Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal

article Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal published Jan-Peter Kucklick author 77066 Oliver Müller author 72849 195 department 196 department 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. Association for Computing Machinery (ACM)2022 eng InterpretabilityConvolutional Neural NetworkAccuracy-Interpretability Trade-OfReal Estate AppraisalHedonic PricingGrad-Ram ACM Transactions on Management Information Systems 2158-656X 2158-657810.1145/3567430 J.-P. Kucklick and O. Müller, “Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal,” ACM Transactions on Management Information Systems, 2022, doi: <a href="https://doi.org/10.1145/3567430">10.1145/3567430</a>. Kucklick, J.-P., & Müller, O. (2022). Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal. ACM Transactions on Management Information Systems. <a href="https://doi.org/10.1145/3567430">https://doi.org/10.1145/3567430</a> J.-P. Kucklick, O. Müller, ACM Transactions on Management Information Systems (2022). Kucklick, Jan-Peter, and Oliver Müller. “Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-Based Real Estate Appraisal.” ACM Transactions on Management Information Systems, 2022. <a href="https://doi.org/10.1145/3567430">https://doi.org/10.1145/3567430</a>. Kucklick, Jan-Peter, and Oliver Müller. “Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-Based Real Estate Appraisal.” ACM Transactions on Management Information Systems, Association for Computing Machinery (ACM), 2022, doi:<a href="https://doi.org/10.1145/3567430">10.1145/3567430</a>. @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} } Kucklick J-P, Müller O. Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal. ACM Transactions on Management Information Systems. Published online 2022. doi:<a href="https://doi.org/10.1145/3567430">10.1145/3567430</a> 356202023-01-10T05:16:02Z2023-01-10T05:20:18Z