Presented by Issam Mazhoud, PhD, Solution Architect, DecisionBrain

In this talk, we draw lessons from a leading automotive supplier who adapted its manufacturing scheduling approaches to leverage optimization to effectively schedule and synchronize its injection and paint lines. The supplier’s production model involves a combination of make-to-order and just-in-time to fulfill the needs of its automotive customers. Using optimization techniques has led to improved service level and capacity usage. The presentation will concentrate on the challenges faced, as well as the methods and approaches used to address them.

14 APRIL 2023 WEBINAR RECORDING

14 APRIL 2023 WEBINAR PRESENTATION

EURO Practitioners’ Forum past and planned activities are available to the Forum members, as well as the wider public.

Visit the website and register as a member for free, to get the regular updates on all activities: EPF Member registration page. The recordings and details from previous webinars are also available on this website. Follow the Forum on X and LinkedIN , and feel free to get in touch.

Presented by Deeksha Sinha, Research Scientist at Meta

What tech lies behind the social media giants’ attempts to keep content ”within the rules”? At Meta, we have both hand-crafted and learned risk models to flag questionable content, for humans to review. To operationalize these, we aggregate the different models to give a single ranking score, calibrating them to prioritize more reliable risk models. But violation trends change over time, affecting which risk models are most reliable; risk models change; and novel models are introduced. To continuously update the system in response to such trends, we use a contextual bandit. Our approach increases Meta’s top-line metric for measuring the effectiveness of its content moderation strategy by 13%.

Presented by Vincent Gosselin (Co-founder, Taipy)

In the Python open-source eco-system, many packages are available that cater to:

– the building of great algorithms

– the visualization of data

– back-end functions

Despite this, over 85% of Data Science Pilots remain pilots and do not make it to the production stage.

In this tutorial talk, we will demonstrate the usage of the Taipy, a new open-source offering we developed. With Taipy, Data Scientists will be able to build great pilots as well as stunning production-ready applications for end-users.

Taipy provides two independent modules: Taipy GUI and Taipy Core.

1. Taipy-GUI goes way beyond the capabilities of the standard graphical stack.

2. Taipy Core provides a simple yet very powerful execution framework for Optimization execution pipelines.

We hope that this contribution will support an easier and faster adoption of the data science and operations research solutions by end users.

13 JANUARY 2023 WEBINAR RECORDING

13 JANUARY 2023 WEBINAR PRESENTATION

Presented by Ramunė Šabanienė, Data Strategy Director (Telia Finland)

Telia, as many large organisations faced continuous struggle with keeping up to date analytics infrastructure through mergers and acquisitions, as well as adopting data structures in line with ever increasing speed of changes in business. Having joined Telia Lithuania to lead the transformation, I will talk through the timeline, inputs used to draw strategy, re-thinking the talent management in light of better support of digitisation initiatives and finally – what it takes to execute Analytics Transformation in short timeline.

2 DECEMBER 2022 WEBINAR RECORDING

Presented by Dr. Leonard Heilig, Co-Founder and CTO (driveMybox)

Truck drayage is essential to link locations and logistics nodes in the port and hinterland. In the Port of Hamburg, for example, about 90% of inter-terminal transports are handled by truck and severely contribute to the road traffic volumes, carbon emissions and situation at gates. An intelligent and automated optimization of truck drayage operations can be the basis for a more efficient appointment booking and facilitates an eco-efficient utilization of trucking capacities, as well as for coordinating available truckers based on real-time information and the use of mobile trucker apps.

Previous research and a prototype called port-IO encouraged and impulsed the collaboration with EUROGATE Intermodal (EGIM), a leading drayage and intermodal transport provider in the Port of Hamburg (Germany), to develop an innovative decision support system for providing timely port-related truck operations. Besides developing efficient solution methods for solving rich vehicle routing problems, the dispatching system considered trailer swaps, truck appointment scheduling and multi-objective optimizations for covering emission-related objectives.

The practical project paved the way for the start-up driveMybox, which was founded in mid 2019. The cloud-based digital platform fully organizes containerized truck transports by establishing fully digital processes and by using AI at its core.

Since January 2020, container transports are fully managed by the platform, from the booking over the planning, optimization and execution to automated settlement. The platform is the first of its kind in the container logistics industry and transformed mainly paper-based processes into fully digital, transparent and optimized processes, where mathematical optimization, (meta-)heuristics and predictive analytics are used to further improve planing and operations. After a seven month beta phase and the final go-live in August 2020 (DVZ, 2020), the company transported thousands of containers and generated a multi-million turnover for 2021 (Hafen Hamburg, 2021). This year, new offices were opened in Milan (Italy) and Rotterdam to drive the expansion of the platform in Europe.

