[{"citation":{"bibtex":"@article{Kucklick_2023, title={HIEF: a holistic interpretability and explainability framework}, DOI={<a href=\"https://doi.org/10.1080/12460125.2023.2207268\">10.1080/12460125.2023.2207268</a>}, journal={Journal of Decision Systems}, publisher={Taylor &#38; Francis}, author={Kucklick, Jan-Peter}, year={2023}, pages={1–41} }","ama":"Kucklick J-P. HIEF: a holistic interpretability and explainability framework. <i>Journal of Decision Systems</i>. Published online 2023:1-41. doi:<a href=\"https://doi.org/10.1080/12460125.2023.2207268\">10.1080/12460125.2023.2207268</a>","mla":"Kucklick, Jan-Peter. “HIEF: A Holistic Interpretability and Explainability Framework.” <i>Journal of Decision Systems</i>, Taylor &#38; Francis, 2023, pp. 1–41, doi:<a href=\"https://doi.org/10.1080/12460125.2023.2207268\">10.1080/12460125.2023.2207268</a>.","short":"J.-P. Kucklick, Journal of Decision Systems (2023) 1–41.","chicago":"Kucklick, Jan-Peter. “HIEF: A Holistic Interpretability and Explainability Framework.” <i>Journal of Decision Systems</i>, 2023, 1–41. <a href=\"https://doi.org/10.1080/12460125.2023.2207268\">https://doi.org/10.1080/12460125.2023.2207268</a>.","ieee":"J.-P. Kucklick, “HIEF: a holistic interpretability and explainability framework,” <i>Journal of Decision Systems</i>, pp. 1–41, 2023, doi: <a href=\"https://doi.org/10.1080/12460125.2023.2207268\">10.1080/12460125.2023.2207268</a>.","apa":"Kucklick, J.-P. (2023). HIEF: a holistic interpretability and explainability framework. <i>Journal of Decision Systems</i>, 1–41. <a href=\"https://doi.org/10.1080/12460125.2023.2207268\">https://doi.org/10.1080/12460125.2023.2207268</a>"},"user_id":"77066","_id":"45299","publisher":"Taylor & Francis","page":"1-41","status":"public","department":[{"_id":"195"},{"_id":"196"}],"keyword":["Explainable AI (XAI)","machine learning","interpretability","real estate appraisal","framework","taxonomy"],"type":"journal_article","date_created":"2023-05-26T05:04:45Z","abstract":[{"text":"Many applications are driven by Machine Learning (ML) today. While complex ML models lead to an accurate prediction, their inner decision-making is obfuscated. However, especially for high-stakes decisions, interpretability and explainability of the model are necessary. Therefore, we develop a holistic interpretability and explainability framework (HIEF) to objectively describe and evaluate an intelligent system’s explainable AI (XAI) capacities. This guides data scientists to create more transparent models. To evaluate our framework, we analyse 50 real estate appraisal papers to ensure the robustness of HIEF. Additionally, we identify six typical types of intelligent systems, so-called archetypes, which range from explanatory to predictive, and demonstrate how researchers can use the framework to identify blind-spot topics in their domain. Finally, regarding comprehensiveness, we used a random sample of six intelligent systems and conducted an applicability check to provide external validity.","lang":"eng"}],"publication":"Journal of Decision Systems","doi":"10.1080/12460125.2023.2207268","language":[{"iso":"eng"}],"main_file_link":[{"url":"https://www.tandfonline.com/doi/full/10.1080/12460125.2023.2207268"}],"publication_status":"published","date_updated":"2023-05-26T05:08:36Z","publication_identifier":{"issn":["1246-0125","2116-7052"]},"author":[{"first_name":"Jan-Peter","last_name":"Kucklick","full_name":"Kucklick, Jan-Peter","id":"77066"}],"year":"2023","title":"HIEF: a holistic interpretability and explainability framework"},{"abstract":[{"lang":"eng","text":"Explainable Artificial Intelligence (XAI) is currently an important topic for the application of Machine Learning (ML) in high-stakes decision scenarios. Related research focuses on evaluating ML algorithms in terms of interpretability. However, providing a human understandable explanation of an intelligent system does not only relate to the used ML algorithm. The data and features used also have a considerable impact on interpretability. In this paper, we develop a taxonomy for describing XAI systems based on aspects about the algorithm and data. The proposed taxonomy gives researchers and practitioners opportunities to describe and evaluate current XAI systems with respect to interpretability and guides the future development of this class of systems."}],"publication":"Wirtschaftsinformatik 2022 Proceedings","citation":{"apa":"Kucklick, J.-P. (2022). Towards a model- and data-focused taxonomy of XAI systems. <i>Wirtschaftsinformatik 2022 Proceedings</i>. Wirtschaftsinformatik 2022 (WI22), Nürnberg (online).","mla":"Kucklick, Jan-Peter. “Towards a Model- and Data-Focused Taxonomy of XAI Systems.” <i>Wirtschaftsinformatik 2022 Proceedings</i>, 2022.","ieee":"J.-P. Kucklick, “Towards a model- and data-focused taxonomy of XAI systems,” presented at the Wirtschaftsinformatik 2022 (WI22), Nürnberg (online), 2022.","chicago":"Kucklick, Jan-Peter. “Towards a Model- and Data-Focused Taxonomy of XAI Systems.” In <i>Wirtschaftsinformatik 2022 Proceedings</i>, 2022.","short":"J.