INFORMS IN THE NEWS

Growing analytics, exec pay issues, continuing ed

Compiled by Barry List

Barry.List@informs.org

INFORMS podcasts continue to offer provocative conversation with leading analytics/O.R. practitioners and thinkers. The latest podcasts include Norm Reiter and Aaron Burciaga on INFORMS’ recently launched Analytics Maturity Model and journalist Adam Tanner on consumer concerns about privacy in the new information age. Visit INFORMS Today at www.informs.org to download the latest selections.

Visit the INFORMS Newsroom at www.informs.org for news about analytics and INFORMS press releases. Remember to share your news-making research with the INFORMS Communications Department. Contact INFORMS Communications Director Barry List at barry.list@informs.org or 1-800-4INFORMs.

And now, excerpts of INFORMS in the News:

Four Ways to Grow Analytics Intelligently in the Year Ahead

As analytics continues to capture the attention of the business world, we contemplate a distinct field that uses newly available data to make better decisions. In the coming year, we must pay attention to our university analytics degrees, our continuing education, certifying competent practitioners, and organization-wide evaluations to make sure that our field grows and we bring greater benefit to those who seek our insights.

With McKinsey’s now famous forecast of a shortage in analytics professionals ringing in the ears of CIOs and executives, my fellow academics and business leaders must plan now to make sure that the supply of trained professionals remains high and that those who currently use analytics stay up to date in a fast-changing world.

- INFORMS President-Elect L. Robin Keller in Data-Informed.com, Nov. 11

A Private Jet to Your Kidney Transplant with some O.R. help

The supply and demand imbalance between organs and the people who need them means that wait lists in New York or San Francisco might be twice that of, say, Kansas or Tennessee. The problem was brought to public attention in recent years by Steve Jobs, who used his resources to travel across the country for a liver transplant. For decades, doctors and policymakers have debated how to move organs or change allocation maps in an effort to eliminate these disparities.

Now, Sridhar Tayur proposes to turn the problem on its head. OrganJet, his brainchild, is a company that uses an online app to help patients find out where in the country they could go to get a liver or kidney the fastest, and then promises a private jet to fly them there at a few hours’ notice when the organ becomes available.

It might all sound a bit crazy. At 49, Tayur doesn’t have any training in healthcare or in the field of medical ethics. He is a Carnegie Mellon University-chaired professor of operations management with a Ph.D. in operations research, a field that uses mathematical modeling to solve business problems.

- Atlantic, Oct. 29

Marketing Science Study: Skillfully Use Product Placement

Consumers have become highly adept at avoiding television advertisements. We switch channels, divert attention to our tablets and phones, and of course fast-forward through ads on our DVRs. Partly in response to this loss of attention, marketers are increasingly focused on product placement as an alternative way of exposing us to their brands. After all, product placement is innately much harder to skip given its integration into the actual program content.

Most academic research on product placement has primarily considered it as a separate persuasive technique independent from the commercial break advertising. That is, mirroring early research on TV advertising, research has focused on how product placement influences viewers’ recall of and attitude toward brands. However, this overlooks the possibility that product placement in a show might influence the likelihood of viewers watching an advertisement for related products at the next commercial break.

In research just published in Marketing Science, my colleagues David Schweidel of Emory University and Natasha Foutz of the University of Virginia and I began to explore whether such synergies exist.

- Robin Tanner, Forbes, Sept. 8

Executive Pay: The final reckoning

In his book, “Capital in the Twenty-First Century,” Thomas Piketty argues that it is impossible to find an “objective basis” for the high salaries of senior executives in terms of their individual productivity: They pay themselves such exorbitant sums simply because they can. However, in a forthcoming paper in Management Science, an American journal, two academics claim to have found such an objective measure, and conclude that most bosses are not overpaid.

In their study, Bang Dang Nguyen of the University of Cambridge’s Judge Business School and Kasper Meisner Nielsen of the Hong Kong University of Science and Technology looked at how firms’ shares react when the chief executive or another prominent manager dies suddenly. They identified 149 cases of this happening at American companies between 1991 and 2008.

