---
_id: '60680'
abstract:
- lang: eng
text: "Classical machine learning techniques often struggle with overfitting and
unreliable predictions when exposed to novel conditions. Introducing causality
into the modelling process offers a promising way to mitigate these challenges
by enhancing predictive robustness. However, constructing an initial causal graph
manually using domain knowledge is time-consuming, particularly in complex time
series with numerous variables. To address this, causal discovery algorithms can
provide a preliminary causal structure that domain experts can refine. This study
investigates causal feature selection with domain knowledge using a data center
system as an example. We use simulated time-series data to compare \r\ndifferent
causal feature selection with traditional machine-learning feature selection methods.
Our results show that predictions based on causal features are more robust compared
to those derived from traditional methods. These findings underscore the potential
of combining causal discovery algorithms with human expertise to improve machine
learning applications."
author:
- first_name: David Ricardo
full_name: Zapata Gonzalez, David Ricardo
id: '105506'
last_name: Zapata Gonzalez
- first_name: Marcel
full_name: Meyer, Marcel
id: '105120'
last_name: Meyer
- first_name: Oliver
full_name: Müller, Oliver
id: '72849'
last_name: Müller
citation:
ama: 'Zapata Gonzalez DR, Meyer M, Müller O. Bridging the gap between data-driven
and theory-driven modelling – leveraging causal machine learning for integrative
modelling of dynamical systems. In: ; 2025.'
apa: Zapata Gonzalez, D. R., Meyer, M., & Müller, O. (2025). Bridging the
gap between data-driven and theory-driven modelling – leveraging causal machine
learning for integrative modelling of dynamical systems. European Conference
on Information Systems, Amman, Jordan.
bibtex: '@inproceedings{Zapata Gonzalez_Meyer_Müller_2025, title={Bridging the gap
between data-driven and theory-driven modelling – leveraging causal machine learning
for integrative modelling of dynamical systems}, author={Zapata Gonzalez, David
Ricardo and Meyer, Marcel and Müller, Oliver}, year={2025} }'
chicago: Zapata Gonzalez, David Ricardo, Marcel Meyer, and Oliver Müller. “Bridging
the Gap between Data-Driven and Theory-Driven Modelling – Leveraging Causal Machine
Learning for Integrative Modelling of Dynamical Systems,” 2025.
ieee: D. R. Zapata Gonzalez, M. Meyer, and O. Müller, “Bridging the gap between
data-driven and theory-driven modelling – leveraging causal machine learning for
integrative modelling of dynamical systems,” presented at the European Conference
on Information Systems, Amman, Jordan, 2025.
mla: Zapata Gonzalez, David Ricardo, et al. Bridging the Gap between Data-Driven
and Theory-Driven Modelling – Leveraging Causal Machine Learning for Integrative
Modelling of Dynamical Systems. 2025.
short: 'D.R. Zapata Gonzalez, M. Meyer, O. Müller, in: 2025.'
conference:
end_date: 18.06.2025
location: Amman, Jordan
name: European Conference on Information Systems
start_date: 16.06.2025
date_created: 2025-07-21T07:52:03Z
date_updated: 2025-07-22T06:30:37Z
department:
- _id: '196'
keyword:
- Causal Machine Learning
- Causality in Time Series
- Causal Discovery
- Human-Machine Collaboration
language:
- iso: eng
main_file_link:
- url: https://aisel.aisnet.org/ecis2025/bus_analytics/bus_analytics/2/
status: public
title: Bridging the gap between data-driven and theory-driven modelling – leveraging
causal machine learning for integrative modelling of dynamical systems
type: conference
user_id: '72849'
year: '2025'
...
