Supply Chain

Bernardo Almada-Lobo

INESC-TEC, Faculdade Engenharia Universidade Porto

Optimizing the Ship-pack of a Fresh-department Food Retailer

The definition of ship-packs – transportation unit from supplier to distribution center and then to stores – for all SKUs is an underestimated process that may have a large impact throughout the Supply chain.
This talk focuses on:

  • How to develop a comprehensive cost-based optimization model to define the ship-packs of a fresh-food retailer;
  • How to account for SC details and SKUs specificities to grasp the different cost terms;
  • The impact of ship-pack in the different KPIs and retail formats.

The model is holistic and has followed a bottom-up approach. It computes for a given ship-pack, costs carried at an individual SKU-store-weekly level. The model was implemented over 5k SKUs of fresh categories and has proposed changes for 25% of them. The decrease of the ship-packs may yield a 2% increase of the margin, whereas its increase may boost the margin of the respective products by 0.7%. (Manuel Pina Marques, Pedro Amorim, Luís Guimarães, Hugo Simões, Bernardo Almada-Lobo)


Associate Professor at the Industrial Engineering and Management Department – Faculty of Engineering of University of Porto; Head of the Industrial Engineering and Management Research Centre of the Associate Laboratory INESC-TEC; Vice-Director of the IBM Center of Advanced Studies Portugal (IBM-CAS); Co-founder of LTPlabs

Almada-Lobo’s main area of activity is Management Science/Operations Research. He develops and applies advanced analytical models and methods to help make better decisions, solving managerial problems in various domains (manufacturing, health, retail and mobility), with a special focus on Operations Management.

Current projects include production planning and scheduling; supply chain optimization; demand planning and forecasting; Reliability Engineering and Maintenance Management; Replenishment and allocation; human resources staffing and scheduling.

Back to schedule

Pan Chen

HAVI Global Solutions

Improving Network Utilization through Continuous Evaluation

In today’s fast-paced environment with consumer demands and product strategies changing based on a tweet or a snowstorm, additional flexibility and agility in the supply chain are more important than ever.  Pan and his team have developed an innovative approach to network optimization that can reinforce individual product strategies, achieve higher value, minimize risk, and better support business changes via more frequent evaluation.  In this presentation, HGS will discuss their unique approach which pairs Network Design with Network Utilization (effective asset management).  By reviewing case studies in the food service industry, Pan will illustrate how this approach solves common challenges like:

  • Network Optimization exercises done only once every 3-5 years can leave business exposed, unable to respond to ever-changing consumer demands, and can miss critical cost savings opportunities
  • The dynamic nature of the business, where the solution can be outdated shortly after implementation
  • The varying and different business strategies across product strategies


Pan Chen is a Senior Director in the Analytics & Supply Chain Services division of HAVI Global Solutions.  Pan has 15+ years of Analytics experience over multiple industry sectors, including Food Service, CPG, Financial Services, Automotive Industries and Management Consulting. At HGS, Pan is leading the Supply Chain Analytics practice, responsible for end-to-end supply chain visibility and optimization, integration between supply chain and marketing, as well as other innovation opportunities in supply chain related areas. Pan holds a Ph.D. in Operations Research from Cornell University, and a double B.Sc. in Computer Science and Mathematics from University of Victoria in Canada.

Back to schedule


Edward Cook

Capital One

Using Multi-stakeholder, Multi-objective Decision Analysis to Manage a Change Process

This talk describes a decision analysis to support the process of choosing the best way to roll out a complex software and process change across a 1000 branch network for a bank that impacted about 10,000 associates and several million customers. This talk and the underlying paper attempts to provide three contributions to decision analysis literature.

  • A broadly pertinent application of multi-object decision analysis for a complex set of objectives
  • A methodology that employs a balanced method for constructing scales with quantitative and qualitative objectives
  • A new method for assessing weights with a multi-stakeholder group of decision makers that employs a Proxy Swing Weights
  • A multi-objective, multi-stakeholder approach to decision making would pushes the underlying theory towards greater complexity but is reflective of typical large corporate decisions. Providing a practical solution to that multi-objective, multi-stakeholder decision that utilizes the theory is the aim of this paper and talk.


An executive with Capital One Bank with experience in IT, strategy, and operation analysis, Ed is currently focused on large change initiatives. Ed is also a Ph.D. candidate at Virginia Commonwealth University, pursuing a degree in Systems Modeling and Analysis with a focus on applying game theory to decisions that are multi-objective multi-decision-maker.

