Explainable AI for Tailored Electricity Consumption Feedback – An Experimental Evaluation of Visualizations





Faculty/Professorship: Information Systems and Energy Efficient Systems  
Author(s): Wastensteiner, Jacqueline; Weiss, Tobias M.; Haag, Felix ; Hopf, Konstantin  
Publisher Information: Bamberg : Otto-Friedrich-Universität
Year of publication: 2021
Pages: 1-19
Source/Other editions: 29. European Conference on Information Systems (ECIS), 2021, Marrakesh: Morocco / Virtual: ECIS 2021 Research Paper Proceedings, AIS electronic library
Language(s): English
DOI: 10.20378/irb-49912
Licence: Creative Commons - CC BY-SA - Attribution - ShareAlike 4.0 International 
URL: https://aisel.aisnet.org/ecis2021_rp/55/
URN: urn:nbn:de:bvb:473-irb-499123
Abstract: 
Machine learning (ML) methods can effectively analyse data, recognize patterns in them, and make high-quality predictions. Good predictions usually come along with “black-box” models that are unable to present the detected patterns in a human-readable way. Technical developments recently led to eXplainable Artificial Intelligence (XAI) techniques that aim to open such black-boxes and enable humans to gain new insights from detected patterns. We investigated the application of XAI in an area where specific insights can have a significant effect on consumer behaviour, namely electricity use. Knowing that specific feedback on individuals’ electricity consumption triggers resource conservation, we created five visualizations with ML and XAI methods from electricity consumption time series for highly personalized feedback, considering existing domain-specific design knowledge. Our experimental evaluation with 152 participants showed that humans can assimilate the pattern displayed by XAI visualizations, but such visualizations should follow known visualization patterns to be well-understood by users.
SWD Keywords: Intelligenter Zähler ; Künstliche Intelligenz ; Maschinelles Lernen ; Datenvisualisierung ; Energieeinsparung ; Rückmeldung
Keywords: eXplainable Artificial Intelligence, Visualizations, Energy Conservation, Machine Learning, Feedback.
DDC Classification: 004 Computer science  
330 Economics  
RVK Classification: ST 530   
Peer Reviewed: Ja
International Distribution: Ja
Document Type: Conferenceobject
URI: https://fis.uni-bamberg.de/handle/uniba/49912
Release Date: 16. June 2021
Project: Kombinierte Verhaltens- und Analyse-Innovation zur Steigerung der Energieeffizienz mittels Smart Meter in Privathaushalt; Teilprojekt: Maschinelle Lernverfahren für Energieeffizienz-Feedback

File Description SizeFormat  
fisba49912.pdf1.01 MBAdobe PDFView/Open