---
_id: '37312'
abstract:
- lang: eng
text: Optimal decision making requires appropriate evaluation of advice. Recent
literature reports that algorithm aversion reduces the effectiveness of predictive
algorithms. However, it remains unclear how people recover from bad advice given
by an otherwise good advisor. Previous work has focused on algorithm aversion
at a single time point. We extend this work by examining successive decisions
in a time series forecasting task using an online between-subjects experiment
(N = 87). Our empirical results do not confirm algorithm aversion immediately
after bad advice. The estimated effect suggests an increasing algorithm appreciation
over time. Our work extends the current knowledge on algorithm aversion with insights
into how weight on advice is adjusted over consecutive tasks. Since most forecasting
tasks are not one-off decisions, this also has implications for practitioners.
author:
- first_name: Dirk
full_name: Leffrang, Dirk
id: '51271'
last_name: Leffrang
orcid: 0000-0001-9004-2391
- first_name: Kevin
full_name: Bösch, Kevin
last_name: Bösch
- first_name: Oliver
full_name: Müller, Oliver
id: '72849'
last_name: Müller
citation:
ama: 'Leffrang D, Bösch K, Müller O. Do People Recover from Algorithm Aversion?
An Experimental Study of Algorithm Aversion over Time. In: Hawaii International
Conference on System Sciences. ; 2023.'
apa: Leffrang, D., Bösch, K., & Müller, O. (2023). Do People Recover from Algorithm
Aversion? An Experimental Study of Algorithm Aversion over Time. Hawaii International
Conference on System Sciences. Hawaii International Conference on System Sciences.
bibtex: '@inproceedings{Leffrang_Bösch_Müller_2023, title={Do People Recover from
Algorithm Aversion? An Experimental Study of Algorithm Aversion over Time}, booktitle={Hawaii
International Conference on System Sciences}, author={Leffrang, Dirk and Bösch,
Kevin and Müller, Oliver}, year={2023} }'
chicago: Leffrang, Dirk, Kevin Bösch, and Oliver Müller. “Do People Recover from
Algorithm Aversion? An Experimental Study of Algorithm Aversion over Time.” In
Hawaii International Conference on System Sciences, 2023.
ieee: D. Leffrang, K. Bösch, and O. Müller, “Do People Recover from Algorithm Aversion?
An Experimental Study of Algorithm Aversion over Time,” presented at the Hawaii
International Conference on System Sciences, 2023.
mla: Leffrang, Dirk, et al. “Do People Recover from Algorithm Aversion? An Experimental
Study of Algorithm Aversion over Time.” Hawaii International Conference on
System Sciences, 2023.
short: 'D. Leffrang, K. Bösch, O. Müller, in: Hawaii International Conference on
System Sciences, 2023.'
conference:
name: Hawaii International Conference on System Sciences
date_created: 2023-01-18T10:53:51Z
date_updated: 2024-01-10T09:52:59Z
department:
- _id: '196'
keyword:
- Algorithm aversion
- Time series
- Decision making
- Advice taking
- Forecasting
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://scholarspace.manoa.hawaii.edu/items/62b58ddc-895c-48c3-8194-522a1758a26f
oa: '1'
publication: Hawaii International Conference on System Sciences
status: public
title: Do People Recover from Algorithm Aversion? An Experimental Study of Algorithm
Aversion over Time
type: conference
user_id: '51271'
year: '2023'
...
---
_id: '24547'
abstract:
- lang: eng
text: 'Over the last years, several approaches for the data-driven estimation of
expected possession value (EPV) in basketball and association football (soccer)
have been proposed. In this paper, we develop and evaluate PIVOT: the first such
framework for team handball. Accounting for the fast-paced, dynamic nature and
relative data scarcity of hand- ball, we propose a parsimonious end-to-end deep
learning architecture that relies solely on tracking data. This efficient approach
is capable of predicting the probability that a team will score within the near
future given the fine-grained spatio-temporal distribution of all players and
the ball over the last seconds of the game. Our experiments indicate that PIVOT
is able to produce accurate and calibrated probability estimates, even when trained
on a relatively small dataset. We also showcase two interactive applications of
PIVOT for valuing actual and counterfactual player decisions and actions in real-time.'
