A0603
Title: Bayesian identification of support and resistance levels in financial time series
Authors: Milan Ficura - University of Economics in Prague (Czech Republic) [presenting]
Jiri Witzany - University of Economics in Prague (Czech Republic)
Abstract: A methodology is presented for the Bayesian identification of Support \& Resistance (SR) levels in financial time series of asset prices. SR levels, commonly used by stock, forex and commodity traders, represent price levels at which large volumes of buy (or sell) orders are concentrated. This causes the asset price to get pushed away from these levels whenever it approaches them and the orders get executed. A methodology is proposed to test for the presence of SR levels in the asset price evolution, by using the Stochastic-Volatility Jump-Diffusion (SVJD) model framework. Specifically a modified SVJD model is proposed that allows for the presence of price levels at whose proximity the conditional drift of the price process becomes significantly different from the unconditional drift. The posterior distributions of the latent state variables and the parameters of the model, including the locations and the strength of the potential SR levels, are then estimated with the Bayesian Markov-Chain Monte-Carlo method. The analysis is performed on multiple assets and time periods with the results confirming the usefulness of SR levels for asset price modelling.
