Michael F. Gorman, University of Dayton

Our section is thriving - an active discussion board at our LinkedIn site, the analytics conference just around the corner where we will celebrate the Analytics Section's first birthday. Don't forget to register for the INFORMS Conference on Business Analytics and Operations Research with your $30 Analytics Section Member Discount. Enter promocode: ANALYTICSMBR when registering.

In this, our fourth newsletter, we announce the winner of the SAS/INFORMS Analytics Section Student Scholarship and finalists of the Innovations in Analytics Award. Also, Bruce Patty of Veritec Solutions provides another Analytics Story for your enjoyment and education. As a service to our members, we also provide a summary of some of the leading academic programs in analytics, below. Read on!

I am happy to report to our members that the Analytics Section is forging a strategic alliance with the Analytics Magazine's eNewsletter, merging the Analytics Lens with content from the Analytics Magazine. What does that mean to members? First, more content, delivered more frequently. The Analytics Magazine's eNewsletter is delivered monthly. Second, broader distribution of the activities of the Analytics Section. But, we will still maintain members-only content such as Analytics Stories, as well as information on upcoming tracks and sessions.

Important Developments and opportunities to participate!

We are currently accepting nominees for our three elected positions: Secretary, Treasurer, and Vice President. (Our vice president, Zahir Balaporia will assume the President's role at the fall INFORMS meeting). Please feel free to contact me for more information or to step up!

What topics would you like to see covered or present your work on at the fall Annual Meeting? Have direct influence over the fall program by stepping up now to be:

• Cluster Chair - Coordinates sessions chair for various topics and coordinates with the CPMS Cluster chair Russell Labe and the Annual Meeting Practice Chair Karl Kempf.
• Session Chair - Finds speakers on specific session topics
• Speaker - Presents on topics in their area of analytics expertise

Please feel free to contact me!

Michael Gorman
Analytics Section Chair and Analytics Lens Editor
University of Dayton
Michael.gorman@udayton.edu

This scholarship is geared towards encouraging students interested in analytics to attend the INFORMS Conference of Business Analytics and Operations Research. This was a competitive program, supported by SAS® and sponsored by the Analytics Section of INFORMS with twenty applicants. The award recognizes one outstanding student who would like to learn more about the practice of analytics at this conference in Huntington Beach, California, April 15-17, 2012 by covering the costs of attending the event and additional networking opportunities.

What does the scholarship cover?

• Round-trip flight to the conference
• Hotel (3-4 nights, depending on whether the student can catch a flight home the day the conference ends or must wait until the next day)
• Most meals (which are included in conference registration)
• Registration for the conference and for the Professional Colloquium 

I would like to thank my fellow committee members, Polly Mitchell-Guthrie and Udo Sglavo of SAS, and William VanMarter.

A full description of the scholarship is found at our website.

We are happy to announce this year's winner is Sarah LaRocca of Johns Hopkins University. Congratulations, Sarah!

Sarah LaRocca, a doctoral student at Johns Hopkins University in Environmental Systems Engineering, has been named the first SAS and INFORMS Analytics Section Student Analytical Scholar. Her research is on developing and testing innovative methods for modeling the performance and reliability of interdependent infrastructure systems, which has allowed her to gain experience in using a wide variety of analytics techniques, including statistics, data mining, optimization, game theory, and decision analysis. Her award will support her travel to and participation in both the INFORMS Professional Colloquium and the INFORMS Conference on Business Analytics and Operations Research in Huntington Beach, California. Sarah was chosen because she is truly passionate about analytics and has clear goals for how attending the conference will help her as she finishes her research and begins her career search for a research position in government or industry. Sarah would like to use a data-driven approach to solving problems in the field of infrastructure security and reliability. As she wrote, "Although the term analytics is frequently associated with business, I believe that the techniques it encompasses are tremendously useful in solving problems in the public sector, and will only become increasingly beneficial in the future." Please join us in congratulating Sarah on her award, and if you will be attending the conference look for her in person!

