Machine learning in finance: A metadata-based systematic review of the literature

Machine learning in finance has been on the rise in the past decade. The applications of machine learning have become a promising methodological advancement. The paper's central goal is to use a metadata-based systematic literature review to map the current state of neural networks and machine...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of risk and financial management Jg. 14; H. 7; S. 1 - 31
Hauptverfasser: Warin, Thierry, Stojkov, Aleksandar
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI 01.07.2021
MDPI AG
Schlagworte:
Algorithms
Artificial intelligence
Datasets
Deep learning
efficient market hypothesis
Efficient markets
Keywords
Literature reviews
Machine learning
Metadata
network analysis
Neural networks
Scientometrics
Securities markets
sentiment analysis
Systematic review
ISSN:1911-8074, 1911-8066, 1911-8074
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Machine learning in finance has been on the rise in the past decade. The applications of machine learning have become a promising methodological advancement. The paper's central goal is to use a metadata-based systematic literature review to map the current state of neural networks and machine learning in the finance field. After collecting a large dataset comprised of 5053 documents, we conducted a computational systematic review of the academic finance literature intersected with neural network methodologies, with a limited focus on the documents' metadata. The output is a meta-analysis of the two-decade evolution and the current state of academic inquiries into financial concepts. Researchers will benefit from a mapping resulting from computational-based methods such as graph theory and natural language processing.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1911-8074
1911-8066
1911-8074
DOI:10.3390/jrfm14070302