Skip to main navigation Skip to main content
info(at)avldigital.remove-this.de
Deutsch English
Last searches

Results for *

Displaying results 1 to 11 of 11.

  1. Towards accountability in machine learning applications
    a system-testing approach
    Author: Wan, Wayne Xinwei; Lindenthal, Thies
    Published: [2022]
    Publisher:  [Department of Land Economy, Environment, Law & Economics, University of Cambridge, Real Estate Research Centre], [Cambridge]

    Access:
    Verlag (kostenfrei)

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    ZSS 53
    Inter-library loan:
    No inter-library loan
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Series: Working paper series / Department of Land Economy, Environment, Law & Economics, University of Cambridge, Real Estate Research Centre ; no. 2022, 03
    Subjects: explainable machine learning; accountability gap; computer vision; real estate; urban studies
    Scope: 1 Online-Ressource (circa 62 Seiten), Illustrationen
  2. Towards accountability in machine learning applications
    a system-testing approach
    Author: Wan, Wayne Xinwei; Lindenthal, Thies
    Published: [2022]
    Publisher:  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... more

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

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 15
    Inter-library loan:
    No inter-library loan

    Location:
    Universitätsbibliothek Mannheim
    Inter-library loan:
    No inter-library loan

     

    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 to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/250385
    Series: Discussion paper / ZEW ; no. 22, 001 (01/2022)
    Subjects: machine learning; accountability gap; computer vision; real estate; urban studies
    Scope: 1 Online-Ressource (63 Seiten), Illustrationen
  3. Visual representation and stereotypes in news media
    Author: Ash, Elliott; Durante, Ruben; Grebenshchikova, Maria; Schwarz, Carlo
    Published: April 2022
    Publisher:  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.... more

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

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 63
    Inter-library loan:
    No inter-library loan

     

    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 to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/260816
    Series: CESifo working paper ; no. 9686 (2022)
    Subjects: stereotypes; gender; race; media; computer vision; text analysis
    Scope: 1 Online-Ressource (circa 46 Seiten), Illustrationen
  4. Machine learning, human experts, and the valuation of real assets
    Author: Aubry, Mathieu; Kräussl, Roman; Manso, Gustavo; Spaenjers, Christophe
    Published: [2019]
    Publisher:  Center for Financial Studies, Goethe University, Frankfurt am Main, Germany

    We study the accuracy and usefulness of automated (i.e., machine-generated) valuations for illiquid and heterogeneous real assets. We assemble a database of 1.1 million paintings auctioned between 2008 and 2015. We use a popular machine-learning... more

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

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 108
    Inter-library loan:
    No inter-library loan

     

    We study the accuracy and usefulness of automated (i.e., machine-generated) valuations for illiquid and heterogeneous real assets. We assemble a database of 1.1 million paintings auctioned between 2008 and 2015. We use a popular machine-learning technique - neural networks - to develop a pricing algorithm based on both non-visual and visual artwork characteristics. Our out-of-sample valuations predict auction prices dramatically better than valuations based on a standard hedonic pricing model. Moreover, they help explaining price levels and sale probabilities even after conditioning on auctioneers' pre-sale estimates. Machine learning is particularly helpful for assets that are associated with high price uncertainty. It can also correct human experts' systematic biases in expectations formation - and identify ex ante situations in which such biases are likely to arise.

     
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/206414
    Series: CFS working paper series ; no. 635
    Subjects: asset valuation; auctions; experts; big data; machine learning; computer vision; art
    Scope: 1 Online-Ressource (circa 38 Seiten), Illustrationen
  5. Predicting poverty using geospatial data in Thailand
    Author: Puttanapong, Nattapong; Martinez, Arturo M.; Addawe, Mildred; Bulan, Joseph; Durante, Ron Lester; Martillan, Marymell
    Published: [2020]
    Publisher:  Asian Development Bank, Metro Manila, Philippines

    Poverty statistics are conventionally compiled using data from household income and expenditure survey or living standards survey. This study examines an alternative approach in estimating poverty by investigating whether readily available geospatial... more

