Direkt zur Hauptnavigation springen Direkt zum Inhalt springen
info(at)avldigital.remove-this.de
Deutsch English
Letzte Suchanfragen

Ergebnisse für *

Zeige Ergebnisse 1 bis 8 von 8.

  1. Towards accountability in machine learning applications
    a system-testing approach
    Autor*in: Wan, Wayne Xinwei; Lindenthal, Thies
    Erschienen: 01/2022
    Verlag:  ZEW, Mannheim

    A rapidly expanding universe of technology-focused startups is trying to change and improve the way real estate markets operate. The undisputed predictive power of machine learning (ML) models often plays a crucial role in the ‘disruption’ of... mehr

    Standort:
    Niedersächsische Staats- und Universitätsbibliothek Göttingen
    Signatur:
    2 : Z 2027:2022,001
    Fernleihe:
    keine Fernleihe

    Standort:
    Badische Landesbibliothek
    Fernleihe:
    uneingeschränkte Fernleihe, Kopie und Ausleihe

     

    A rapidly expanding universe of technology-focused startups is trying to change and improve the way real estate markets operate. The undisputed predictive power of machine learning (ML) models often plays a crucial role in the ‘disruption’ of traditional processes. However, an accountability gap prevails: How do the models arrive at their predictions? Do they do what we hope they do – or are corners cut? Training ML models is a software development process at heart. We suggest to follow a dedicated software testing framework and to verify that the ML model performs as intended. Illustratively, we augment two ML image classifiers with a system testing procedure based on local interpretable model-agnostic explanation (LIME) techniques. Analyzing the classifications sheds light on some of the factors that determine the behavior of the systems.

     
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: Verbundkataloge
    Sprache: Englisch
    Medientyp: Buch (Monographie)
    Format: Druck
    Schriftenreihe: Discussion paper / ZEW - Leibniz-Zentrum für Europäische Wirtschaftsforschung GmbH ; No. 22-001
    Schlagworte: machine learning; accountability gap; computer vision; real estate; urban studies
    Umfang: 63 Seiten, Illustrationen, Diagramme
  2. Visual representation and stereotypes in news media
    Autor*in: Ash, Elliott; Durante, Ruben; Grebenshchikova, Maria; Schwarz, Carlo
    Erschienen: April 2022
    Verlag:  CESifo, Center for Economic Studies & Ifo Institute, Munich, Germany

    We propose a new method for measuring gender and ethnic stereotypes in news reports. By combining computer vision and natural language processing tools, the method allows us to analyze both images and text as well as the interaction between the two.... mehr

    Zugang:
    Verlag (kostenfrei)
    Verlag (kostenfrei)
    Resolving-System (kostenfrei)

    Standort:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signatur:
    DS 63
    Fernleihe:
    keine Fernleihe

     

    We propose a new method for measuring gender and ethnic stereotypes in news reports. By combining computer vision and natural language processing tools, the method allows us to analyze both images and text as well as the interaction between the two. We apply this approach to over 2 million web articles published in the New York Times and Fox News between 2000 and 2020. We find that in both outlets, men and whites are generally over-represented relative to their population share, while women and Hispanics are under-represented. We also document that news content perpetuates common stereotypes such as associating Blacks and Hispanics with low-skill jobs, crime, and poverty, and Asians with high-skill jobs and science. For jobs, we show that the relationship between visual representation and racial stereotypes holds even after controlling for the actual share of a group in a given occupation. Finally, we find that group representation in the news is influenced by the gender and ethnic identity of authors and editors.

     
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: Verbundkataloge
    Sprache: Englisch
    Medientyp: Buch (Monographie)
    Format: Online
    Weitere Identifier:
    hdl: 10419/260816
    Schriftenreihe: CESifo working paper ; no. 9686 (2022)
    Schlagworte: stereotypes; gender; race; media; computer vision; text analysis
    Umfang: 1 Online-Ressource (circa 46 Seiten), Illustrationen
  3. Towards accountability in machine learning applications
    a system-testing approach
    Autor*in: Wan, Wayne Xinwei; Lindenthal, Thies
    Erschienen: [2022]
    Verlag:  ZEW - Leibniz Centre for European Economic Research, Mannheim, Germany

    A rapidly expanding universe of technology-focused startups is trying to change and improve the way real estate markets operate. The undisputed predictive power of machine learning (ML) models often plays a crucial role in the ‘disruption’ of... mehr

