The Science of Internet Advertising

Given the number of requests that I have received lately from firms, especially from start-up firms, to write about them in this blog, my daughter suggested that I start charging for such "services."

Since I am a researcher and educator, for the time being, I will instead note some research of ours, which has just been published. The research is on the general theme of the Science of Internet Ads, which we have been pursuing with co-authors. Our latest paper, hot off the press is, "An Integrated Approach for the Design of Optimal Web Banners," and it appears in volume 11 of the journal Netnomics (2010), pp. 69-83. My co-authors are Professors Lili Hai and Lan Zhao of the Department of Mathematics and Computer Information Science at SUNY Old Westbury.

In this paper, we target the very first step of Internet advertising -- that of banner design using the tools of statistical analysis and optimization.

While banner advertising has become prevalent, consumers have also become more selective. Indeed, the banners' click-through rate, which is the ratio of the number of click-throughs to the number of exposures (times that the banner is shown to Internet surfers), has declined precipitously to an average of less than one-half percent.

In order to be fully effective with banners, a scientifically sound approach using real time data is needed to determine an optimal design.

Our paper demonstrates how to use a statistical predictive technique and optimization methods to exploit the richness of data collected on banner visitors' activities in order to achieve the goal of optimizing the banner designs. The optimization procedure begins with establishing a banner information repository that complies with database technology.

The above data may change for each advertising cycle. After the establishment of the information repository, the statistical predictive model is constructed based on the data. It not only identifies the significant components, but also quantifies the contribution of each component to the click-through rate of a banner. The predictive model sets click-through rate as the function of banner components. Finally, mixed integer programming is used to maximize the click-through rate as a function of the feasible set of components.

The major benefits of our method are that it allows one to systematically improve banner advertising by capturing the dynamics of browsers and to "unintrusively" personalize web advertising at the cluster-level.

In our first paper on Internet advertising, published also in Netnomics, in 2005, Zhao and I modeled optimal Internet advertising strategies for allocating an ad budget to websites as a network optimization problem, and constructed an efficient special-purpose algorithm for the determination of the optimal solution. We then explained two different paradoxes that occur in this setting.

In a paper of ours published in the European Journal of Operational Research, the network optimization modeling framework was expanded to model Internet advertising competition in which multiple firms maximize their own ad effects within their limited marketing budgets. In that paper, we introduced an elastic Internet marketing budget in order to conjoin the online and offline marketing strategies. Consequently, the multifirm competitive equilibrium problem was modeled using game theoretic constructs as a Nash equilibrium with network structure.

Professor Lan Zhao is a Center Associate of the Virtual Center for Supernetworks that I direct, and she also consults for flowers.com so our research results have immediate practical applications.

For reprints of various articles, conducted by researchers at the Virtual Center for Supernetworks please click here.

Business Profs that Make a Difference

I recently finished reading "Tuesdays with Morrie," by Mitch Albom, a book that I very much enjoyed. The book is filled with numerous memorable quotes attributed to Professor Morrie Schwartz, a former Professor at Brandeis University, on life, on living, and on education. Mitch Albom, who was a former student of his, captured in this wonderful book not only his deep affection and caring for this very special professor, but also the wisdom and love of life of this exceptional educator.

There was one part in the book, though, that I strongly disagreed with. Albom writes in the chapter, "The Professor, Part Two," that Morrie's classes at Brandeis were light on what you'd call "career skills" and heavy on "personal development."

And because of this, business and law students today might look at Morrie as foolishly naive about his contributions. How much money did the students go on to make? How many big-time cases did they win?

Then again, how many business or law students ever visit their old professors once they leave? Morrie's students did that all the time.

Albom, in his book, captured the essence of what makes a great teacher, and the book is a testament also to an exceptional writer as he takes the "final class" with his beloved professor through the final stages of his serious illness until his death.

As debates rage on regarding student evaluations of teachers at the college level, with Dr. Stanley Fish's provocative recent piece in The New York Times, as well as his followup with links to many thoughtful comments and responses, it is clear that the impact of a great teacher cannot be measured simply after the class and semester are over with a short questionnaire and evaluation form. Such a myopic but prevalent perspective may be convenient from an administrative point of view but does not measure true greatness in terms of instruction and lasting impact.

Those who were once students and who come back years and even decades after graduation to see a professor realize this, for sure.

In our local paper, the Daily Hampshire Gazette, there is a front page article today on one of my colleagues, Professor Richard "Dick" Simpson, who is an accounting professor at the Isenberg School at UMass Amherst. Professor Simpson has been teaching for 42 years and his former students keep their accounting class notes for as long as thirty years. His remarkable influence on business education and on individual students has been recognized with numerous teaching awards.