-P. Kucklick, in: Wirtschaftsinformatik 2022 Proceedings, 2022.","ama":"Kucklick J-P. Towards a model- and data-focused taxonomy of XAI systems. In: <i>Wirtschaftsinformatik 2022 Proceedings</i>. ; 2022.","bibtex":"@inproceedings{Kucklick_2022, title={Towards a model- and data-focused taxonomy of XAI systems}, booktitle={Wirtschaftsinformatik 2022 Proceedings}, author={Kucklick, Jan-Peter}, year={2022} }"},"type":"conference","keyword":["Explainable Artificial Intelligence","XAI","Interpretability","Decision Support Systems","Taxonomy"],"oa":"1","department":[{"_id":"195"},{"_id":"196"}],"date_created":"2022-01-26T08:22:03Z","date_updated":"2022-01-26T08:24:30Z","status":"public","title":"Towards a model- and data-focused taxonomy of XAI systems","year":"2022","conference":{"location":"Nürnberg (online)","start_date":"2022-02-21","name":"Wirtschaftsinformatik 2022 (WI22)","end_date":"2022-02-23"},"author":[{"id":"77066","full_name":"Kucklick, Jan-Peter","last_name":"Kucklick","first_name":"Jan-Peter"}],"user_id":"77066","main_file_link":[{"open_access":"1","url":"https://aisel.aisnet.org/cgi/viewcontent.cgi?article=1056&context=wi2022"}],"_id":"29539","language":[{"iso":"eng"}]},{"publication_identifier":{"issn":["2158-656X","2158-6578"]},"author":[{"first_name":"Jan-Peter","last_name":"Kucklick","full_name":"Kucklick, Jan-Peter","id":"77066"},{"id":"72849","full_name":"Müller, Oliver","first_name":"Oliver","last_name":"Müller"}],"year":"2022","title":"Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal","article_type":"original","publication_status":"published","date_updated":"2023-01-10T05:20:18Z","language":[{"iso":"eng"}],"main_file_link":[{"url":"https://dl.acm.org/doi/pdf/10.1145/3567430"}],"doi":"10.1145/3567430","publication":"ACM Transactions on Management Information Systems","abstract":[{"lang":"eng","text":"Deep learning models fuel many modern decision support systems, because they typically provide high predictive performance. Among other domains, deep learning is used in real-estate appraisal, where it allows to extend the analysis from hard facts only (e.g., size, age) to also consider more implicit information about the location or appearance of houses in the form of image data. However, one downside of deep learning models is their intransparent mechanic of decision making, which leads to a trade-off between accuracy and interpretability. This limits their applicability for tasks where a justification of the decision is necessary. Therefore, in this paper, we first combine different perspectives on interpretability into a multi-dimensional framework for a socio-technical perspective on explainable artificial intelligence. Second, we measure the performance gains of using multi-view deep learning which leverages additional image data (satellite images) for real estate appraisal. Third, we propose and test a novel post-hoc explainability method called Grad-Ram. This modified version of Grad-Cam mitigates the intransparency of convolutional neural networks (CNNs) for predicting continuous outcome variables. With this, we try to reduce the accuracy-interpretability trade-off of multi-view deep learning models. Our proposed network architecture outperforms traditional hedonic regression models by 34% in terms of MAE. Furthermore, we find that the used satellite images are the second most important predictor after square feet in our model and that the network learns interpretable patterns about the neighborhood structure and density."}],"date_created":"2023-01-10T05:16:02Z","department":[{"_id":"195"},{"_id":"196"}],"keyword":["Interpretability","Convolutional Neural Network","Accuracy-Interpretability Trade-Of","Real Estate Appraisal","Hedonic Pricing","Grad-Ram"],"type":"journal_article","status":"public","_id":"35620","publisher":"Association for Computing Machinery (ACM)","user_id":"77066","citation":{"chicago":"Kucklick, Jan-Peter, and Oliver Müller. “Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-Based Real Estate Appraisal.” <i>ACM Transactions on Management Information Systems</i>, 2022. <a href=\"https://doi.org/10.1145/3567430\">https://doi.org/10.1145/3567430</a>.","short":"J.-P. Kucklick, O. Müller, ACM Transactions on Management Information Systems (2022).","apa":"Kucklick, J.-P., &#38; Müller, O. (2022). Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal. <i>ACM Transactions on Management Information Systems</i>. <a href=\"https://doi.org/10.1145/3567430\">https://doi.org/10.1145/3567430</a>","ieee":"J.-P. Kucklick and O. Müller, “Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal,” <i>ACM Transactions on Management Information Systems</i>, 2022, doi: <a href=\"https://doi.org/10.1145/3567430\">10.1145/3567430</a>.","ama":"Kucklick J-P, Müller O. Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal. <i>ACM Transactions on Management Information Systems</i>. Published online 2022. doi:<a href=\"https://doi.org/10.1145/3567430\">10.1145/3567430</a>","bibtex":"@article{Kucklick_Müller_2022, title={Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal}, DOI={<a href=\"https://doi.org/10.1145/3567430\">10.1145/3567430</a>}, journal={ACM Transactions on Management Information Systems}, publisher={Association for Computing Machinery (ACM)}, author={Kucklick, Jan-Peter and Müller, Oliver}, year={2022} }","mla":"Kucklick, Jan-Peter, and Oliver Müller. “Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-Based Real Estate Appraisal.” <i>ACM Transactions on Management Information Systems</i>, Association for Computing Machinery (ACM), 2022, doi:<a href=\"https://doi.org/10.1145/3567430\">10.1145/3567430</a>."}}]