    Zugang:
    Verlag (kostenfrei)
    Verlag (kostenfrei)
    Verlag (kostenfrei)
    Resolving-System (kostenfrei)

    Standort:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signatur:
    DS 15
    Fernleihe:
    keine Fernleihe

    Standort:
    Universitätsbibliothek Mannheim
    Fernleihe:
    keine Fernleihe

     

    A rapidly expanding universe of technology-focused startups is trying to change and improve the way real estate markets operate. The undisputed predictive power of machine learning (ML) models often plays a crucial role in the ‘disruption’ of traditional processes. However, an accountability gap prevails: How do the models arrive at their predictions? Do they do what we hope they do – or are corners cut? Training ML models is a software development process at heart. We suggest to follow a dedicated software testing framework and to verify that the ML model performs as intended. Illustratively, we augment two ML image classifiers with a system testing procedure based on local interpretable model-agnostic explanation (LIME) techniques. Analyzing the classifications sheds light on some of the factors that determine the behavior of the systems.

     
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: Verbundkataloge
    Sprache: Englisch
    Medientyp: Buch (Monographie)
    Format: Online
    Weitere Identifier:
    hdl: 10419/250385
    Schriftenreihe: Discussion paper / ZEW ; no. 22, 001 (01/2022)
    Schlagworte: machine learning; accountability gap; computer vision; real estate; urban studies
    Umfang: 1 Online-Ressource (63 Seiten), Illustrationen
  4. Towards accountability in machine learning applications
    a system-testing approach
    Autor*in: Wan, Wayne Xinwei; Lindenthal, Thies
    Erschienen: [2022]
    Verlag:  [Department of Land Economy, Environment, Law & Economics, University of Cambridge, Real Estate Research Centre], [Cambridge]

    Zugang:
    Verlag (kostenfrei)

    Standort:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signatur:
    ZSS 53
    Fernleihe:
    keine Fernleihe
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: Verbundkataloge
    Sprache: Englisch
    Medientyp: Buch (Monographie)
    Format: Online
    Schriftenreihe: Working paper series / Department of Land Economy, Environment, Law & Economics, University of Cambridge, Real Estate Research Centre ; no. 2022, 03
    Schlagworte: explainable machine learning; accountability gap; computer vision; real estate; urban studies
    Umfang: 1 Online-Ressource (circa 62 Seiten), Illustrationen
  5. Biased auctioneers
    Autor*in: Aubry, Mathieu; Kräussl, Roman; Manso, Gustavo; Spaenjers, Christophe
    Erschienen: [2022]
    Verlag:  Center for Financial Studies, Goethe University, Frankfurt am Main, Germany

    We construct a neural network algorithm that generates price predictions for art at auction, relying on both visual and non-visual object characteristics. We find that higher automated valuations relative to auction house pre-sale estimates are... mehr

    Zugang:
    Verlag (kostenfrei)
    Verlag (kostenfrei)
    Resolving-System (kostenfrei)
    Resolving-System (kostenfrei)
    Resolving-System (kostenfrei)
    Resolving-System (kostenfrei)
    Verlag (kostenfrei)
    Verlag (kostenfrei)

    Standort:
    Helmut-Schmidt-Universität, Universität der Bundeswehr Hamburg, Universitätsbibliothek
    Fernleihe:
    keine Fernleihe

    Standort:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signatur:
    DS 108
    Fernleihe:
    keine Fernleihe

     

    We construct a neural network algorithm that generates price predictions for art at auction, relying on both visual and non-visual object characteristics. We find that higher automated valuations relative to auction house pre-sale estimates are associated with substantially higher price-to-estimate ratios and lower buy-in rates, pointing to estimates' informational inefficiency. The relative contribution of machine learning is higher for artists with less dispersed and lower average prices. Furthermore, we show that auctioneers' prediction errors are persistent both at the artist and at the auction house level, and hence directly predictable themselves using information on past errors.