One of Professor Simpson's present students, Carmelina Romano, who is a mother of two children (and who instead of bedtime stories read Professor Simpson's accounting class notes to her two young children) and was formerly homeless, was also featured in the article. She would bring her children to class, with his permission, studied about 20 hours a week for his class alone, and her 4 year old son would sometimes answer questions posed by Simpson in class to the fascination of the college students.

Ms. Romano wrote a letter nominating Simpson for the Mass Society of CPAs educator of the year and then hounded everyone who could possibly be involved with that decision to make sure that he received this honor.

Professor Simpson ended up receiving the Society's Career Achievement Award for Excellence in Accounting Education and stood with Romano when he got it.

So, business professors can make a difference!

When I returned from the ALIO-INFORMS conference, which took place in Argentina, 2 weeks ago, I found a business card under my office door. A former student of mine in the first class that I ever taught as a professor had left his business card under my door. He had been a student in my MBA class and was working very hard at a menial job to advance his education. To that class I brought my Brown University PhD diploma to show some students, who were mid-level managers, who doubted that I was a professor since I reminded them of their granddaughters.

The message on the business card said:

Dr. Nagurney:

It's been 25 years so I thought I would stop by and say hello!

Call me sometime.

This former student now has a top executive-level position with a major automobile company and his daughter will be matriculating at UMass in the Fall. I remember him just like yesterday. We will see each other in September.

FIFA President apologizes and goal-line technology

The FIFA President, Sepp Blatter, has apologized for the refereeing calls at the 2010 World Cup, and has acknowledged that both England and Mexico were shortchanged a goal each in their elimination games recently.

We, as spectators around the world, have also been stunned by what our eyes perceived to be erroneous calls by the referees even against the United States in two games.

The idea of goal-line technology is getting increasing credence according to The New York Times. Interestingly, before this World Cup started, Blatter was adamant against video replay — and other forms of in-game technology.

“We want to keep football as a game of the people with a human face, so we don’t want technology on the field of play because we want to maintain the spontaneity of football — played, administered and controlled by human beings,” Blatter said.

Now that the 2010 World Cup has identified the top 8 remaining teams, Blatter is now quoted in The Times as saying:

“It is obvious that after the experiences so far at this World Cup,” “it would be nonsense not to reopen the file on goal-line technology.”

At least he apologized and is willing to admit the (obvious) oversights by the referees in several games.

The damage has been done but Sepp Blatter had the courage to admit that errors were made. I wish that some heads of professional and even youth sports organizations would do the same.

The Economics of Happiness and Optimization

Andrew Marszal writes in a recent Aol News Opinion Piece on the "Economics of Happiness" and reports on research and studies on this topic which, he notes, is "catching on" with the likes of the Nobel laureate Joe Stiglitz (who I might add is an Amherst College grad) and with the French President Nicholas Sarkozy even getting involved.

According to a recent global survey, participants, when asked what is their most important goal in life, ranked "happiness" first, ahead of "'success," "knowledge" or even "material wealth." The
global survey is worth reading since it captures the psychological, economic, and social aspects of well-being in a very thoughtful writeup.

In his Opinion Piece, Marszal writes: Trust is strongly correlated to happiness and varies dramatically among societies. A recent World Values Survey, conducted by an international network of social scientists, found 64 percent of Norwegians responded "Yes, most people can be trusted," compared with just 5 percent of Brazilians. Of Americans, 56 percent held this opinion in the 1960s, but only 33 percent by 1998.

In addition, it is emphasized that family relationships and work are crucial, too.

In economics, as in operations research, the concepts of optimization and utility maximization, under constraints, are fundamental. What is emerging from the above noted studies (and more links to others can be found in the Opinion Piece) is that social networks, whether familial, community-based, or at work do matter and in significant ways. Social networks capture relationships and their evolution can serve as indicators of trust.

In a series of articles, we examined the impact of social networks on different networks, and introduced flows in social networks in the form of relationship levels. When relationship levels are higher, various costs are reduced (not only in a business sense but also, generally, in the form of transaction costs). Our research captured the effects of social networks and relationship levels on supply chain networks as well as on financial networks.

As Dr. Patricia Randall writes in Reflections on Operations Research, It will be interesting to see in the future how Operations Research and analytics can be applied to social networking problems and how these approaches differ from more “traditional” applications.

I strongly believe that much of the breakthroughs will come through the synergies of synthesizing, integrating, and expanding findings and perspectives from different disciplines from the social and behavioral sciences to computer science and operations research and the management sciences, as some of the leaders in social science and social computing are suggesting. As for the potential payoffs, what could be more rewarding than creating societies in which there is a greater level of trust and higher levels of "happiness?!"

