dc.identifier.uri |
http://dx.doi.org/10.15488/17126 |
|
dc.identifier.uri |
https://www.repo.uni-hannover.de/handle/123456789/17254 |
|
dc.contributor.author |
Chen, Xia
|
|
dc.contributor.author |
Sun, Ruiji
|
|
dc.contributor.author |
Saluz, Ueli
|
|
dc.contributor.author |
Schiavon, Stefano
|
|
dc.contributor.author |
Geyer, Philipp
|
|
dc.date.accessioned |
2024-04-18T06:09:21Z |
|
dc.date.available |
2024-04-18T06:09:21Z |
|
dc.date.issued |
2024 |
|
dc.identifier.citation |
Chen, X.; Sun, R.; Saluz, U.; Schiavon, S.; Geyer, P.: Using causal inference to avoid fallouts in data-driven parametric analysis: A case study in the architecture, engineering, and construction industry. In: Developments in the Built Environment 17 (2024), 100296. DOI: https://doi.org/10.1016/j.dibe.2023.100296 |
|
dc.description.abstract |
The decision-making process in real-world implementations has been affected by a growing reliance on data-driven models. Recognizing the limitations of isolated methodologies - namely, the lack of domain understanding in data-driven models, the subjective nature of empirical knowledge, and the idealized assumptions in first-principles simulations, we explore their synergetic integration. We showed the potential risk of biased results when using data-driven models without causal analysis. Through a case study on energy consumption in building design, we demonstrate how causal analysis significantly enhances the modeling process, mitigating biases and spurious correlations. We concluded that: (a) Sole data-driven models' accuracy assessment or domain knowledge screening may not rule out biased and spurious results; (b) Data-driven models' feature selection should involve careful consideration of causal relationships, especially colliders; (c) Integrating causal analysis results aid to first-principles simulation design and parameter checking to avoid cognitive biases. We advocate for the routine integration of causal inference within data-driven models in engineering practices, emphasizing its critical role in ensuring the models' reliability and real-world applicability. |
eng |
dc.language.iso |
eng |
|
dc.publisher |
[Amsterdam] : Elsevier ScienceDirect |
|
dc.relation.ispartofseries |
Developments in the Built Environment 17 (2024) |
|
dc.rights |
CC BY-NC-ND 4.0 Unported |
|
dc.rights.uri |
https://creativecommons.org/licenses/by-nc-nd/4.0/ |
|
dc.subject |
Architecture, engineering, and construction industry |
eng |
dc.subject |
Biased outcomes |
eng |
dc.subject |
Building energy performance |
eng |
dc.subject |
Causal inference |
eng |
dc.subject |
Cognitive biases |
eng |
dc.subject |
Data-driven models |
eng |
dc.subject |
Domain knowledge |
eng |
dc.subject |
Feature selection |
eng |
dc.subject |
First-principles simulations |
eng |
dc.subject |
Machine learning methods |
eng |
dc.subject.ddc |
624 | Ingenieurbau und Umwelttechnik
|
|
dc.subject.ddc |
720 | Architektur
|
|
dc.title |
Using causal inference to avoid fallouts in data-driven parametric analysis: A case study in the architecture, engineering, and construction industry |
eng |
dc.type |
Article |
|
dc.type |
Text |
|
dc.relation.essn |
2666-1659 |
|
dc.relation.doi |
https://doi.org/10.1016/j.dibe.2023.100296 |
|
dc.bibliographicCitation.volume |
17 |
|
dc.bibliographicCitation.firstPage |
100296 |
|
dc.description.version |
publishedVersion |
eng |
tib.accessRights |
frei zug�nglich |
|
dc.bibliographicCitation.articleNumber |
100296 |
|