Overview
After 20 years of consulting in the freight transportation arena, I joined Pacer Stacktrain as AVP of Equipment in 2003. One of the key responsibilities of our group was to determine how many chassis of each size (20', 40', 48' and 53') needed to be positioned at each location across North America where Pacer containers would arrive on trains. At the time, Pacer had the largest domestic container fleet in North America with over 27,000 containers and also had contracts with its rail partners which allowed Pacer to provide its own chassis at rail terminals across North America. (Note: In the domestic intermodal marketplace, containers are designed to move around North America on trains, then be mounted on chassis at rail terminals in order to be transported from the rail terminal to the destination by trucks.)

In the years preceding my arrival, Pacer had developed a spreadsheet model to estimate the number of chassis of each size that would be needed at each equipment supply point (EQSP). This analytic model used traditional inventory planning inputs like turntime (estimated number of days that an arriving container would use a chassis), forecasted number of containers arriving on a train each day, and the number of days each week that trains arrived or departed. In general, this model did a good job at estimating the number of chassis that would be needed in "steady state" conditions. And yet, more often than was desirable, the number of chassis actually needed far exceeded the projection. We needed to identify what was causing the model to be so far off.

Since the model was developing accurate projections at about 90% of the EQSPs, we believed the fundamentals of the model must be working properly. Given that, our initial guess was that one or more of the inputs to the model was off. The most likely possibilities were that inbound freight had surged, turn-times had significantly increased, or the number of trains operated each week had dramatically dropped. However, when we analyzed updated measurements for these values, we found that actual numbers were quite close to those used in the model! With our first hypothesis proven wrong, we needed to consider other possibilities.

We decided to step back from the problem and see if we could identify any business conditions that consistently were present at EQSPs where the actual number of chassis needed exceeded the projections. We set up conference calls with both the Equipment team and the Operations team to discuss what was happening at the terminals that were "in trouble". After several calls it became evident that we needed to conduct some historic analyses PRIOR to the calls, or we would get bogged down with anecdotal discussions about what happened on one particular day when some unusual situation took place; this made it virtually impossible to move the discussion to the underlying fundamentals. After using these analyses to discredit some theories that were driven by these one-time occurrences, we realized that EQSPs where we were running short of chassis tended to be locations where empty containers would build up until they were repositioned out on trains. That is, inbound loaded container volume exceeded outbound loads and empties were building up at the terminal.

We then went back and looked at the model to see how it handled this situation. We found out that turn-times were being measured from when the container and chassis left the terminal after arriving on an inbound train to when the container and chassis "ingated" the terminal after being released by the customer. The time between when the container ingated the terminal and when the container was taken off the chassis and placed on the outbound train was not included in this measurement, often because those events were not transmitted to Pacer by the rail carrier. However, this time was not included for both loaded and empty containers. Why was its omission only causing problems at terminals where empties accumulated?

To answer this question, we arranged another round of conference calls with the Operations team. We found out that a key difference in the way that loaded containers and empty containers were handled by the railroads was that, if there was limited space on the trains, the loaded containers would get priority. So, empty containers would be left behind. While this worked fine in terms of meeting delivery promises for the loaded containers, it caused situations where empty containers would stay mounted on chassis for days. And since these days were not being captured in our measurement of turntime, the model was not accounting for this in the chassis projection. In short, we discovered that under certain and occasional conditions, our modeling assumptions did not reflect operational practice.

We ended up modifying the model that estimated chassis requirements by using historic chassis usage trends that did include chassis on terminal, and then looking at averages, maximums and variances from the norm to develop demand projections. With this change, we were able to dramatically improve the accuracy of the model. The change in our modeling approach was one of the key reasons that Pacer was able to meet chassis needs with an industry low chassis-to-container ratio of 85%. But, I'll save that story for another article.