     
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: Verbundkataloge
    Sprache: Englisch
    Medientyp: Buch (Monographie)
    Format: Online
    Weitere Identifier:
    hdl: 10419/268894
    Auflage/Ausgabe: This version: January 6, 2022
    Schriftenreihe: CFS working paper series ; no. 692
    Schlagworte: art; auctions; experts; asset valuation; biases; machine learning; computer vision
    Weitere Schlagworte: Array
    Umfang: 1 Online-Ressource (circa 46 Seiten), Illustrationen
  6. Computer Vision-Based Classification of Flow Regime and Vapor Quality in Vertical Two-Phase Flow
    Autor*in: Shai Kadish; David Schmid; Jarryd Son; Edward Boje
    Erschienen: 2022
    Verlag:  MDPI AG

    This paper presents a method to classify flow regime and vapor quality in vertical two-phase (vapor-liquid) flow, using a video of the flow as the input; this represents the first high-performing and entirely camera image-based method for the... mehr

     

    This paper presents a method to classify flow regime and vapor quality in vertical two-phase (vapor-liquid) flow, using a video of the flow as the input; this represents the first high-performing and entirely camera image-based method for the classification of a vertical flow regime (which is effective across a wide range of regimes) and the first image-based tool for estimating vapor quality. The approach makes use of computer vision techniques and deep learning to train a convolutional neural network (CNN), which is used for individual frame classification and image feature extraction, and a deep long short-term memory (LSTM) network, used to capture temporal information present in a sequence of image feature sets and to make a final vapor quality or flow regime classification. This novel architecture for two-phase flow studies achieves accurate flow regime and vapor quality classifications in a practical application to two-phase CO 2 flow in vertical tubes, based on offline data and an online prototype implementation, developed as a proof of concept for the use of these models within a feedback control loop. The use of automatically selected image features, produced by a CNN architecture in three distinct tasks comprising flow-image classification, flow-regime classification, and vapor quality prediction, confirms that these features are robust and useful, and offer a viable alternative to manually extracting image features for image-based flow studies. The successful application of the LSTM network reveals the significance of temporal information for image-based studies of two-phase flow.

     
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: BASE Fachausschnitt AVL
    Sprache: Englisch
    Medientyp: Aufsatz aus einer Zeitschrift
    Format: Online
    Übergeordneter Titel: Sensors, Vol 22, Iss 996, p 996 (2022)
    Schlagworte: flow regime; vapor quality; computer vision; machine learning; Chemical technology
  7. Demand estimation with text and image data
    Autor*in: Compiani, Giovanni; Morozov, Ilya; Seiler, Stephan
    Erschienen: October 2023
    Verlag:  CESifo, Munich, Germany

    We propose a demand estimation method that allows researchers to estimate substitution patterns from unstructured image and text data. We first employ a series of machine learning models to measure product similarity from products' images and textual... mehr

    Zugang:
    Verlag (kostenfrei)
    Verlag (kostenfrei)
    Resolving-System (kostenfrei)

    Standort:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signatur:
    DS 63
    Fernleihe:
    keine Fernleihe

     

    We propose a demand estimation method that allows researchers to estimate substitution patterns from unstructured image and text data. We first employ a series of machine learning models to measure product similarity from products' images and textual descriptions. We then estimate a nested logit model with product-pair specific nesting parameters that depend on the image and text similarities between products. Our framework does not require collecting product attributes for each category and can capture product similarity along dimensions that are hard to account for with observed attributes. We apply our method to a dataset describing the behavior of Amazon shoppers across several categories and show that incorporating texts and images in demand estimation helps us recover a flexible cross-price elasticity matrix.

     
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: Verbundkataloge
    Sprache: Englisch
    Medientyp: Buch (Monographie)
    Format: Online
    Weitere Identifier:
    hdl: 10419/282383
    Schriftenreihe: CESifo working papers ; 10695 (2023)
    Schlagworte: demand estimation; unstructured data; computer vision; text models
    Umfang: 1 Online-Ressource (circa 30 Seiten), Illustrationen
  8. Using machine learning to create a property tax roll
    evidence from the city of Kananga, DR Congo
    Autor*in: Bergeron, Augustin; Fournier, Arnaud; Kabeya Kabeya, John; Tourek, Gabriel
    Erschienen: November 2023
    Verlag:  The International Centre for Tax and Development at the Institute of Development Studies, Brighton, UK

    Zugang:
    Verlag (kostenfrei)
    Resolving-System (kostenfrei)

    Standort:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signatur:
    Nicht speichern
    Fernleihe:
    keine Fernleihe
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: Verbundkataloge
    Sprache: Englisch
    Medientyp: Ebook
    Format: Online
    ISBN: 9781804701539
    Weitere Identifier:
    Schriftenreihe: ICTD working paper ; 176
    Schlagworte: property tax; machine learning; Democratic Republic of Congo; computer vision; property valuation; state capacity
    Umfang: 1 Online-Ressource (circa 33 Seiten), Illustrationen