On the profitability of scalping strategies based on neural networks

Authors:
Marina Resta
Affiliations:
DIEM sez. di Matematica Finanziaria, University of Genova, Genova, Italy
Venue:
KES'06 Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part III
Year:
2006

Citing 3
Cited 0

Self-organizing maps

Self-organizing maps
Statistical tools to assess the reliability of self-organizing maps

Neural Networks - New developments in self-organizing maps
Neural networks in financial engineering: a study in methodology

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We analyze the potential of unsupervised neural networks when they are employed to support intraday trading activity on financial markets. Several time frequencies have been considered: from five minutes to daily trades. At the current stage our major findings may be summarized as follows: a) unsupervised neural networks are helpful to localize profitable intraday patterns, and they make possible to achieve higher performances than common trading rules; b) trading strategies based on neural networks make exploitable with profits almost continuous trades (i.e. scalping), until transaction costs maintain below proper thresholds.