Automatic Detection of Relevant Information, Predictions and Forecasts in Financial News through Topic Modelling with Latent Dirichlet Allocation
By Silvia García-Méndez, Francisco de Arriba-Pérez, Ana Barros-Vila, Francisco J. González-Castaño, Enrique Costa-Montenegro
Rating
1166
Battle Count: 82
Relevance
8/10
The system can be valuable for quantitative traders by automatically extracting relevant information and predictions from financial news, potentially improving decision-making processes and market analysis.
Implementation Complexity
7/10
The system involves multiple complex NLP techniques and machine learning models, requiring expertise in these areas for implementation. However, the authors provide detailed information about the methodology and implementation.
Reproducibility
4/5
The paper provides detailed information about the methodology, algorithms, and implementation details. However, the exact dataset is not publicly available.
About this paper
Methodology: Topic Modelling with Latent Dirichlet Allocation. Problem types: Natural Language Processing, Information Extraction, Text Classification, Topic Modeling.
The interactive Everscope explorer (charts, battles, favorites) loads below.