Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/316977 
Year of Publication: 
2024
Citation: 
[Journal:] Digital Finance [ISSN:] 2524-6186 [Volume:] 6 [Issue:] 3 [Publisher:] Springer International Publishing [Place:] Cham [Year:] 2024 [Pages:] 341-377
Publisher: 
Springer International Publishing, Cham
Abstract: 
Abstract This paper introduces custom neural network techniques to the problem of latent economic factor extraction for voluminous news analytics data. In the context of macro-financial news, we derive low-dimensional representations of time series that arise in textual sentiment analyses spanning various topics. We explore three applications for compressed news sentiment data: nowcasting GDP growth, explaining asset class returns in a panel data analysis, and time series momentum investment. Our empirical study shows that nonlinear data representations based on supervised autoencoder architectures compare favorably to alternatives across all applications. In specific, we demonstrate that augmenting autoencoders with supervision tasks based on common asset class returns and market characteristics disciplines the dimension reduction and naturally supports the transparency of resulting representations. Taken together, our findings position supervised autoencoders as attractive competitor models alongside PCA and PLS approaches.
Subjects: 
Neural networks
Sentiment analysis
Semi-structured data
Dimension reduction
Latent factor extraction
High-frequency macro-data
Persistent Identifier of the first edition: 
Additional Information: 
C45;C55;C58;C38
Creative Commons License: 
cc-by Logo
Document Type: 
Article
Document Version: 
Published Version
Appears in Collections:

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.