Maryland Smith Research / July 25, 2019

Finding the Best Path to Your Target

Algorithm Helps Organizations Find Their Sweet Spot

Finding the Best Path to Your Target

Political candidates, manufacturers and even online game designers can hit their performance targets with increased regularity using a new algorithm developed by professor Ilya Ryzhov at the University of Maryland’s Robert H. Smith School of Business.

The prediction model works best in situations where decision makers have a complex set of variables to consider and a predetermined target — rather than a general desire to maximize results as much as possible.

An example occurs during presidential campaigns. Candidates use polling data to identify locations where political rallies and media buys might have the biggest impact. The goal is not to maximize results as much as possible, but to push candidates past the threshold to win elections in key “swing states.”

Boosting someone’s popularity by 5 or 10 percentage points is wasted effort if the starting point is 30% or 60%. The real objective is to select regions where the candidate’s rating is as close to 50% as possible.

A similar situation occurs in manufacturing and quality control. The goal is usually not zero product defects, which might be too expensive to achieve. Instead, process designers determine an acceptable tolerance level and run simulations to find the most efficient path to the target.

With online gaming platforms like Microsoft’s Xbox Live, the goal is to match opponents whose skill levels are as close together as possible.

Simulation optimization often relies on a “ranking and selection” framework, which assumes a desire to maximize mean performance. Ryzhov uses a “targeting and selection” framework instead, which assumes a predetermined target.

His proposed algorithm then simulates the option with the best chance of matching the target — or the alternative with the highest expected "Brownian local time," a mathematical term used to predict the proximity of a moving variable to a predetermined location. "The local time argument is a novel and potentially useful idea for sequential selection problems that involve targeting," he says.

Read more: The Local Time Method for Targeting and Selection, by Ilya Ryzhov is featured in Operations Research, Vol. 66, No. 5.

Media Contact

Greg Muraski
Media Relations Manager
301-892-0973 Mobile 

Get Smith Brain Trust Delivered To Your Inbox Every Week

Business moves fast in the 21st century. Stay one step ahead with bite-sized business insights from the Smith School's world-class faculty.

Subscribe Now

Read More Research

Back to Top