What can be gleaned from the process described above that can be applied to many business problems? Below are just three key insights:

Confirm the assumptions behind a model: Analytic models are just that, an attempt to model a real-world phenomenon. These models are based on fundamental assumptions such as the probability distribution of arrivals, linearity of a cost function, or limitations on supply. Often when models are developed and subsequently used, assumptions are glossed over and attention is paid to getting the inputs as accurate as possible, or ensuring that all of the constraints are accurately represented. But, in situations where the results from the model are not accurately reflecting the real world phenomenon, it is often best to start with confirming that the model assumptions are truly valid for the situations where the model is failing. In our case, the assumption that the chassis requirements were driven by inbound loaded container volumes did not hold for locations where empties could build up, requiring significant quantities of chassis. That said, the original modeling assumptions were reasonable for 90 percent of the actual situations!

Diagnose causes of problems by identifying similarities or commonalities: Often, there will be situations where models are working well for a majority of cases and not working for only a few. In these situations, one of the quickest ways to diagnose the problem is to identify what the few "problem" cases have in common and then determine how the model behaves or handles those similarities. In our process, by identifying that the locations where the model was not performing well were locations where empties built up, we were able to focus our attention on how the model handled empties.

Understand how measures are being calculated: In school, we're often presented problem descriptions where the values (costs, supplies, demands, times, etc.) are provided to us and we are then responsible for building a model or solving a system of equations. We don't spend much time questioning how the values were calculated or derived. In practice, determining how to come up with these parameters is often the most challenging aspect. I've never encountered a situation where my manager or my client came to me with a table of numbers and asked me to solve for the correct answer. Often, we are limited in our ability to come up with the most accurate set of values by the data that is captured in our systems. To develop accurate and useful models, we must understand how these limitations will impact our solutions and make allowances for these impacts. In our situation, the fact that turn-times did not include the on-terminal time after a container came back into the terminal on a chassis until the container was loaded onto the train became a serious shortcoming, especially at EQSPs where empties could build up and this time became significant.

NC State University became the first school in country to offer a Master of Science in Analytics (MSA) degree when the Institute for Advanced Analytics opened its doors to students in June 2007. The MSA is a uniquely designed professional degree that equips students for the challenging task of deriving insights from a vast quantity and variety of data. The Institute operates as a university-wide collaboration that involves a large number of faculty from a dozen different departments, including areas such as OR, mathematics, statistics, computer science and business. The Institute's independence as an academic unit enables it to create and deliver a degree program in a way that goes beyond traditional institutional structures to directly address the educational needs of its students.

The MSA curriculum was developed entirely new and exclusively for students in the program. It is a fully integrated 10-month learning experience that immerses students in the tools, methods and applications of analytics. The curriculum keenly focuses on nurturing those skills employers want most when hiring candidates. In addition to a broad array of technical skills-in areas such as data and text mining, time series and forecasting, optimization, and risk, among others-the MSA places heavy emphasis on developing teamwork, leadership and communication skills. Students work in teams throughout the program and receive individualized feedback and coaching on how to improve their performance. The curriculum also gives students hands-on experience working with the complexities of real-world data (from sponsoring organizations) and using industry standard tools, such as SAS. Students become so adept with using tools most will complete one or more programming certifications en route to their degree. As a result, MSA students can gain a level of understanding in solving real business problems that exceeds the typical internship experience.

The MSA has proven to be a powerful learning model. The Institute has an unparalleled 5-year track record of success in producing analytics professionals. Since its inception, each year the Institute has placed over 90% of its students in jobs by graduation. The Institute manages the job placement process for its students and plays a role in most, if not all, placements with employers. In 2012, students had an average of 15 initial job interviews, and over 80% had two or more job offers. The salaries for students in 2012 ranged from $60,000 - $160,000 with the average offer to students with two or more years of previous job experience at $100,100. The average offer to students without any previous experience was $77,200. This strong demand for MSA students is quite favorable given the relatively low cost of the program - $19,400 in-state and $34,300 out-of-state tuition - and quick time to completion.

The Institute currently admits 80 students each year in June. More information can be found online at http://analytics.ncsu.edu.