Welcome to the homepage of

Gui B. Liberali

Full Professor, RSM, Erasmus University
Researcher, Erasmus Medical Center
The Netherlands

Editorial Service, Conference Organizing Publications Recent Grants and Awards Invited Talks Code, Data, User Guides, and Demonstrations Teaching - Bandits/Reinforcement Learning, Analytics

Editorial Service, Conference Organizing

Guest Department Editor at Management Science, special issue on prescriptive analytics.

Vice-President for Membership at INFORMS Society of Marketing Science (ISMS), elected for the 2020/2021 and 2019/2018 terms.

Co-Chair of the Workshop on Multi-Armed Bandits and Learning Algorithms (May 2018).

ERIM Fellow, since 2018

Founder of the Erasmus Center for Optimization for Digital Experiments(eCode) at Rotterdam School of Management, Erasmus University.

Co-Editor of the Special Issue of IJRM - International Journal of Research in Marketing, on Marketing and Innovation.

Ad-Hoc reviewer for Marketing Science, Journal of Marketing Research and Management Science .

Member of the Editorial Review Board for IJRM.

Co-Chair of the first joint EMAC-AMA conference (Erasmus University, in 2014).

Scientific Committee of the 2013 Workshop on Distance Geometry and Applications.

Co-Founder of Erasmus Center for Marketing and Innovation (2010).

Coordinator of the ERIM Marketing Seminar Series at Erasmus University from 2010 to 2012.

Selected Publications, SIs and Editorials

"Morphing for Consumers Dynamics: Bandits Meet HMM", with Alina Ferecatu (2021). Marketing Science, forthcoming. Download draft

Kay Giesecke, Gui Liberali, Hamid Nazerzadeh, J. George Shanthikumar, Chung Piaw Teo (2018) Call for Papers - Management Science - Special Issue on Data-Driven Prescriptive Analytics. Management Science 64(6):2972-2972. https://doi.org/10.1287/mnsc.2018.3120

"Introduction to the IJRM Special Issue on Marketing and Innovation", with Eitan Muller, Roland Rust and Stefan Stremersch (2015). International Journal of Research in Marketing. Download

"Website Morphing 2.0: Switching Costs, Partial Exposure, Random Exit, and When to Morph", with John Hauser, Glen Urban (2014). Management Science. Download paper, data, demonstrations.

"Morphing Banner Advertising", with John Hauser, Glen Urban, Robert Bordley, Erin Mac Donald (2014). Marketing Science. Download paper

"Competitive Information, Trust, Brand Consideration and Sales: Two Field Experiments ", with John Hauser, Glen Urban (2013). International Journal of Research in Marketing. Download paper, appendices.

Lead article.

Finalist, Best 2013 IJRM paper award

Featured at MSI selections.

"Product Line Design Optimization" (2011). International Journal of Research in Marketing. Download .

Invited Commentary.

"Effects of Sensitization and Habituation in Durable Goods Markets", with Thomas Gruca and Walter Nique (2011). European Journal of Operational Research. Download paper,

"Website Morphing", with John Hauser, Glen Urban and Michael Braun (2009). Marketing Science. Download paper

Lead article with commentaries.

Finalist, John D. C. Little Award for Best Article published in Marketing Science and Management Science, 2009.

"Rejoinder and Response to Comments on Website Morphing" , with John Hauser, Glen Urban, and Michael Braun(2009). Marketing Science.

Response to comments by Hal Varian, Andrew Gelman, John Gittins

"Morphing the Web - Building Empathy, Trust, and Sales" , with Glen Urban, John Hauser, Michael Braun and Fareena Sultan (2009). MIT Sloan Management Review. Download paper

Recent Grants, Awards and Honors

Finalist, ISMS Long-Term Award, 2019, 2018 and 2017, Marketing Science

One of the Top 7% Reviewers of Marketing Science in 2014, Fastest Turnaround (>2 reviews), INFORMS, 2015

Top Talent Researcher, Erasmus School of Economics, 2013 (10,000 Euro award)