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

    Location:
    Max-Planck-Institut für ausländisches öffentliches Recht und Völkerrecht, Bibliothek
    Inter-library loan:
    No inter-library loan

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 496
    Inter-library loan:
    No inter-library loan

     

    Poverty statistics are conventionally compiled using data from household income and expenditure survey or living standards survey. This study examines an alternative approach in estimating poverty by investigating whether readily available geospatial data can accurately predict the spatial distribution of poverty in Thailand. In particular, geospatial data examined in this study include night light intensity, land cover, vegetation index, land surface temperature, built-up areas, and points of interest. The study also compares the predictive performance of various econometric and machine learning methods such as generalized least squares, neural network, random forest, and support vector regression. Results suggest that intensity of night lights and other variables that approximate population density are highly associated with the proportion of an area's population who are living in poverty. The random forest technique yielded the highest level of prediction accuracy among the methods considered in this study, perhaps due to its capability to fit complex association structures even with small and mediumsized datasets. Moving forward, additional studies are needed to investigate whether the relationships observed here remain stable over time, and therefore, may be used to approximate the prevalence of poverty for years when household surveys on income and expenditures are not conducted, but data on geospatial correlates of poverty are available.

     
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/246707
    Series: ADB economics working paper series ; no. 630 (December 2020)
    Subjects: big data; computer vision; data for development; machine learning algorithm; multidimensional poverty; official statistics; poverty; SDG; Thailand
    Scope: 1 Online-Ressource (circa 38 Seiten), Illustrationen
  6. Applying artificial intelligence on satellite imagery to compile granular poverty statistics
    Author: Hofer, Martin; Sako, Tomas; Martinez, Arturo; Addawe, Mildred; Bulan, Joseph; Durante, Ron Lester; Martillan, Marymell
    Published: [2020]
    Publisher:  Asian Development Bank, Metro Manila, Philippines

    The spatial granularity of poverty statistics can have a significant impact on the efficiency of targeting resources meant to improve the living conditions of the poor. However, achieving granularity typically requires increasing the sample sizes of... more

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

    Location:
    Max-Planck-Institut für ausländisches öffentliches Recht und Völkerrecht, Bibliothek
    Inter-library loan:
    No inter-library loan

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 496
    Inter-library loan:
    No inter-library loan

     

    The spatial granularity of poverty statistics can have a significant impact on the efficiency of targeting resources meant to improve the living conditions of the poor. However, achieving granularity typically requires increasing the sample sizes of surveys on household income and expenditure or living standards, an option that is not always practical for government agencies that conduct these surveys. Previous studies that examined the use of innovative (geospatial) data sources such as those from highresolution satellite imagery suggest that such method may be an alternative approach of producing granular poverty maps. This study outlines a computational framework to enhance the spatial granularity of government-published poverty estimates using a deep layer computer vision technique applied on publicly available medium-resolution satellite imagery, household surveys, and census data from the Philippines and Thailand. By doing so, the study explores a potentially more cost-effective alternative method for poverty estimation method. The results suggest that even using publicly accessible satellite imagery, in which the resolutions are not as fine as those in commercially sourced images, predictions generally aligned with the distributional structure of government-published poverty estimates, after calibration. The study further contributes to the existing literature by examining robustness of the resulting estimates to user-specified algorithmic parameters and model specifications.

     
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/246706
    Series: ADB economics working paper series ; no. 629 (December 2020)
    Subjects: big data; computer vision; data for development; machine learning algorithm; official statistics; poverty; SDG
    Scope: 1 Online-Ressource (circa 28 Seiten), Illustrationen
  7. Towards accountability in machine learning applications
    a system-testing approach
    Author: Wan, Wayne Xinwei; Lindenthal, Thies
    Published: 01/2022
    Publisher:  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... more

    Location:
    Niedersächsische Staats- und Universitätsbibliothek Göttingen
    Signature:
    2 : Z 2027:2022,001
    Inter-library loan:
    No inter-library loan

    Location:
    Badische Landesbibliothek
    Inter-library loan:
    Unlimited inter-library loan, copies and loan

     

