TY - GEN AU - Koldewey, Christian AU - Dumitrescu, Roman AU - Rabe, Martin ID - 29149 T2 - Proceedings of the 55th Hawaii International Conference on System Sciences TI - Introduction to the Data-driven Services in Manufacturing Minitrack - Exploring Management, Engineering, and Organizational Transformation ER - TY - JOUR AU - Eke, Norbert ID - 29155 IS - 18 JF - Literatur in Westfalen. Beiträge zur Forschung. Hg. von Walter Gödden und Arnold Maxwill. TI - Blurred Lines. Der Reisende Michael Roes ER - TY - JOUR AU - Eke, Norbert ID - 29156 JF - Arbeitsbuch Judith Kuckart: Erzählen – Theater – Tanz. Hg. von Johanna Canaris und Stefan Elit. Berlin u.a.: TI - Schweigen, Erzählen (und Lieben). Judith Kuckarts Roman Lenas Liebe (2002) und seine Verfilmung Bittere Kirschen (2011) ER - TY - JOUR AU - Eke, Norbert ID - 29157 JF - Theater und Krise. Paradigmen der Störung in Dramentexten und Bühnenkonzepten nach 2000. Hg. von Marta Famula und Verena Witschel. TI - „Das Grundelement von Theater ist Verwandlung“. Heiner Müllers Idee des Theaters als Krise (und Störung). ER - TY - JOUR AU - Eke, Norbert ID - 29158 JF - Literatur in Westfalen. Beiträge zur Forschung 18. Hg. von Walter Gödden und Arnold Maxwill. TI - „Ich glaube, der Melancholiker ist jemand, der die Fremde lies, der sie nicht gestalten will und sich von ihr nicht gestalten lässt, sondern der sie wie ein Buch aufschlägt…“. Ein Gespräch mit Michael Roes. ER - TY - CONF AU - Schoormann, T. AU - Möller, F. AU - Szopinski, Daniel ID - 27280 T2 - Tagungsband der 17. Internationalen Tagung Wirtschaftsinformatik 2022 TI - Exploring purposes of using taxonomies ER - TY - CONF AU - Altenhöner, Reinhard AU - Dieckmann, Lisa AU - Münzmay, Andreas AU - Richts-Matthaei, Kristina AU - Röwenstrunk, Daniel AU - Stellmacher, Martha AU - Pratschke, Margarete AU - Primavesi, Patrick AU - Schulz, Christoph ID - 27461 TI - Kultur – Daten – Kuratierung: Was Speichern Wir Und Wozu? ER - TY - CONF AB - 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%. AU - Kucklick, Jan-Peter ID - 27506 KW - Explainable Artificial Intelligence (XAI) KW - Regression Activation Maps KW - Real Estate Appraisal KW - Convolutional Block Attention Module KW - Computer Vision T2 - 55th Annual Hawaii International Conference on System Sciences (HICSS-55) TI - Visual Interpretability of Image-based Real Estate Appraisal ER - TY - CONF AB - 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. AU - Heuwinkel, Tim AU - Kucklick, Jan-Peter AU - Müller, Oliver ID - 27507 KW - Real Estate Appraisal KW - Text Regression KW - Natural Language Processing (NLP) KW - Location Intelligence KW - Wikipedia T2 - 55th Annual Hawaii International Conference on System Sciences (HICSS-55) TI - Using Geolocated Text to Quantify Location in Real Estate Appraisal ER - TY - JOUR AU - Widhalm, Alex AU - Golla, Christian AU - Weber, Nils AU - Mackwitz, Peter AU - Zrenner, Artur AU - Meier, Cedrik ID - 29716 IS - 4 JF - Optics Express KW - Atomic and Molecular Physics KW - and Optics SN - 1094-4087 TI - Electric-field-induced second harmonic generation in silicon dioxide VL - 30 ER -