied Mathematics | Statistics and Probability | Theory and Algorithms

Comments

Attached: PDF containing one slide

 
Jun 8th, 10:00 AM Jun 8th, 10:30 AM

Stationary and Time-Dependent Optimization of the Casino Floor Slot Machine Mix

The Mirage Hotel & Casino, Las Vegas, Nevada

Modeling and optimizing the performance of a mix of slot machines on a gaming floor can be addressed at various levels of coarseness, and may or may not consider time-dependent trends. For example, a model might consider only time-averaged, aggregate data for all machines of a given type; time-dependent aggregate data; time-averaged data for individual machines; or fully time dependent data for individual machines. Fine-grained, time-dependent data for individual machines offers the most potential for detailed analysis and improvements to the casino floor performance, but also suffers the greatest amount of statistical noise. We present a theoretical analysis of single and multi-objective optimization methods that address the casino floor optimization problem at all levels of coarseness, considering both linear and non-linear formulations of the problem. We also address the impact of statistical noise and time-dependent trends on solutions, using both Gaussian and non-Gaussian distributions to model the performance of individual machines. We show that advanced methods from evolutionary computing can track trends in performance and continually adjust the optimal mix of machines, potentially allowing an operator to respond rapidly to customer preferences, and allowing a property to operate continuously near the optimal mix.