|
|
|
Abstract and Bio Keynote Speakers LNMB/NGB Seminar
Prof dr ir Jan Fransoo (Eindhoven University of Technology)Brief resume: Jan Fransoo is a professor of Operations Management and Logistics in the School of Industrial Engineering at Eindhoven University of Technology in the Netherlands. He holds an MSc in Industrial Engineering and a PhD in Operations Management & Logistics from Eindhoven University of Technology. He is also Research Director of the European Supply Chain Forum and Vice-President of the Dutch Institute for Advanced Logistics. He has held visiting position ns at a variety of universities in the US and Europe. As of February 1, he will be a visiting professor at the Massachusetts Institute of Technology. He serves on a number of editorial positions in international journals, and has published close to 60 peer reviewed papers in a variety of journals, including Management Science, Manufacturing & Service Operations Management , and European Journal of Operational Research. As part of his research and teaching activities, Jan Fransoo has worked with a large variety of companies, with an emphasis in the chemical, food, and pharmaceutical sectors.Title: Collaboration and coordination in supply chains
Abstract:
Once current theory is implemented in best practices,
the limits of efficiency and effectiveness are reached
within the boundaries of a company. Therefore, both horizontal
collaboration and vertical collaboration have received lots of
attention in both research and industry. In this talk, I will
provide an overview of horizontal and vertical collaboration in
supply chains, and make explicit how and where OR model play,
can play, or cannot play a role. The overview will be illustrated
by examples from industry.
Prof dr ir Geert-Jan van Houtum (Eindhoven University of Technology)Brief resume: Geert-Jan van Houtum is Professor of Maintenance, Reliability, and Quality at Eindhoven University of Technology since 2008. Prior to that he filled positions as assistant/associate professor at the University of Twente (1994-1998) and Eindhoven University of Technology (1999-2007). He obtained his M.Sc and Ph.D. degree in Applied Mathematics from Eindhoven University of Technology in 1990 and 1995, respectively. He is the scientific director of the Beta Research School for Operations Management and Logistics. His research is focused on: (i) Spare parts management; (ii) Maintenance and availability management of capital goods; (iii) The effect of design decisions on the total cost of ownership of capital goods. A significant part of this research is in collaboration with companies such as ASML, DAF, IBM, Nedtrain, Oce Technologies, Marel Stork, and Vanderlande Industries.Title: Planning and design of service supply chains for advanced capital goods
Abstract:
The maintenance of advanced capital goods is often in the hands
of the Original Equipment Manufacturer or a third party. They have
strict Service Level Agreements (SLA's) with the users of the equipment.
These agreements may specify the (average) time within which a failure
of a system has to be solved or within which a spare part has to be
provided. In this talk we focus on the spare parts provisioning and
in particular on the planning and design of networks of spare parts
stockpoints. While normal supply chains are focused on target service
levels of individual items, in service supply chains the focus is on
availability of the technical systems that are supported. Further,
it is important to have spare parts stocks at close distance of the
technical systems and to create pooling via lateral transshipments.
We explain these principles, and demonstrate them on the basis of
real-life cases.
Dr Marc Teerlink mba/mbi (IBM)Brief resume: Dr Marc Teerlink is een Global Strategist voor IBM als het gaat om onderwerpen zoals "Business Optimalizaion", "Business Analytics","Business Intelligence". Hij is actief binnen IBM's Global Center of Competence, Marc is een "sparring partner" and "thought leader" voor zowel US als Europese klanten en participeert in grote en complexe projecten. Voordat Marc zijn ervaring ging delen met klanten heeft hij ruim vier jaar binnen IBM's BI & Sales Transformation team gewerkt en leiding gegeven aan IBM's Consulting practices in Europa.Marc is ook verantwoordelijk voor een research project dat uitgevoerd wordt met een aantal toonaangevende internationale business scholen onder de titel "turning data into dollars", Zij verzamelen de ervaringen en best practices over hoe meer dan 1500 wereldwijde bedrijven hun klant/product gerelateerde information te gelden maken. Voordat Marc in 2001 bij IBM begon heeft hij 17 jaar gewerkt bij o.a. een internationale bank, als consultant binnen strategisch management, als sales transformatie manager in een telecommunicatie bedrijf en als Europees directeur bij een high-tech bedrijf dat zich bezig hield met klant-relatie technologieen. Marc heeft de afgelopen 15 jaar in verschillende landen gewoond en is recentelijk verhuist naar Nederland. Title: How Companies Are Turning Data into Dollars
Abstract:
Practical Cases and Lessons Learned about how
innovative companies are using data analytics to tap the voice of
the customer and how the age of web 2.0 and social media analytics
are changing Marketing and Marketing Optimization.
