{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:47:23Z","timestamp":1772833643315,"version":"3.50.1"},"reference-count":58,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T00:00:00Z","timestamp":1673827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Manage. Inf. Syst."],"published-print":{"date-parts":[[2023,3,31]]},"abstract":"<jats:p>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 extending 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 article, 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 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.<\/jats:p>","DOI":"10.1145\/3567430","type":"journal-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T12:04:47Z","timestamp":1665403487000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["Tackling the Accuracy-Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal"],"prefix":"10.1145","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9091-396X","authenticated-orcid":false,"given":"Jan-Peter","family":"Kucklick","sequence":"first","affiliation":[{"name":"Paderborn University (UPB), Paderborn, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0369-1607","authenticated-orcid":false,"given":"Oliver","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Paderborn University (UPB), Paderborn, Germany"}]}],"member":"320","published-online":{"date-parts":[[2023,1,16]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.5555\/3327546.3327621"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/3327757.3327875"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00870"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.42"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533189"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_2_10_2","unstructured":"City of Asheville. 2018. Real estate appraisal residential building 2018. Retrieved from http:\/\/data-avl.opendata.arcgis.com\/datasets\/bunco::real-estate-appraisal-residential-building-201."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3359786"},{"key":"e_1_3_2_12_2","volume-title":"Proceedings of the 25th Americas Conference on Information Systems, Cancun, 2019","author":"Elnagar Samaa","year":"2019","unstructured":"Samaa Elnagar and Manoj A. Thomas. 2019. Real estate image-based appraisal using mask region based convolutional networks. In Proceedings of the 25th Americas Conference on Information Systems, Cancun, 2019. Association for Information Systems."},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2014.907095"},{"key":"e_1_3_2_15_2","unstructured":"Google LLC. 2022. Get a static map. Retrieved from https:\/\/developers.google.com\/maps\/documentation\/maps-static\/star."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.2307\/249487"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.25300\/MISQ\/2013\/37.2.01"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3236009"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay7120"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2013.01.001"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaf7894"},{"key":"e_1_3_2_23_2","first-page":"189","article-title":"The right to explanation, explained","volume":"34","author":"Kaminski Margot E.","year":"2019","unstructured":"Margot E. Kaminski. 2019. The right to explanation, explained. Berkeley Tech. Law J. 34 (2019), 189.","journal-title":"Berkeley Tech. Law J."},{"issue":"6","key":"e_1_3_2_24_2","doi-asserted-by":"crossref","first-page":"202","DOI":"10.3905\/jpm.2017.43.6.202","article-title":"Big data in real estate? From manual appraisal to automated valuation","volume":"43","author":"Kok Nils","year":"2017","unstructured":"Nils Kok, Eija-Leena Koponen, and Carmen Adriana Mart\u00ednez-Barbosa. 2017. Big data in real estate? From manual appraisal to automated valuation. J. Portfolio Manage. 43, 6 (2017), 202\u2013211.","journal-title":"J. Portfolio Manage."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2966890"},{"key":"e_1_3_2_26_2","volume-title":"Proceedings of the European Conference on Information Systems (ECIS\u201921)","author":"Kucklick Jan-Peter","year":"2021","unstructured":"Jan-Peter Kucklick, Jennifer M\u00fcller, Daniel Beverungen, and Oliver M\u00fcller. 2021. Quantifying the impact of location data in real estate appraisal\u2014A gis-based deep learning approach. In Proceedings of the European Conference on Information Systems (ECIS\u201921). Association for Information Systems."},{"key":"e_1_3_2_27_2","volume-title":"Proceedings of the AAAI Workshop on Knowledge Discovery from Unstructured Data in Financial Services (AAAI\u201921)Retrieved from https:\/\/aaai-kdf.github.io\/kdf2021\/assets\/pdfs\/KDF_21_paper_12.pdf","author":"Kucklick Jan-Peter","year":"2021","unstructured":"Jan-Peter Kucklick and Oliver M\u00fcller. 2021. A comparison of multi-view learning strategies for satellite image-based real estate appraisal. In Proceedings of the AAAI Workshop on Knowledge Discovery from Unstructured Data in Financial Services (AAAI\u201921). Association for the Advancement of Artifical Intelligence. Retrieved from https:\/\/aaai-kdf.github.io\/kdf2021\/assets\/pdfs\/KDF_21_paper_12.pdf."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1086\/259131"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3356471.3365238"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342240"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2872063"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbspro.2016.05.497"},{"key":"e_1_3_2_33_2"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"key":"e_1_3_2_35_2","first-page":"4765","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Lundberg Scott M.","year":"2017","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.). Curran Associates, 4765\u20134774. Retrieved from http:\/\/papers.nips.cc\/paper\/7062-a-unified-approach-to-interpreting-model-predictions.pdf."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-018-0304-0"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.25300\/MISQ\/2014\/38.1.04"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1108\/14635789710189227"},{"key":"e_1_3_2_39_2","unstructured":"Microsoft.2019. Get a static map. Retrieved from https:\/\/docs.microsoft.com\/en-us\/bingmaps\/rest-services\/imagery\/get-a-static-ma."},{"key":"e_1_3_2_40_2","volume-title":"Interpretable Machine Learning","author":"Molnar Christoph","year":"2019","unstructured":"Christoph Molnar. 2019. Interpretable Machine Learning. Lulu Press, Research Triangle, NC."},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380086"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbspro.2015.01.069"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-018-0922-2"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2021.3077875"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1086\/260169"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2599820"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330784"},{"key":"e_1_3_2_51_2","volume-title":"IEICE Conferences Archives","author":"Shimomura Masaki","year":"2020","unstructured":"Masaki Shimomura, Makoto Nakaune, Toru Yamada, Kazunori Tsukazawa, and Kazuyuki Nakamura. 2020. Crop yields prediction with CNN and visual explanation with Grad-RAM. In IEICE Conferences Archives. The Institute of Electronics, Information and Communication Engineers."},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449967"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6064"},{"key":"e_1_3_2_55_2","first-page":"514","volume-title":"Proceedings of the Workshops at the 32nd AAAI Conference on Artificial Intelligence","author":"Wang Zhiguang","year":"2018","unstructured":"Zhiguang Wang and Jianbo Yang. 2018. Diabetic retinopathy detection via deep convolutional networks for discriminative localization and visual explanation. In Proceedings of the Workshops at the 32nd AAAI Conference on Artificial Intelligence. Association for the Advancement of Artificial Intelligence, 514\u2013521."},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1304.5634"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.11227"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["ACM Transactions on Management Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3567430","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3567430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:43:46Z","timestamp":1750286626000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3567430"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,16]]},"references-count":58,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,3,31]]}},"alternative-id":["10.1145\/3567430"],"URL":"https:\/\/doi.org\/10.1145\/3567430","relation":{},"ISSN":["2158-656X","2158-6578"],"issn-type":[{"value":"2158-656X","type":"print"},{"value":"2158-6578","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,16]]},"assertion":[{"value":"2021-04-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-22","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}