    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 to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Print
    Series: Discussion paper / ZEW - Leibniz-Zentrum für Europäische Wirtschaftsforschung GmbH ; No. 22-001
    Subjects: machine learning; accountability gap; computer vision; real estate; urban studies
    Scope: 63 Seiten, Illustrationen, Diagramme
  8. Biased auctioneers
    Author: Aubry, Mathieu; Kräussl, Roman; Manso, Gustavo; Spaenjers, Christophe
    Published: [2022]
    Publisher:  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... more

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

    Location:
    Helmut-Schmidt-Universität, Universität der Bundeswehr Hamburg, Universitätsbibliothek
    Inter-library loan:
    No inter-library loan

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 108
    Inter-library loan:
    No inter-library loan

     

    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 to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/268894
    Edition: This version: January 6, 2022
    Series: CFS working paper series ; no. 692
    Subjects: art; auctions; experts; asset valuation; biases; machine learning; computer vision
    Other subjects: Array
    Scope: 1 Online-Ressource (circa 46 Seiten), Illustrationen
  9. Using machine learning to create a property tax roll
    evidence from the city of Kananga, DR Congo
    Author: Bergeron, Augustin; Fournier, Arnaud; Kabeya Kabeya, John; Tourek, Gabriel
    Published: November 2023
    Publisher:  The International Centre for Tax and Development at the Institute of Development Studies, Brighton, UK

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

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    Nicht speichern
    Inter-library loan:
    No inter-library loan
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Ebook
    Format: Online
    ISBN: 9781804701539
    Other identifier:
    Series: ICTD working paper ; 176
    Subjects: property tax; machine learning; Democratic Republic of Congo; computer vision; property valuation; state capacity
    Scope: 1 Online-Ressource (circa 33 Seiten), Illustrationen
  10. Demand estimation with text and image data
    Author: Compiani, Giovanni; Morozov, Ilya; Seiler, Stephan
    Published: October 2023
    Publisher:  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... more

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

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 63
    Inter-library loan:
    No inter-library loan

     

    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 to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/282383
    Series: CESifo working papers ; 10695 (2023)
    Subjects: demand estimation; unstructured data; computer vision; text models
    Scope: 1 Online-Ressource (circa 30 Seiten), Illustrationen
  11. Ikonographie und Interaktion. Computergestützte Analyse von Posen in Bildern der Heilsgeschichte
    Author: Bell, Peter; Impett, Leonardo

    Abstract: The last few years have seen an explosion of medieval images in digital form, chiefly as a result of photo-library and manuscript digitisation projects. An entire corpus of images, even selected solely by scene or iconography, becomes an... more

     

    Abstract: The last few years have seen an explosion of medieval images in digital form, chiefly as a result of photo-library and manuscript digitisation projects. An entire corpus of images, even selected solely by scene or iconography, becomes an unwieldy object of study by traditional art-historical means. This is even more the case for medieval images, where authorship and dating are often cloudy and unclear, and the image itself is in many cases the first resource for scholarly inquiry.We take the digital image – in particular, the digital image of the body – as our object of study in a wide-ranging computationally-augmented reading of an image-corpus; ours is made up of thousands of depictions of the ‘Annunciation’ and ‘Baptism’, selected not only for their primacy in Christian art but for their dialogical interaction. Our corpus of 6,564 ‘Annunciations’ and 883 ‘Baptisms’, whilst not necessarily representative in density, includes a wide range of stylistic, theological and historical tendencies.We computationally extract not only body images but poses, gestures and interactions. Such a range of gestures allows for a morphological treatment of bodily motifs, whose multi-dimensional, quantitative nature allows us to complicate and problematise iconographic taxonomies, populating the spaces between categories. Finally, our gestural manifolds provide a morphological pointer to dissecting the microtemporalities of the scenes, and their relative dynamics and inconsistencies.

     
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: German
    Media type: Article (journal)
    Format: Online
    Other identifier:
    Parent title:
    Enthalten in: Das Mittelalter; Heidelberg : Heidelberg University Publishing, 1996-; 24, Heft 1 (2019), 31-53 (gesamt 23); Online-Ressource
    Other subjects: computer vision; pose recognition; Christian iconography; art history; digital humanities
    Scope: Online-Ressource