- The Economist, Sept. 6

Jacobson: Use O.R. Airport Screening Methods for Ebola

“Screening for Ebola is more difficult than screening for threats to the air system” from terrorists, said [2015 INFORMS Treasurer] Sheldon Jacobson, a computer science professor at the University of Illinois at Urbana-Champaign, who has written extensively about aviation security. He said more needs to be done to vet passengers, perhaps including blood tests for the Ebola virus and some sort of trusted-traveler program for people considered low-risk.

- Associated Press, Oct. 2

Continuing Ed Preview: Harness the Predictive Power of Simulation

One important question that arises with simulation experiments is whether a Monte Carlo simulation or a discrete-event simulation is appropriate. A Monte Carlo simulation is appropriate when the passage of time does not play a significant role in the events being simulated. Estimating probabilities, expected values, etc., in problems associated with dealing playing cards, rolling dice and flipping coins, for example, can be addressed by a Monte Carlo simulation. In order to estimate the probability of a specific event, a Monte Carlo experiment is conducted repeatedly, often several million times, and then the number of times that the event of interest arises is identified. This serves as an estimate of the true probability of the event of interest.

Although the concept is simple, the real-world implications are profound. Monte Carlo simulations are used in varied contexts, such as stock-price predictions, sports outcome predictions and even to explore various molecular conformations of antibiotics…

Authors Larry Leemis, a professor in the Department of Mathematics at The College of William & Mary, and Barry Lawson, an associate professor of Computer Science in the Department of Mathematics and Computer Science at the University of Richmond, will conduct Introduction to Monte Carlo and Discrete-Event Simulation, a continuing-education course offered by INFORMS, Oct. 16-17 in Chicago.

- DataInformed, Sept. 23

Training Healthcare Analytics Experts

A well-trained data scientist is often called a unicorn: elusive, desirable and more than probably mythical. Even as healthcare joins a slew of other industries in its transformation into a technology-reliant ecosystem built on data analytics, finding and retaining qualified analytics and informatics staff members is easier said than done.

At Georgia Tech’s Stewart School of Industrial and Systems Engineering (ISyE), a group of professors led by Nicoleta Serban, ISyE Coca-Cola Associate Professor, and Julie Swann, ISyE’s Harold R. and Mary Anne Nash Associate Professor, has brought together an interdisciplinary collaboration of healthcare analytics experts, including many members of INFORMS, the largest analytics professional society, to train the new generation of data scientists.

- Health IT Analytics, Oct. 6

ManSci Study: Good Working Relationship with Bankers Reduce Defaults

As a newly published study co-authored by an MIT professor shows, strong working relationships between bankers and clients reduce the likelihood of loan delinquencies and defaults, at least in the context of an emerging economy.

Using propriety data from a large bank in Chile, the study finds that when loan officers go on leave, their clients in good standing – often small businesses – increase their probability of becoming delinquent on loans by almost 22 percent. For already-delinquent clients, the probability of default on loans increases by 18 percent.

At the same time, there is a 5 percent reduction in the approval rate for loans among those clients. That means banks are both issuing fewer loans and suffering more defaults when relationships between individual bankers and clients are interrupted…

“It is a two-way channel,” says Antoinette Schoar, the Michael M. Koerner Professor of Entrepreneurship and a professor of finance at the MIT Sloan School of Management, and a co-author of the paper reporting the findings. She attributes the results to “a type of loyalty building up between the client and the loan officer” that “could not only affect how good the loan information is ... but also the willingness of the client to default.”

The paper, “Do Relationships Matter? Evidence from Loan Officer Turnover,” has been published in the journal Management Science. The authors are Schoar and Alejandro Drexler of the Federal Reserve Bank of Chicago.

- Science Codex, Sept. 29

Get Smart About Analytics Education

Ideal students don’t just hand over their predictions from a churn analysis they’ve been asked to complete and then move on to the next assignment. Rather, they’ll probe deeper into the data. They’ll want to find out why some customers are prone to churn while others aren’t, and more importantly, they’ll want to come up with recommendations for how a company can cope with the propensity of customers to churn.

“Students have to have that curiosity that drives them to find additional patterns from the data even though the business users or management hasn’t specifically asked for it,” explained Diego Klabjan, program director for Northwestern University’s two-year-old Master of Science in Analytics program, during yesterday’s A2 Radio episode on how to pick an advanced analytics degree program (listen on demand).

- allanalytics.com, Sept. 15

Barry List (barry.list@informs.org) is the director of communications for INFORMS.