An Agent-based System for Issuing Stock Trading Signals

Zheyuan Su, Mirsad Hadzikadic

2015

Abstract

Simulation-based models are becoming a promising research tool in financial markets. A general Complex Adaptive System can be tailored to different application scenarios. This paper describes an application of a Complex Adaptive System-based agent model in stock trades signalling. The model has been evaluated using historical movement of Bank of America stock. Agents in the system are initialized using random decision rules. Genetic algorithms and machine learning methods are utilized to reduce the sample space and improve the decision rules. Final rules are generated via Monte Carlo simulation and modified with a market momentum estimate. By following the advice suggested by the model. The hypothetical investors have outperformed the S&P 500 index and buy-and-hold investors. Compared with benchmark agents with buy-and-hold strategy on stock and index respectively, the model achieved higher return even in periods of stock’s poor performance. The stock trade-signalling model is implemented using the Netlogo framework.

Paper Citation

in Harvard Style

Su Z. and Hadzikadic M. (2015). An Agent-based System for Issuing Stock Trading Signals . In Proceedings of the 5th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH, ISBN 978-989-758-120-5, pages 352-358. DOI: 10.5220/0005508203520358

in Bibtex Style

@conference{simultech15,
author={Zheyuan Su and Mirsad Hadzikadic},
title={An Agent-based System for Issuing Stock Trading Signals},
booktitle={Proceedings of the 5th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH,},
year={2015},
pages={352-358},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005508203520358},
isbn={978-989-758-120-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH,
TI - An Agent-based System for Issuing Stock Trading Signals
SN - 978-989-758-120-5
AU - Su Z.
AU - Hadzikadic M.
PY - 2015
SP - 352
EP - 358
DO - 10.5220/0005508203520358