author:
- first_name: Oliver
full_name: Müller, Oliver
id: '72849'
last_name: Müller
- first_name: Matthew
full_name: Caron, Matthew
id: '60721'
last_name: Caron
- first_name: Michael
full_name: Döring, Michael
last_name: Döring
- first_name: Tim
full_name: Heuwinkel, Tim
last_name: Heuwinkel
- first_name: Jochen
full_name: Baumeister, Jochen
id: '46'
last_name: Baumeister
orcid: 0000-0003-2683-5826
citation:
ama: 'Müller O, Caron M, Döring M, Heuwinkel T, Baumeister J. PIVOT: A Parsimonious
End-to-End Learning Framework for Valuing Player Actions in Handball using Tracking
Data. In: 8th Workshop on Machine Learning and Data Mining for Sports Analytics
(ECML PKDD 2021).'
apa: 'Müller, O., Caron, M., Döring, M., Heuwinkel, T., & Baumeister, J. (n.d.).
PIVOT: A Parsimonious End-to-End Learning Framework for Valuing Player Actions
in Handball using Tracking Data. 8th Workshop on Machine Learning and Data
Mining for Sports Analytics (ECML PKDD 2021). European Conference on Machine
Learning and Principles and Practice of Knowledge Discovery (ECML PKDD 2021),
Online.'
bibtex: '@inproceedings{Müller_Caron_Döring_Heuwinkel_Baumeister, title={PIVOT:
A Parsimonious End-to-End Learning Framework for Valuing Player Actions in Handball
using Tracking Data}, booktitle={8th Workshop on Machine Learning and Data Mining
for Sports Analytics (ECML PKDD 2021)}, author={Müller, Oliver and Caron, Matthew
and Döring, Michael and Heuwinkel, Tim and Baumeister, Jochen} }'
chicago: 'Müller, Oliver, Matthew Caron, Michael Döring, Tim Heuwinkel, and Jochen
Baumeister. “PIVOT: A Parsimonious End-to-End Learning Framework for Valuing Player
Actions in Handball Using Tracking Data.” In 8th Workshop on Machine Learning
and Data Mining for Sports Analytics (ECML PKDD 2021), n.d.'
ieee: 'O. Müller, M. Caron, M. Döring, T. Heuwinkel, and J. Baumeister, “PIVOT:
A Parsimonious End-to-End Learning Framework for Valuing Player Actions in Handball
using Tracking Data,” presented at the European Conference on Machine Learning
and Principles and Practice of Knowledge Discovery (ECML PKDD 2021), Online.'
mla: 'Müller, Oliver, et al. “PIVOT: A Parsimonious End-to-End Learning Framework
for Valuing Player Actions in Handball Using Tracking Data.” 8th Workshop on
Machine Learning and Data Mining for Sports Analytics (ECML PKDD 2021).'
short: 'O. Müller, M. Caron, M. Döring, T. Heuwinkel, J. Baumeister, in: 8th Workshop
on Machine Learning and Data Mining for Sports Analytics (ECML PKDD 2021), n.d.'
conference:
end_date: 2021-09-17
location: Online
name: European Conference on Machine Learning and Principles and Practice of Knowledge
Discovery (ECML PKDD 2021)
start_date: 2021-09-13
date_created: 2021-09-16T08:33:04Z
date_updated: 2023-02-28T08:58:24Z
department:
- _id: '196'
- _id: '172'
keyword:
- expected possession value
- handball
- tracking data
- time series classification
- deep learning
language:
- iso: eng
main_file_link:
- url: https://dtai.cs.kuleuven.be/events/MLSA21/papers/MLSA21_paper_muller.pdf
publication: 8th Workshop on Machine Learning and Data Mining for Sports Analytics
(ECML PKDD 2021)
publication_status: inpress
status: public
title: 'PIVOT: A Parsimonious End-to-End Learning Framework for Valuing Player Actions
in Handball using Tracking Data'
type: conference
user_id: '60721'
year: '2021'
...