References

1. DVZ, 2020. driveMybox startet Plattform für Containertrucking. https://www.dvz.de/digitalisierung/startups/detail/news/drivemybox-startet-plattform-fuer-containertrucking.html

2. Hafen Hamburg, 2021. driveMybox: Digitale trucking-plattform startet Deutschlandweit durch. https://www.hafen-hamburg.de/de/presse/news/drivemybox-digitale-trucking-plattform-startet-deutschlandweit-durch–37110/

4 NOVEMBER 2022 WEBINAR RECORDING

Presented by Michaël Gabay, PhD (Director, Artelys)

Libra is the European platform for the activation and exchange of electricity reserves. The platform is used to select reserve offers for activation on replacement reserve (RR) and manual frequency restoration reserve markets (mFRR). At the center of the platform, an optimization algorithm is used to optimize the set of bids to activate in order to satisfy demands, maximize social welfare and compute the market clearing price while abiding by numerous market rules and taking into account many complex dimensions such as market coupling, time coupling, complex offers, etc.

Because of the criticality of the process, the market clearing algorithm has a very short time to run and must return a solution in all circumstances. Therefore, the optimization system must achieve very high performance and robustness.

After an introduction to the platform and its purpose, we will discuss the approach used to tackle this problem in practice and ensure meeting the performance and resilience goals.

WEBINAR RECORDING

Presented by Stefano Gualandi, Professor at the Department of Mathematics, University of Pavia

This seminar presents ongoing work on a joint project to develop a multimodal schedule-based routing application. This application is motivated by the necessity of transport policymakers to evaluate the potential impact of public transport investments at the national and European levels. In the first part of the seminar, we illustrate accessibility metrics that permit to evaluate the performance of a public transport system by combining the spatial distribution of the population of the region of interest with the average travel time between any pair of possible origin-destinations within that region. In the second part of the talk, we present Veloci-RAPTOR, the algorithm at the core of our multimodal schedule-based routing application that solves an all-pairs constrained path problem. We conclude with a perspective on ongoing activities.

WEBINAR RECORDING

Presented by Parvathy Krishnan, Lead Data Scientist

The Geospatial Planning & Budgeting Platform is being developed by researchers and practitioners from Analytics for a Better World Institute in close collaboration with World Bank.

These digital decision-support interfaces focus on promoting inclusive and resilient access to social and economic infrastructure services, including for health. The Geospatial Planning and Budgeting Platform (GPBP) provides users with online, interactive, and collaboration-friendly interfaces for powerful descriptive and prescriptive decision support. The GPBP user interfaces for any given problem statements (or “use-cases”) are presented in two forms:

(i) an interactive website for non-technical end-users,

(ii) a Jupyter Notebook environment that allows for exploratory and background analytics and visualization to be made more transparent and accessible.

In this talk, the overview of two GPBP use cases – Health Facility Location Optimisation in Timor Leste and Stroke Case Accessibility Optimization in Vietnam – will be explained. The challenges and opportunities of this platform along with potential extensions and the plans for the way forward will also be discussed.

1 JULY 2022 WEBINAR RECORDING

Presented by Prof. dr. Ger Koole (Vrije Universiteit Amsterdam)

In this talk, I will make a comparison between call centers and hospitals, from the point of view of operations management.

I will show how advanced prediction and optimization techniques impact call center operations and how academia and industry interact to move the field forward. We will compare this with the current state of our health care system, identify similarities and differences, and discuss what blocks further improvements in quality and efficiency.

About the speaker:

Ger Koole is full professor of business analytics and optimization at Vrije Universiteit Amsterdam. He is also founder and lead scientist of the call center workforce management company CCmath. He obtained his PhD at Leiden University in 1992 with theoretical work on the control of queueing systems.

Before moving to Amsterdam he held the postdoc positions at CWI and INRIA. Over the years, his interests moved to applications of optimization under uncertainty, especially in call centers, health care and revenue management.

WEBINAR RECORDING

Presented by Dr. Jason Atkin, Associate Professor (School of Computer Science, University of Nottingham)

Dr Jason Atkin is a member of the Computational Optimisation and Learning lab in the School of Computer Science at the University of Nottingham. He has been working with NATS and Heathrow airport since he started his PhD on the topic in late 2003. Although he has also worked on various other airport optimisation and modelling problems, his work has primarily been focusing on real-world runway sequencing at the airport, considering the ‘often messy’ real world constraints and characteristics of the problems. Having previously been a software engineer in industry, he applied various software engineering techniques to the challenge, which gives a somewhat different perspective to the usual academic approaches.

This talk will discuss the work with NATS and Heathrow, which contributed to Heathrow being able to predict take-off times accurately enough to gaining CDM compliance. Various versions of the problem will be discussed, introducing both the real world situation at Heathrow and considering the various academic simplifications that have sometimes been used for similar problems, and their implications in the real world. Ongoing work with Heathrow is still providing further enhancements and improvements over time.

WEBINAR RECORDING