From the World Cup to the World Expo

After the painful loss today of the US soccer team to Ghana's at the World Cup in South Africa, resulting in the US team being eliminated, I thought that I would offer some distraction by posting the above photos taken at the World Expo which is now taking place in Shanghai, China.

But, first, I would like to congratulate the US soccer team and their coaches for their extraordinary efforts. You won the hearts of our country and we are tremendously proud of how well you played.

Congrats to Ghana for being the only African country left representing this continent at this stage of the World Cup.

The above photos were taken recently by relatives of a doctoral student of mine who visited the World Expo in Shanghai and I thank them for allowing me to share them with you. Several of my collaborators are now also in Shanghai and I hope that over the summer I will be able to post additional photos.

The first photo is of China's pavilion (and interestingly in yesterday's New York Times there was a two page photo spread and ad for this World Expo). The second one is especially lovely at night, I am told, and the color and images change. The third photo is of Estonia's pavilion. The fourth photo is of the World Exposition Museum. The fifth is an artwork with four monkeys, which is a symbol of families' happiness. The bottom photo is the Qatar pavilion.

Although China did not qualify for the World Cup I am hearing marvelous things about its World Expo.

Professor George L. Nemhauser and Sports Scheduling in The Chronicle of Higher Ed

The name of George L. Nemhauser is well-known (I should say renowned) in operations research.

The Chronicle of Higher Education has a really nice writeup on Professor Nemhauser's work in sport scheduling and on his company. According to the article: His company, Sports Scheduling Group, now handles all scheduling for Major League Baseball and has worked with the Atlantic Coast Conference, Big Ten, Mountain West, and other college leagues. Over the past few weeks, as conferences considered all kinds of changes, he fielded numerous calls from athletics officials wondering how their schedules might be affected by the addition of one or more programs.

George Nemhauser's paper, with Mike Trick, entitled, "Scheduling a Major College Basketball Conference," that appeared in one of our top journals, Operations Research, is a classic.

Earlier in this blog I wrote about the work of Professor Celso Ribeiro in soccer game scheduling in his home country of Brazil.

It is great that The Chronicle of Higher Ed recognizes the great contributions of our profession to applications in sports!

The full Chonicle of Higher Ed article can be accessed here.

I have a special soft spot for Professor Nemhauser because, after my PhD dissertation advisor at Brown University, Stella Dafermos, received her PhD from Johns Hopkins, she moved to Cornell University and George was her mentor there. I also regularly cite his work with Trotter on column generation as applied to traffic network equilibrium algorithms for the solution of large-scale problems.

When Stella died, back in 1990, George was one of the first people that I called with the sad news and he was instrumental in having me write her obituary which appeared in Operations Research.

Portfolio optimization, risk management, and operations

As we see every day -- whether in business or in our personal and professional lives -- decision-making and its consequences, are fraught with risk. The risks may take on many forms from political risk to exchange rate risk and price volatility risk to environmental risk and disruption-based risk, as in disasters due to natural causes, accidents, or planned attacks, to name just a few. The world now is reeling from the BP Deep Horizon oil rig blowout, the most graphic, high impact recent environmental and economic disaster.

Risk management, hence, has evolved as a topic in its own right and is necessarily interdisciplinary because of its vital components, be they social, engineering-based, financial, natural, operational, etc.

In terms of business operations, firms may need to decide whether to outsource various economic activities associated with their supply chains or to continue business as usual. They may need to assess whether to merge or to acquire another firm, which may lie thousands of miles away. They may have to identify new partnerships or to shed older ones; to promote and hire new executives, or let others go. Should one build a new manufacturing plant and where? Should one bring to production a new product? Should one expand into new global markets? All such decisions must have embedded within them some measure of risk since we live in uncertain and very dynamic times.

The areas of finance and operations management (propitiously also the name of my department at the Isenberg School of Management at UMass Amherst) can bring much to both research in and the practice of risk management.

Last year I had the honor and pleasure of instructing a course on portfolio optimization in the Executive Education program at Harvard University's Graduate School of Design. The course covered the fundamentals of portfolio optimization and risk management and also discussed the importance of a network and systems perspective to financial management.

My course lecture notes can be accessed here.

Today we are conducting research on global outsourcing and risk management as well as on supply chain network design and risk. Our recent studies on various supply chain network as well as financial network topics can be accessed here.

Without appropriate risk management and risk mitigation strategies our already fragile and vulnerable networks may not be sustainable.