Slot Floor Optimization


Part art, part science, slot floor optimization can help a casino understand the relationship between its machines and their profitability. Slot Floor Optimization helps managers determine the best mix of machines, the best prices on the machines, and the best utilization of the floor space to maximize returns. When it comes to slot floor planning, bad decisions will lower returns on deployed assets and can have a direct impact on the patron experience. Ensuring the right mix of games, at the right price, aligned to customer demands and preferences can help the casino generate incremental revenue, all the while improving the customer experience.

When deciding which games to offer or replace, casinos may look at historic results and surmise reasons why games which were popular in the past will continue to be so in the future. Advanced analytics can help casinos with slot floor planning to forecast the right mix of gaming choices, denominations, and machine placements to optimize customer interest and use.

When it comes to slots, casinos must ask the following questions:

  1. How much gross revenue will each game generate next year?
  2. How much will a new game generate?
  3. Which games need to be replaced?
  4. Which ones should be acquired?
  5. When should we purchase new games to replace poor performing existing games?
  6. What do we need to do to maximize gross wins, given business constraints such as space, budgets and timelines?

Optimizing the slot floor then becomes much more complex than replicating past and patron behavior with future slots that might be variations on a theme. Optimizing becomes much more complex than looking narrowly at daily win per unit (WPU), without regard for other factors that affect machine performance.

A unique combination of data profiling, statistical forecasting and optimization can improve slot floor performance from both a placement and replenishment standpoint. A multistep analytic process can use available data – machine attributes, transactions, player behaviors, business parameters, current state and more – to create optimized shopping lists and deployment plans for new slot machine purchases.

The first step is to identify machines that should be decommissioned. “No single attribute will explain all of the variation in performance,” claims SAS. “In a sample case from a Canadian casino company, seven variables were influential, and some of the findings were surprising,” says SAS. “Some rules of thumb that were seen as instrumental in previous decisions are not as important as one might expect."

The next steps is choosing the replacement machines. “Having generated a revenue forecast for all the machines, we now understand where the revenue is going to be, based on where a machine is in its life cycle, as well as where demand is expected to migrate as new machines are deployed,” said Carothers. The goal, of course, is to select more machines that replicate the performance of the good machines.“The next step is to gather data from manufacturers to identify which new machines are more like those best-performing machines, both in gross wins and patron experience,” says SAS.“ These new machines – candidates for purchase – become analysis surrogates for comparable machines and replacements for others that have lost their luster,” explains SAS.

The third step is to deploy the new units within some constraints. Forecasting predictions should be used to determine the best mix of machines for the floor through optimization. “Optimization is a prescriptive type of analytical work that will generate specific recommendations and timelines for purchasing new machines, decommissioning others, and reconfiguring the machine mix,” says Ivan Oliveira, Director of Advanced Analytics at SAS.

Step Four is to assess the effects of the replacements. “A closed-loop process ensures that forecasts of future revenues are appropriately calibrated in the models, cannibalization is understood and accounted for, and the analytic tools are optimized and fine-tuned along the way,” argues SAS.

In summary, SAS says, “the slot floor optimization process starts by categorizing machines and generating revenue forecasts for existing and new machines. Since there are many permutations of potential changes to the slot floor, these forecasts are pushed into an optimization process that generates an action plan. The results of implementing those recommendations are continuously monitored, and that information is rolled back into the process to refine predictive models for ever greater accuracy.”


Intelligencia's consultants can help you get your data house in order, then work with your team to build the models, or we can build them alone, then deploy and maintain them on your systems. Or ours. The choice is yours.


Our managing director has written The A.I. Casino, a book about how airlines can optimize their operations. 

From Amazon:

"The A.I. Casino breaks down A.I., machine learning, and deep learning into five unique use cases—sound, time series, text, image, and video—and also reveals how casino marketing executives can utilize this powerful technology to help them more finely tune their marketing campaigns, better segment their customers, increase lead generation, and foster on strong customer loyalty."


We are here to help you navigate the complex world of analytics, AI, BI, CX, Cloud, DI, digital marketing, and social media implementations, showing you how open source technology can, potentially, augment your current software footprint and reduce cost. We understand ROI is king, above all else.


Address: 505 Hennessy Road, #613, Causeway Bay, Hong Kong

Phone: +852 5196 1277 (HK)

Phone: +853 6616 1033 (Macau)

WhatsApp: +853 6616 1033



Join Our Community

Sign up to receive email for the latest information.
© Intelligencia Ltd. All Rights Reserved. 2020