Skip to main content

Bayesian Neural Networks for Bridging the Gap Between Machine Learning and Econometrics

Project description

Bayesian neural networks for better insight into markets

The complexity of financial data has rapidly expanded over the past two decades. This poses challenges for appropriate and effective tools for data analytics. Econometrics relies on parsimonious probabilistic models aimed at describing the economic phenomena. While it allows for models of great interpretability and excellent properties, it cannot upscale and embed the complexity of such modern data. Conversely, machine learning proved to be of high appeal for tackling a broad class of challenging multidimensional big-data problems. The EU-funded project BNNmetrics proposes to apply a class of ML methods known as Bayesian Neural Networks as a feasible tool for modern econometric research. This will significantly improve modelling processes, analyses and insights into the complexity of real markets.

Field of science

  • /social sciences/economics and business/economics/econometrics
  • /natural sciences/computer and information sciences/artificial intelligence/computational intelligence
  • /natural sciences/computer and information sciences/artificial intelligence/machine learning/deep learning
  • /social sciences/economics and business/business and management/commerce

Call for proposal

H2020-MSCA-IF-2019
See other projects for this call

Funding Scheme

MSCA-IF-EF-ST - Standard EF

Coordinator

AARHUS UNIVERSITET
Address
Nordre Ringgade 1
8000 Aarhus C
Denmark
Activity type
Higher or Secondary Education Establishments
EU contribution
€ 207 312