Welcome
Ravi Suman
I'm an Operations Research Consultant at American Airlines in the Operations Research and Advanced Analytics group where I support the Network Planning and Revenue team. I am responsible for making AI/ML/Optimization tools which are used to make strategic decisions for the company such as new destinations that we should fly, making alliance with different domestic and international airlines, pricing for our new routes, and improving on-time performance among others. I develop solutions at the valuable intersection of scientific discovery and business application.
I did my Phd from University of Wisconsin-Madison in Industrial and Systems Engineering with focus on Manufacturing Production Systems and Operations Research under Professor Ananth Krishnamurthy.
BS in Industrial Engineering, Indian Institute of Technology Kharagpur, 2015.
MS in Operations Research, UW-Madison
Minor in Computer Science, UW-Madison.
Research interest:
My research interests are in stochastic models and applied probability, focusing on the analysis, design, and control of stochastic systems, such as production system, supply chains, communication networks, and related resource control and risk management issues. My PhD thesis focuses on building stochastic models for queues, specially polling queues, and optimizing the manufacturing system where the production system resembles a tandem polling queues. I have worked on network of polling queues having exhaustive and gated service policies. As a part of my dissertation, I will be extending the work on polling queues to determine optimal policies for it using Markov Decision Process (MDP). I'm a member of INFORMS, IISE, IEEE, IJPR, and reviewer for IJPR and IEEE Transactions on Systems, Man, and Cybernetics.
Figure: A polling system.
The stochastic system that we analyzed is a network of polling queues with multiple products and multiple stations. We assume that external arrivals to the network follow a Poisson process, and that each station can be modeled as single server queue with exponentially distributed service times for each product. We develop a stochastic model to analyze this system and develop a procedure to estimate mean waiting times at each station under different service disciplines.
Figure: Tandem polling queue.
Recent publications and talks:
Research Assistant at the Center of Quick Response Manufacturing (QRM):
I was a research assistant at the center for Quick Response Manufacturing, I have worked on projects in collaboration with industries like ALCOA, CL&D Graphics, Cottrell, NOV, and Wacker Neuson. The main focus of these projects have been to streamline the manufacturing processes to reduce the lead time and minimize the on-hand inventory.
Some courses I have taken:
Introduction to stochastic process, stochastic modelling techniques, performance analysis of manufacturing system, Markov decision process
Introduction to optimization, linear optimization, heuristics for optimization, simulation, financial engineering, engineering supply chain models
Introduction to artificial intelligence, machine learning, design and analysis of algorithms, game theory
Ways to reach me:
Address: 1550 Engineering Drive, Madison, Wisconsin
Email id: rsuman@wisc.edu, rsuman@cs.wisc.edu
Link to my accounts: Google scholar, GitHub, LinkedIn