Wouter Egberink (KPN)Brief resume: Wouter Egberink is since 2008 Senior Customer Intelligence (CI) Analist with KPN and has 10 years experience in Marketing Intelligence. As CI analyst he is responsible for customer analyses and marketing evaluations. KPN uses the principle of fact based marketing. This implies that an integral client image is created in order to maximize the total Customer Lifetime Value (CLV).Title: Customer database analytics
Abstract:
KPN operates in the very dynamic telecom market of (mobile) telephone, internet (broadband, fiber)
and tv. This market has a high competitive character and is regulated (in the Netherlands) bij Opta,
Brussels and Privacy legislation. Moreover, the customer needs and wants vary substantially among
the individual clients. Technological innovations occur with high frequency and have high capital
consumption. Clearly, it is essential for KPN to have a very good understanding of the developments
of the customer s needs and wants and the market dynamics. Key success factors are the development
of a flexible customer database for Analytics, belief in fact based marketing from top management and
the competencies to translate complex analyses in concrete suggestions. We do this using the latest
analysis techniques such as social network analyses and marketing mix modeling.
Abstracts Invited and Contributed SpeakersJ.M. Bloemhof (Wageningen University)Title: The value of RFID technology enabled information to manage perishables
Abstract: We address the value of RFID technology enabled information to manage perishables in the
context of a retailer that sells a random lifetime product subject to stochastic demand and lost sales.
The product's lifetime is largely determined by the temperature history and the flow time through
the supply chain. We compare the case in which information on flow time and temperature history
is available and used for inventory management to a base case in which such information is not
available. We formulate the two cases as Markov Decision Processes and evaluate the value of
information through an extensive simulation using representative, real world supply chain parameters.
Cees Doets (Thales Nederland) and Rob Basten (Eindhoven University of Technology and Gordian Logistic Experts)Title: Optimal repair decisions and spare parts stock levels in a repair network
Abstract: For each of the components in a capital good, in our case a sensor system developed by
Thales Nederland, a failure pattern can be estimated. This is used in the so-called Level Of Repair
Analysis (LORA) to decide which components will be discarded upon failure and which ones will be
repaired. For the latter components, it is also decided where to perform the repairs (on board
of the naval vessel, at a base, or at Thales Nederland). After these tactical level decisions
are taken, it is decided where to stock spare parts in the network and in which amounts. This
is called the spare parts stocking problem, which is often solved using METRIC-type methods.
We propose a method to solve the joint problem of LORA and spare parts stocking, instead of
solving them sequentially as explained above. Using a case study at Thales Nederland, we show
that we can achieve a 10% cost reduction in this way, compared with the sequential method.
Such a cost reduction is worth millions of Euro's over the life cycle of a couple of sensor
systems.
René Haijema (Wageningen University)Title: Wageningen University : Teaching Markov Models to students Marketing and Consumer studies
Abstract: In this presentation the emphasize is on how to introduce the framework of Markov chains,
Markov reward chains, and Markov decision problems to students with an interest in Marketing and
Consumer studies. At the Wageningen University many subjects are taught in cooperation with other
chair groups. This to enrich each other's discipline and to put the disciplines in perspective of
each other. The Operational Research and Logistics group teaches theoretical subjects like the
simplex method and dynamic programming to students ranging from management and consumer studies
to agro and bio technologists. In this talk I explain how the Markov (reward) chains, and Markov
decision problems is taught to students. I discuss the challenges faced when teaching to non-OR
students and show some applications, exercises, solution techniques and how Excel is employed
to support the learning process. There will be room for some discussion on this topic.
