Programme 2022

Programme of the Causal Data Science Meeting 2022, Nov 7–8.

All times are Central European Time. Use the worldtimebuddy to easily convert to your local time.

Affiliations correspond to the respective presenting author. Note on work-in-progress: Co-authors will be added.

Day 1 – November 07, 2022

TimePresentation
10:30Welcome
Paul Hünermund, Jermain Kaminski, Carla Schmitt, Beyers Louw
Copenhagen Business School & Maastricht University, DK & NL
10:40Session 1
Bounding counterfactuals under selection bias
Alessandro Antonucci
IDSIA, Lugano, CH
A proposed theoretical framework for retinal biomarkers
Ian MacCormick
Centre for Inflammation Research, University of Edinburgh, The Queen’s Medical Research Institute, UK
Quantitative probing: Validating causal models with quantitative domain knowledge
Daniel Grünbaum
OSRAM Group & University of Regensburg, DE
Leveraging causal relations to provide counterfactual explanations and feasible recommendations to end users
Riccardo Crupi
Intesa Sanpaolo, IT
11:5070 min break (click for timer)
13:00Session 2
The interventional Bayesian Gaussian equivalent score for Bayesian causal inference with unknown soft interventions
Giusi Moffa
Department of Mathematics and Computer Science, University of Basel, CH & Division of Psychiatry, University College London, London, UK
The importance of hyperparameter tuning in causal effect estimation
Damian Machlanski
Department of Computer Science and Electronic Engineering, University of Essex, UK
Testing the identification of causal effects in observational data
Jannis Kueck
University of Hamburg, Faculty of Business Administration, DE
Explainable Bayesian networks applied to transport vulnerability
Alta de Waal
Department of Statistics, University of Pretoria, SA & Centre for Artificial Intelligence Research (CAIR), SA
14:2030 min break (click for timer)
14:50Session 3
Benchpress: A scalable and versatile workflow for benchmarking structure learning algorithms
Jack Kuipers
ETH Zurich, CH
Differentiable causal discovery under latent interventions
Goncalo Faria
Instituto Superior Tecnico & LUMLIS (Lisbon ELLIS Unit), Universidade de Lisboa, PT
Learning Bayesian networks through Birkhoff polytope: A relaxation method
Aramayis Dallakyan
StataCorp, US
Image-based treatment effect heterogeneity
Connor Jerzak
University of Texas at Austin, Department of Government, US
16:1030 min break (click for timer)
16:40Session 4
Applying causal AI to industrial use cases
Stuart Frost
Geminos, US
A dynamic bayesian model for causal inference with mediation
Ho Kim
University of Missouri-St. Louis, US
Orthogonal policy learning under ambiguity
Riccardo d’Adamo
University College London, Department of Economics, UK
An open-source suite of causal AI tools and libraries
Emre Kiciman
Microsoft Research, US
18:0030 min break (click for timer)
18:30Keynote
Judea Pearl, UCLA
20:0030 min break (click for timer)
20:30Causal science in the industry: A roundtable with industry leaders
Moderator
Victor Zitian Chen
Director of Experimental Design and Causal Inference, Fidelity Investments
Panelists
Sathya Anand
Director of Data Science and Engineering, Netflix
Somit Gupta
Principal Data Scientist at Experimentation Platform, Microsoft
Mikael Konutgan
Software Engineering Manager at Experimentation Platform, Meta
Benjamin Skrainka
Data Science Manager in Experimentation, eBay
Eric Weber
Senior Director of Data Science, Experimentation, Causal Inference & Platform, Stitch Fix
YinYin Yu
Applied Research Manager, Experimentation & Causal Inference, LinkedIn
22:00End of day

Day 2 – November 08, 2022

TimePresentation
10:30Welcome
Paul Hünermund, Jermain Kaminski, Carla Schmitt, Beyers Louw
Copenhagen Business School & Maastricht University
10:40Session 1
Effect or treatment heterogeneity? Policy evaluation with aggregated and disaggregated treatments
Michael Knaus
University of Tübingen & IZA, Bonn, DE
Can causal graphs improve estimation with Double Machine Learning?
Patrick Rehill
Centre for Social Research and Methods, Australian National University, AU
So many choices in Double Machine Learning!? Practical insights from an extensive simulations study
Oliver Schacht
University of Hamburg, DE
How causal machine learning can leverage marketing strategies: Assessing and improving the performance of a coupon campaign
Henrika Langen
University of Helsinki, FI
11:5070 min break (click for timer)
13:00Session 2
A field experiment on attracting crowdfunders
Lars Hornuf
University of Bremen, Faculty of Business Studies and Economics, DE
Too casual causality: On the risks of comparing the ITCV to casual benchmarks in management research
Sirio Lonati
NEOMA Business School, FR
Fair policy learning from observational data
Dennis Frauen
Institute for AI in Management, LMU Munich, DE
Sophisticated consumers with inertia: Long-term implications from a large-scale field experiment
Klaus Miller
HEC Paris, FR
14:2030 min break (click for timer)
14:50Session 3
Political networking: Consequences for cross-border acquisitions of peer firms
Zhiyan Wu
Erasmus University, NL
Differences: A package for difference-in-differences with Python
Bernardo Dionisi
Fuqua School of Business, Duke University, US
Pricing algorithms, nursing homes, and Covid
Ben Tengelsen
IntelyCare, US
Structural causal modeling of managerial interventions: What if managers had not intervened by doing this?
Gwendolyn Lee
University of Florida, Warrington College of Business, US
16:1030 min break (click for timer)
16:40Session 4
Targeted learning in observational studies with multi-level treatments: an evaluation of antipsychotic drug treatment safety for patients with serious mental illnesses
Jason Poulos
Harvard Medical School, Department of Health Care Policy, US
Long story short: Omitted variable bias in causal machine learning
Carlos Cinelli
University of Washington, Department of Statistics, US
Ensure a/b test quality at scale with automated randomization validation and sample ratio mismatch detection
Zhang Zezhong
eBay, US
Exploiting selection bias on underspecified tasks in large language models
Emily McMilin
Independent Researcher, US
18:0030 min break (click for timer)
18:30Keynote
Silvia Chiappa, DeepMind & UCL
19:30End of day