Design of an Artificial Neural Network battery for an optimal recognition of patterns in financial time series

Simone Fioribello () and Pier Giuseppe Giribone
Additional contact information
Simone Fioribello: Chartered Management Engineer, Italy
Pier Giuseppe Giribone: #x2020;Department of Economics, University of Genoa, 16126 Genova, Italy†CARIGE Bank, Financial Engineering, 16123 Genova, Italy

International Journal of Financial Engineering (IJFE), 2018, vol. 05, issue 04, 1-17

Abstract: The increasingly massive use of advanced Machine Learning methodologies in the financial field sector has led credit institutions to quickly move to new FinTech technologies. This paper deals with how a battery of Artificial Neural Networks (ANN), dedicated to the automatic recognition of financial patterns of potential interest to traders, can be designed and validated. The battery of neural networks that have been designed is composed of a shallow ANN, a deep ANN with ReLu, a deep ANN with Dropout and a convolutional network (ConvNet). Depending on the type of classification problem, the ANN battery dynamically recognizes the best classifier and makes use of it for pattern recognition. The first part of the paper describes how these technologies work, the second one performs a validation of the code and the third one suggests a technical analysis application on financial time series.

Keywords: Machine learning; artificial intelligence; classification problem; shallow neural networks; multi-layer neural networks; deep learning networks; convolutional neural networks; neural network battery; fintech; technical analysis (search for similar items in EconPapers)
Date: 2018
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S2424786318500317
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:ijfexx:v:05:y:2018:i:04:n:s2424786318500317

Ordering information: This journal article can be ordered from

DOI: 10.1142/S2424786318500317

Access Statistics for this article

International Journal of Financial Engineering (IJFE) is currently edited by George Yuan

More articles in International Journal of Financial Engineering (IJFE) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().