@article{45299, abstract = {{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.}}, author = {{Kucklick, Jan-Peter}}, issn = {{1246-0125}}, journal = {{Journal of Decision Systems}}, keywords = {{Explainable AI (XAI), machine learning, interpretability, real estate appraisal, framework, taxonomy}}, pages = {{1--41}}, publisher = {{Taylor & Francis}}, title = {{{HIEF: a holistic interpretability and explainability framework}}}, doi = {{10.1080/12460125.2023.2207268}}, year = {{2023}}, } @inproceedings{27506, abstract = {{Explainability for machine learning gets more and more important in high-stakes decisions like real estate appraisal. While traditional hedonic house pricing models are fed with hard information based on housing attributes, recently also soft information has been incorporated to increase the predictive performance. This soft information can be extracted from image data by complex models like Convolutional Neural Networks (CNNs). However, these are intransparent which excludes their use for high-stakes financial decisions. To overcome this limitation, we examine if a two-stage modeling approach can provide explainability. We combine visual interpretability by Regression Activation Maps (RAM) for the CNN and a linear regression for the overall prediction. Our experiments are based on 62.000 family homes in Philadelphia and the results indicate that the CNN learns aspects related to vegetation and quality aspects of the house from exterior images, improving the predictive accuracy of real estate appraisal by up to 5.4%.}}, author = {{Kucklick, Jan-Peter}}, booktitle = {{55th Annual Hawaii International Conference on System Sciences (HICSS-55)}}, keywords = {{Explainable Artificial Intelligence (XAI), Regression Activation Maps, Real Estate Appraisal, Convolutional Block Attention Module, Computer Vision}}, location = {{Virtual}}, title = {{{Visual Interpretability of Image-based Real Estate Appraisal}}}, year = {{2022}}, } @inproceedings{27507, abstract = {{Accurate real estate appraisal is essential in decision making processes of financial institutions, governments, and trending real estate platforms like Zillow. One of the most important factors of a property’s value is its location. However, creating accurate quantifications of location remains a challenge. While traditional approaches rely on Geographical Information Systems (GIS), recently unstructured data in form of images was incorporated in the appraisal process, but text data remains an untapped reservoir. Our study shows that using text data in form of geolocated Wikipedia articles can increase predictive performance over traditional GIS-based methods by 8.2% in spatial out-of-sample validation. A framework to automatically extract geographically weighted vector representations for text is established and used alongside traditional structural housing features to make predictions and to uncover local patterns on sale price for real estate transactions between 2015 and 2020 in Allegheny County, Pennsylvania.}}, author = {{Heuwinkel, Tim and Kucklick, Jan-Peter and Müller, Oliver}}, booktitle = {{55th Annual Hawaii International Conference on System Sciences (HICSS-55)}}, keywords = {{Real Estate Appraisal, Text Regression, Natural Language Processing (NLP), Location Intelligence, Wikipedia}}, location = {{Virtual}}, title = {{{Using Geolocated Text to Quantify Location in Real Estate Appraisal}}}, year = {{2022}}, } @inproceedings{29539, abstract = {{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.}}, author = {{Kucklick, Jan-Peter}}, booktitle = {{Wirtschaftsinformatik 2022 Proceedings}}, keywords = {{Explainable Artificial Intelligence, XAI, Interpretability, Decision Support Systems, Taxonomy}}, location = {{Nürnberg (online)}}, title = {{{Towards a model- and data-focused taxonomy of XAI systems}}}, year = {{2022}}, } @article{35620, abstract = {{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.}}, author = {{Kucklick, Jan-Peter and Müller, Oliver}}, issn = {{2158-656X}}, journal = {{ACM Transactions on Management Information Systems}}, keywords = {{Interpretability, Convolutional Neural Network, Accuracy-Interpretability Trade-Of, Real Estate Appraisal, Hedonic Pricing, Grad-Ram}}, publisher = {{Association for Computing Machinery (ACM)}}, title = {{{Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal}}}, doi = {{10.1145/3567430}}, year = {{2022}}, } @inproceedings{21204, author = {{Kucklick, Jan-Peter and Müller, Oliver}}, booktitle = {{ The AAAI-21 Workshop on Knowledge Discovery from Unstructured Data in Financial Services}}, title = {{{A Comparison of Multi-View Learning Strategies for Satellite Image-based Real Estate Appraisal}}}, year = {{2021}}, } @inproceedings{22514, author = {{Kucklick, Jan-Peter and Müller, Jennifer and Beverungen, Daniel and Müller, Oliver}}, booktitle = {{European Conference on Information Systems}}, location = {{Virtual}}, title = {{{Quantifying the Impact of Location Data for Real Estate Appraisal – A GIS-based Deep Learning Approach}}}, year = {{2021}}, } @inproceedings{17348, author = {{Kucklick, Jan-Peter and Müller, Oliver}}, booktitle = {{Symposium on Statistical Challenges in Electronic Commerce Research (SCECR)}}, title = {{{Location, location, location: Satellite image-based real-estate appraisal}}}, year = {{2020}}, } @inproceedings{35660, abstract = {{Effective customer loyalty programs are essential for every company. Small and medium sized brick-and- mortar stores, such as bakeries, butcher and flower shops, often share a common overarching loyalty program, organized by a third-party provider. Furthermore, these small shops have limited resources and often cannot afford complex BI tools. Out of these reasons we investigated how traditional brick-and- mortar stores can benefit from an expansion of service functionalities of a loyalty card provider. To answer this question, we cooperated with a cross-industry customer loyalty program in a polycentric region. The loyalty program was transformed from simple card-based solution to a mobile app for customers and a web- application for shop owners. The new solution offers additional BI services for performing data analytics and strengthening the position of brick-and-mortar stores. Participating shops can work together in order to increase sales and align marketing campaigns. Therefore, shopping data from 12 years, 55 shops, and 19,000 customers was analyzed.}}, author = {{Kucklick, Jan-Peter and Kamm, Michael Reiner and Schneider, Johannes and vom Brocke, Jan}}, booktitle = {{Proceedings of the 53rd Hawaii International Conference on System Sciences}}, keywords = {{brick-and-mortar stores, business intelligence, case study, loyalty program}}, title = {{{Extending Loyalty Programs with BI Functionalities A Case Study for Brick-and-Mortar Stores}}}, year = {{2020}}, } @article{35662, abstract = {{While the analysis and usage of data are increasing in importance, the application of sophisticated BI solutions in small stores is limited by available technical capabilities and financial resources. This study investigates how brick-and-mortar stores can benefit from an expansion of service functionalities of a cross-industry loyalty card provider. Digitalizing the loyalty program created new opportunities, while the analysis of shopping data of 13 years, 19,000 customers, and 55 shops empowered data-based decision support.}}, author = {{Kamm, Michael Reiner and Kucklick, Jan-Peter and Schneider, Johannes and vom Brocke, Jan}}, issn = {{1058-0530}}, journal = {{Information Systems Management}}, keywords = {{Customer loyalty, case study, brick-and-mortar stores, business intelligence, loyalty programs}}, number = {{4}}, pages = {{270--286}}, publisher = {{Informa UK Limited}}, title = {{{Data mining for small shops: Empowering brick-and-mortar stores through BI functionalities of a loyalty program1}}}, doi = {{10.1080/10580530.2020.1855486}}, volume = {{38}}, year = {{2020}}, }