---
_id: '17810'
abstract:
- lang: eng
text: In all fields, the significance of a reliable and accurate predictive model
is almost unquantifiable. With deep domain knowledge, models derived from first
principles typically outperforms other models in terms of reliability and accuracy.
When it may become a cumbersome or an unachievable task to build or validate such
models of complex (non-linear) systems, machine learning techniques are employed
to build predictive models. However, the accuracy of such techniques is not only
dependent on the hyper-parameters of the chosen algorithm, but also on the amount
and quality of data. This paper investigates the application of classical time
series forecasting approaches for the reliable prognostics of technical systems,
where black box machine learning techniques might not successfully be employed
given insufficient amount of data and where first principles models are infeasible
due to lack of domain specific data. Forecasting by analogy, forecasting by analytical
function fitting, an exponential smoothing forecasting method and the long short-term
memory (LSTM) are evaluated and compared against the ground truth data. As a case
study, the methods are applied to predict future crack lengths of riveted aluminium
plates under cyclic loading. The performance of the predictive models is evaluated
based on error metrics leading to a proposal of when to apply which forecasting
approach.
author:
- first_name: Osarenren Kennedy
full_name: Aimiyekagbon, Osarenren Kennedy
id: '9557'
last_name: Aimiyekagbon
- first_name: Amelie
full_name: Bender, Amelie
id: '54290'
last_name: Bender
- first_name: Walter
full_name: Sextro, Walter
id: '21220'
last_name: Sextro
citation:
ama: 'Aimiyekagbon OK, Bender A, Sextro W. Evaluation of time series forecasting
approaches for the reliable crack length prediction of riveted aluminium plates
given insufficient data. In: PHM Society European Conference. Vol 5. ;
2020.'
apa: Aimiyekagbon, O. K., Bender, A., & Sextro, W. (2020). Evaluation of time
series forecasting approaches for the reliable crack length prediction of riveted
aluminium plates given insufficient data. PHM Society European Conference,
5(1).
bibtex: '@inproceedings{Aimiyekagbon_Bender_Sextro_2020, title={Evaluation of time
series forecasting approaches for the reliable crack length prediction of riveted
aluminium plates given insufficient data}, volume={5}, number={1}, booktitle={PHM
Society European Conference}, author={Aimiyekagbon, Osarenren Kennedy and Bender,
Amelie and Sextro, Walter}, year={2020} }'
chicago: Aimiyekagbon, Osarenren Kennedy, Amelie Bender, and Walter Sextro. “Evaluation
of Time Series Forecasting Approaches for the Reliable Crack Length Prediction
of Riveted Aluminium Plates given Insufficient Data.” In PHM Society European
Conference, Vol. 5, 2020.
ieee: O. K. Aimiyekagbon, A. Bender, and W. Sextro, “Evaluation of time series forecasting
approaches for the reliable crack length prediction of riveted aluminium plates
given insufficient data,” in PHM Society European Conference, 2020, vol.
5, no. 1.
mla: Aimiyekagbon, Osarenren Kennedy, et al. “Evaluation of Time Series Forecasting
Approaches for the Reliable Crack Length Prediction of Riveted Aluminium Plates
given Insufficient Data.” PHM Society European Conference, vol. 5, no.
1, 2020.
short: 'O.K. Aimiyekagbon, A. Bender, W. Sextro, in: PHM Society European Conference,
2020.'
date_created: 2020-08-11T13:32:40Z
date_updated: 2023-09-22T09:13:16Z
department:
- _id: '151'
intvolume: ' 5'
issue: '1'
keyword:
- PHM 2019
- crack propagation
- forecasting
- unevenly spaced time series
- step ahead prediction
- short time series
language:
- iso: eng
publication: PHM Society European Conference
quality_controlled: '1'
status: public
title: Evaluation of time series forecasting approaches for the reliable crack length
prediction of riveted aluminium plates given insufficient data
type: conference
user_id: '9557'
volume: 5
year: '2020'
...