Back to schedule


Ilyas Iyoob


The Cloud IT Supply Chain

When Dell started building laptops on-demand instead of selling them prepackaged in stores, it was unorthodox at first. However, it turned out to be the biggest game changer in consumer electronics history. A similar phenomenon is starting to emerge in the Cloud Computing domain; information is procured on-demand as opposed to hosting data in physical data centers. All the entities responsible in successfully delivering this information in a timely manner collectively make up the ‘Cloud IT Supply Chain’. In this session, we will describe a case study where a large IT services organization approached us for help with reducing cost through cloud adoption. Using the supply chain analogy, we answered the following questions for them:

  1. Which apps should be moved to the cloud? – product portfolio optimization problem
  2. Which clouds would be ideal? – vendor selection problem
  3. How do we migrate while maintaining current operations? – scheduling problem


Dr. Ilyas Iyoob has pioneered the application of Operations Research to Cloud Computing. He is in the forefront of developing Cloud Analytics, which includes the algorithms for IT Supply Chain Optimization, Virtual Data Center Capacity Planning, and Automatic Scaling and Provisioning of Virtual Machines. He has spent over 10 years providing strategic and tactical decision support to the office of the CIO.

Dr. Iyoob holds multiple patents in Cloud Analytics, and many of his algorithms have been productized and are currently in use at a number of government agencies. He currently works as the Senior Research Scientist and Director of Advanced Analytics at Gravitant.

Back to schedule

Yanqi Xu

Princess Cruises

An Integrated Approach: Joint Optimization of Pricing, Revenue, and Marketing Decisions

Revenue optimization has been receiving increasing attention in various industries due to its top line improvement potential despite all the technical challenges in the accurate estimation of price elasticity. Frequently deriving the price elasticity information can be very difficult due to the fact that the sales volume typically has compounded effects from both pricing and the strength of natural demand for the product or service (seasonality, events). At the same time revenue optimization practice can also be complicated by other sales initiatives such as advertising. In this session, we will describe how to construct the building blocks of a basic revenue optimization model, and then on top of the basic model introduce a new methodology to simultaneously optimize pricing, and marketing decisions for much improved return on company’s assets. In this talk, the audience will learn:

  1. How to decode one of the best kept trade secrets in price and revenue optimization and accurately estimate price elasticity to quantify the relationship between prices you set and demand you get. Real world examples will be used to illustrate how to extract this valuable intelligence from the seemingly chaotic sales data, and set up and apply a basic revenue optimization model
  2. A new modeling methodology that integrates revenue optimization with other key company decisions (such as advertising spend) as well as company’s critical assets (customer loyalty), and achieves best possible decisions by simultaneously optimizing pricing and advertising spend. By comparing results from the basic revenue optimization model with the new integrated model, the audience will be able to see the profitability improvement potential of this integrated approach.
  3. We will present examples to illustrate the new approach, and we will show by how much pricing, advertising and customer loyalty impact the company’s profitability. In addition, we will also show the audience the interesting interactions between all the critical components, which will allow the managers to gain good insight into how activities of various functional departments and company’s assets can work together to drive the company’s profitability, and the best ways to leverage these factors to significantly improve revenue and profits.

The new integrated approach starts from discrete choice modeling and aggregates various detailed consumer level data to higher level so as to be able to jointly optimize company’s several related decisions for best profits. Therefore, in addition to improving ROI on company’s assets, because of its roots in the consumer level, this integrated model will allow the managers to understand their customers better. The integrated approach discussed in this talk demonstrates that the current technology should be capable of supporting the corporate world to break the silos and enable various departments to work coherently under the guidance of an integrated, unified plan for measurable and much improved profitability.

We will also discuss best practices and lessons learned in price and revenue optimization.


Yanqi Xu is director of Applied Technology at Princess Cruises. His analytics experience spans several industries and he has helped companies such as United Airlines, Avis and Princess Cruises make strides in improving revenue and profits by effectively leveraging state of the art analytics. He has a track record in developing award winning analytical models to support business needs in price and revenue optimization, statistical forecasting, large scale combinatorial optimization, marketing and customer analytics. Yanqi also has solid experience leading large analytics initiatives, and has successfully managed $12 million project budget and multiple teams. Yanqi received his M.S. in Industrial and Management Engineering from Rensselaer Polytechnic Institute, Troy, NY.

Back to schedule