Last weekend, I met a friend who works as a Risk Modeler for a financial services company in Chicago. We were meeting in person after four years and therefore we had a lot of catching up to do. Somewhere during our hours long chit-chat, we got into some deep discussion about applications of analytics within Supply Chain domain.
I am a professional Logistician ( or at least I like to believe that I am) who loves Operations Research (OR) and who has used OR tools extensively in his now nearly a decade of logistics engineering career. I have always been obsessed with OR and my friend was very much familiar with my love towards the discipline of OR. He is a Big Data champion and works mostly with predictive analytics tools and methodologies. He asked me whether OR as a separate discipline was still relevant, considering that with advent of Big Data, numerous new analytics methodologies are available these days. That touched a nerve and prompted me to write my very first post on LinkedIn, aimed at defending the discipline of Operations Research from all the non-believers out there.
For starters, Operations Research is an applied mathematics discipline that leverages multiple algorithms and techniques like simulation, modeling, queuing, and other stochastic and probabilistic methods to optimize or improve a business process. The foundation for this discipline was laid during World War II and the key driver was to leverage applied math to find solutions to strategic operations and logistics problems. The discipline has evolved since then and OR techniques are used widely in non-military scenarios today. Operations Research has been employed in Logistics Engineering for quite some time now, some of the classic applications being optimizing flows, identifying optimal locations, minimizing transportation costs, optimizing transportation assets, Inventory Optimization etc.
While Operations Research evolved over the years to find applications outside military and became widely used in Industries, other fields also evolved concurrently. An example can be Management Science, which was essentially leveraging applied math to solve business and economics problems. With advancements in computing technology, data mining tools and database technologies, we saw emergence of new fields like econometrics, machine learning, numerous predictive analytics tools and methodologies and the advent of the hottest buzzword of all-Data Science. Data Science and Big Data are the buzz words these days and no one can deny the benefits of applications of Data Science in end to end Supply Chain. However, as a professional Logistician, I believe OR tools are still the most useful tools available when you are working on solving some of the most complex logistics and transportation challenges.
Actually, rather than hindering the growth of Operations Research (OR) as a discipline, Big Data and advanced data mining technologies have rather acted as enablers to advance the field further. My perspective is that OR techniques can nicely fit within two of the three modern day analytics categories- within Prescriptive and Predictive analytics, as illustrated below. Logisticians these days have an edge as compared to folks who were in this profession decades ago. Even though logistics and transportation networks are becoming more complex and evolved as Supply chains get Global, the explosion in tools and algorithms that are available these days to capture and streamline data from your logistics and transportation network have made it easier to get better control on the data generated by your logistics network. Classic examples are the gigantic data pools that carriers like UPS and FedEx generate and collect by using GPS-enabled big data telematics- and then apply Operations Research techniques on this telematics data to determine the best routes to travel and to redesign their logistics network.
I can quote another example of advances in Big Data and computing technology making a logistics engineer’s life easier from my own experience. When I started my career as a Logistician years ago, I used tools like CPLEX Optimization studio to essentially write thousands of lines of codes of Linear programs pertaining to logistics and distribution network optimization problems. These days, I use an optimization software that reduces the time it takes to model, solve and analyze a logistics problem exponentially and that too with minimal coding. Though tools like CPLEX Studio and Gurobi are still useful and hardcore modelers love them (so do I), advancements in data science have definitely made the profession of OR more productive and interesting.
So to summarize it, while the analytics landscape has evolved, good old Operations Research has always been and will always remain the most important weapon in the arsenal of Logisticians who have to strategically plan and optimize their logistics and transportation operations. So for all the non-believers out there (including my friend)….Operations Research Still Rules!