High-Performance Researcher of ERIM (Erasmus Research Institute of Management) for eight consecutive years

ERIM Research Grant for research on product category modeling (in 2011)

Marie Curie grant for research on optimization models for IPTV (European Union; 185,000 Euro in 2010)

2010 Finalist, John D.C. Little Best Paper Award, Marketing Science/Management Science

2009 Emerald Group Citation of Excellence, top 50 of 15,000 papers in management journals.

Invited Talks - in reverse chronological order

Marketing seminars
Pompeu Fabra (forthcoming), University of Southern California/USC, Stanford, IDC/Israel, Vrije Universiteit Amsterdam, Groeningen, INSEAD, MIT, Australian National University, Eindhoven University, UFRGS/Brazil, FGV/Brazil, University of Iowa

Seminars at non-marketing departments and non-business schools
Department of Cardiology at the Erasmus Medical Center (talk on adaptive trials, 2021), INSEAD (Decision Sciences), University of Amsterdam (Data Science and Operations), Carlos III/Madrid (Business Economics), Erasmus School of Economics

Marketing Camps and Retirement Symposiums
Marketing in Israel (research camp), Frankfurt School of Finance and Management (research camp), Tilburg University (research camp), MIT (Glen Urban Retirement Symposium)

Industry and Government
Trivago (Berlin), Conversion Hotel 2016, eBay Group Netherlands, Booking.com (Amsterdam), European Automotive Summit on Digital Personalization, Digital Data Tips Tuesday Meetup (Amsterdam), Dutch Marketing Online Association

Teaching - Courses on Multi-Armed Bandits, Optimization of Online Experiments

Reinforcement Learning. This is a PhD-level course on using machine learning methods to model and solve problems relevant to management science. In particular, those problems involving machines that autonomously make decisions on the behalf of the modeler, as in online settings. The course is based mainly on reinforcement learning (when we model states and transitions) and multi-armed bandits (when states are not modeled). Students design, solve, and implement learning methods for sequential decision-making under uncertainty. Sequential decision problems involve a trade-off between exploitation (acting on the information already collected) and exploration (gathering more information). These problems arise in many important domains, ranging from online advertising, clinical trials, website optimization, marketing campaign and revenue management.

Learning from Big Data. This is a hands-on undergraduate course on text analytics and online experiments. Bachelor students learn how to design, run, and analyze their own multi-armed bandit experiments using morphing-based algorithms.

Consumer-Centric Digital Transformation using Machine Learning. This MBA course introduces students to the most recent and relevant advances in machine learning that can be readily applied to improve the way companies relate with consumers. We will discuss how to use machine learning to learn from vast amounts of textual data (such as product reviews and tweets), and how to use machine learning and cognitive styles to deliver real-time personalization. We will also discuss tools and issues when transitioning organizations into a more customer-centric digital world. We will discuss the ethical boundaries and limitations of using machine learning and consumer data.

Using Business Analytics and Machine Learning for New Products. This course is focused on using statistics and machine learning tools to solve problems in the area of new product development (NPD). This involves offline problems (e.g., how to design a new product, how to measure value creation) as well as online problems (how machine learning can be deployed to, in real time, assess consumers styles, recommend online products, and communicate with them in a personalized, but computer-mediated way)

Code, Data, User Guides and Demonstrations

Website Morphing 2.0: Switching Costs, Partial Exposure, Random Exit, and When to Morph

Data and Supplemental Results

Site-Evaluation Suruga Data

Empirical Comparison of Outcomes in Suruga

Data from Suruga Bank (Figure 6)

Outcomes data in Suruga


Japanese with English Translations of Suruga Bank Questionnaires (section 6) - Calibration Study

Japanese with English Translations of Suruga Bank Questionnaires (section 6) - Experiment

Demonstrations and User Guide

Demonstration that fractional updating will likely converge from below (Appendix 2)

User Guide to Implementation of Morphing, Including When to Morph

Please also visit
- my webpage at the department website
- eCode, the Erasmus Center for Optimization of Digital Experiments
- my Google scholar page here