Paul Hissink (Adtrackxys)Title: Adtrackxys: Zijn wiskundigen de toekomstige marketeers?
Abstract: Iedereen weet dat marketing- en reclameuitingen een grote dosis creativiteit en gevoel
bevatten. Dit geldt niet alleen voor het creatieproces van marketing uitingen (reclamebureau's),
maar ook voor alle overige disciplines binnen de marketingcommunicatie branche (marketeers,
mediabureaus, uitgeverijen etc). Deze wereld is echter drastisch aan het veranderen. Door de
toepassing van IT en wiskunde wordt (online) marketing niet alleen meer rendabel, maar ook
inzichtelijker en meer dynamisch gemaakt. En vooral ook toetsbaar. In plaats van aannames te
maken over doelgroepprofielen, stelt moderne optimalisatietechnologie ons in staat om deze
doelgroepprofielen zo verfijnd mogelijk te ontdekken. Algoritmiek neemt het over van menselijke
intuitie en ervaring. Aan de hand van diverse sprekende voorbeelden zal dit kruispunt tussen
wiskunde en marketing worden geschetst en deze vraag worden beantwoord: zijn de marketeers van
de toekomst wiskundigen?
Harald Hoogstrate (Pointlogic)Title: Point Logic : Fusing consumer surveys to allow cross media planning
Abstract: Media agencies assist advertisers with placing advertising. Which magazines are most
suitable to reach the relevant target audience? Which TV programs? Which online sites? Agencies
use survey data in order to optimize their planning. Most media have their own 'currency' survey
in which the reach of 'titles', 'programs' ,'websites' or 'outdoor objects' is measured. These
studies are very much focused around a single media at the time. They allow one to predict the
reach of a magazine campaign or a TV campaign, but they do not allow one to determine the reach
of the two together. As the studies are based on different respondents, it is not possible to
determine the overlap.
In today's advertising landscape, most advertising campaigns are multimedia and multimedia
reach measurement is a basic need. There are several approaches. One approach is to develop
a cross-media survey. Initiatives in this direction are project Apollo in the US (a huge
single-source study on media as well as purchase behavior) and the Touchpoint study in the
UK (and now starting in the US). However, since most media require active feedback from the
respondent to measure their reach, these studies miss the depth of the single-media studies.
Another (complementary) approach is to use quantitative techniques to combine the single-media
studies and to use the combined ('fused') data to estimate multimedia reach. We will discuss
two such approaches, an OR approach and a statistical approach.
Martin de Jong (Fokker Services) and Willem van Jaarsveld (Erasmus University Rotterdam)Title: Spare part inventory control for an aircraft component repair shop
Abstract: During aircraft maintenance, unserviceable components are removed from the aircraft
and sent to shops for repair. Only after an unserviceable component is inspected at the repair
shop, it becomes clear which specific spare parts are needed to repair the component. Because
airlines require short repair times of these components, spare parts that are used in
component repairs are often kept on stock at the repair shop.
In a recent project we have studied the inventory control of spare parts at such a repair
shop. This problem is complex, because the inventory decisions are made on a spare part level,
while availability constraints should reflect the requirements on the level of average repair
times for a specific component type. Because spare parts can often be used in the repair of
multiple component types, the inventory of the spare parts must be jointly optimized. We show
how to model this problem, and we discuss how we obtained the parameters for this model in
order to apply it in practice.
Because there are over 10000 spare parts and over 1000 components, the resulting optimization
problem is not trivial. We will shortly discuss the methodology used to solve this problem.
K.G.J. Pauls-Worm (Wageningen University)Title: Replenishment cycle policy parameters for a perishable item with non-stationary stochastic demand under service level constraints
Abstract: Inventory management of perishable products is one of the key challenges in the food
industry. The decision maker has to determine the timing and production quantity of each
replenishment, in order to minimise expected costs, guarantee a service level and avoid excessive
waste. We formulate a mixed-integer linear programming model to compute optimal replenishment
cycle policy parameters for an item with a fixed lifetime of any length and a stochastic
non-stationary demand under service level constraints. The model keeps track of the ages
of the items in stock and uses a FIFO policy
|
