Evolving trading strategies using directional changes

Abstract

The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record.

TSFDC: A trading strategy based on forecasting directional change

“…In 2017, Kampouridis and Otero () proposed a DC‐based trading strategy named ‘DC + GA’. DC + GA runs multiple DC summaries concurrently (using multiple thresholds).…”

“…For each DC summary, DC + GA keeps tracking the identification of corresponding DC or OS events. For each DC summary, DC + GA uses these DC and OS events jointly with some trading parameters (these parameters are reported in Table , page 151, (Kampouridis & Otero, )) to make a recommendation to buy or to sell. In other words, each DC summary is used, along with some trading parameters, to produce a buy, or sell, recommendation.…”

“…DC + GA runs N theta DC summaries concurrently (using N theta thresholds; where N theta is a parameter to be chosen by the investor). Each DC summary is associated with particular values of some trading parameters (see Table , page 151, Kampouridis & Otero, ). Each DC summary analyze the current price and uses its trading parameters to generate a buy or sell recommendation.…”

“…The evolution of the GA consists of finding the best set of DC thresholds along with their trading parameters and weights that maximize the total profits. The best set of DC's thresholds, and their associated weight and trading parameters, will be used for trading during the out‐of‐sample trading period (Kampouridis & Otero, ).…”

“…Kampouridis and Otero report the average monthly returns of applying DC + GA to five currency pairs (shown in Table Kampouridis & Otero, , page 158). We note that DC + GA incurs overall losses in two out of the five cases.…”