Home // ADVCOMP 2022, The Sixteenth International Conference on Advanced Engineering Computing and Applications in Sciences // View article

On the Proportional-Integral-Derivative Based Trading Algorithm under the Condition of the log-Normal Distribution of Stock Market Data

Authors:
Vadim Azhmyakov
Ilya Shirokov
Yuri Dernov
Luz Adriana Guzman Trujillo

Keywords: algorithmic trading, financial engineering, model-free PID control, statistical decision making

Abstract:
Our paper deals with a novel trading algorithm based on the conventional feedback control methodology. A profitable trading algorithm design for stock markets constitutes a very challenging problem of the modern financial engineering. We apply a model-free version of the classic Proportional-Integral-Derivative (PID) control to the modern Algorithmic Trading (AT). The proposed control theoretical application of the classic PID methodology is combined with a specific statistical information on the available historical stock market data. We consider a generic condition of the log-normal distribution of the available stock data. The log-normal property mentioned above implies a new efficient calibration rule for the gain coefficients (gains tuning) for the resulting PID type trading algorithm. We finally apply the developed PID based optimal AT strategy to a specific real-world example of the Binance Bitcoin / USD market. This application illustrates the effectiveness of the proposed trading algorithm.

Pages: 17 to 21

Copyright: Copyright (c) IARIA, 2022

Publication date: November 13, 2022

Published in: conference

ISSN: 2308-4499

ISBN: 978-1-61208-990-4

Location: Valencia, Spain

Dates: from November 13, 2022 to November 17, 2022