{"main_file_link":[{"url":"https://www.tandfonline.com/doi/full/10.1080/12460125.2023.2207268"}],"publication_status":"published","department":[{"_id":"195"},{"_id":"196"}],"keyword":["Explainable AI (XAI)","machine learning","interpretability","real estate appraisal","framework","taxonomy"],"doi":"10.1080/12460125.2023.2207268","publication":"Journal of Decision Systems","publisher":"Taylor & Francis","date_created":"2023-05-26T05:04:45Z","citation":{"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>.","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>.","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>.","short":"J.-P. Kucklick, Journal of Decision Systems (2023) 1–41.","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>","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>"},"publication_identifier":{"issn":["1246-0125","2116-7052"]},"language":[{"iso":"eng"}],"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"}],"_id":"45299","year":"2023","user_id":"77066","type":"journal_article","title":"HIEF: a holistic interpretability and explainability framework","date_updated":"2023-05-26T05:08:36Z","status":"public","author":[{"full_name":"Kucklick, Jan-Peter","first_name":"Jan-Peter","last_name":"Kucklick","id":"77066"}],"page":"1-41"}