This work concerns the optimization of a Trading Systems (TS) based on a small set of Technical Analysis (TA) indicators. Usually, in TA the values of the parameters (window lengths and thresholds) of these indicators are fixed by professional experience. Here, we propose to design the parametric configuration according to historical data, optimizing some performance measures subjected to proper constraints using a Particle Swarm Optimization-based metaheuristic. In particular, such an optimization procedure is applied to obtain both the optimal parameter values and the optimal weighting of the trading signals from the considered TA indicators, in order to provide an optimal trading decision. The use of a metaheuristic is necessary since the involved optimization problem is strongly nonlinear, nondifferentiable and mixed-integer. The proposed TS is optimized using the daily adjusted closing returns of seven Italian stocks coming from different industries and of two stock market indices.

Trading system mixed-integer optimization by PSO

Marco Corazza
;
Francesca Parpinel
;
Claudio Pizzi
2021-01-01

Abstract

This work concerns the optimization of a Trading Systems (TS) based on a small set of Technical Analysis (TA) indicators. Usually, in TA the values of the parameters (window lengths and thresholds) of these indicators are fixed by professional experience. Here, we propose to design the parametric configuration according to historical data, optimizing some performance measures subjected to proper constraints using a Particle Swarm Optimization-based metaheuristic. In particular, such an optimization procedure is applied to obtain both the optimal parameter values and the optimal weighting of the trading signals from the considered TA indicators, in order to provide an optimal trading decision. The use of a metaheuristic is necessary since the involved optimization problem is strongly nonlinear, nondifferentiable and mixed-integer. The proposed TS is optimized using the daily adjusted closing returns of seven Italian stocks coming from different industries and of two stock market indices.
2021
Mathematical and Statistical Methods for Actuarial Science and Finance. eMAF 2020
File in questo prodotto:
File Dimensione Formato  
2021-Corazza_Parpinel_Pizzi-Trading_system_mixed-integer_optimization_by_PSO-eMAF2020.pdf

non disponibili

Descrizione: Articolo nella versione dell'editore.
Tipologia: Versione dell'editore
Licenza: Accesso chiuso-personale
Dimensione 5.76 MB
Formato Adobe PDF
5.76 MB Adobe PDF   Visualizza/Apri

I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10278/3757012
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact