Social Science & Business Research Network

 Objective:

The field of Machine Learning (ML) appeared in the mid-50s mainly to create and deliver the “Learning” component on the (pioneering then) Artificial Intelligence (AI) systems. Its practical applications though, have been implemented without precedent in the last two decades. In between, ML followed the fate of AI and experienced long periods of low interest and funding (often referred to as “AI winters”). Nonetheless, the present period is quite different as the timing of recent technological advances of parallel computer processing (and soon quantum computing) and the inception of new ML structures (mainly expressed by Deep Learning) is ideal. These novel and innovative methodologies include Bayesian Networks, Recurrent Neural Networks, Convolutional Networks, Support Vector Machines, Boosting and Bagging Classifiers, etc.

In economics, such methodologies have been used mainly in forecasting financial time series where long datasets of high frequency and/or time length are widely available, and frequently outperformed the traditional econometrics methodologies in terms of forecasting accuracy. The application of ML in macroeconomics, nonetheless, as of today is rather limited. This is mainly due to the fact that the initial ML implementations (such as Neural Networks) required extensive data sets in order to be efficient in forecasting. Today, the use of many new ML architectures that do not demand unreasonably long data sets, is an interesting and very promising endeavor in macroeconomic forecasting. Recent relevant ML applications (i.e. in business cycles and recession forecasting) seem very successful as compared to traditional models. These new ML methodologies have some particularly attractive characteristics: a) not only the model parameters but also the model structure is derived automatically from the data, b) they impose no a priori assumptions, and c) they can approximate any continuous function.

The scope of this Special Issue is to publish state-of-the-art Machine Learning contributions in the areas of Economics and Finance. The contributions may be either in the methodologies employed or the unique and innovative application of these methodologies in these fields that provides new and significant empirical insight. The contributions that will be considered for publication in this MLEF Special Issue will belong in the broad field of Machine Learning.

Submission Deadline: 29 February 2020
Reviewing Deadline: 31 May 2020
Final Decision by: 30 June 2020

When submitting, in Step 4, please select the Special Issue:
“Machine Learning in Economics and Finance (MLEF)

Information online: https://www.springer.com/journal/10614/updates/17272156