English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

With the development of artificial intelligence,more and more financialpractitioners apply deep reinforcement learning to financial tradingstrategies.However,It is difficult to extract accurate features due to thecharacteristics of considerable noise,highly non-stationary,and non-linearityof single-scale time series,which makes it hard to obtain high returns.In thispaper,we extract a multi-scale feature matrix on multiple time scales offinancial time series,according to the classic financial theory-Chan Theory,andput forward to an approach of multi-scale stroke deep deterministic policygradient reinforcement learning model(MSSDDPG)to search for the optimal tradingstrategy.We carried out experiments on the datasets of the Dow Jones,S&P 500 ofU.S. stocks, and China's CSI 300,SSE Composite,evaluate the performance of ourapproach compared with turtle trading strategy, DeepQ-learning(DQN)reinforcement learning strategy,and deep deterministic policygradient (DDPG) reinforcement learning strategy.The result shows that ourapproach gets the best performance in China CSI 300,SSE Composite,and get anoutstanding result in Dow Jones,S&P 500 of U.S.

DDPG based on multi-scale strokes for financial time series trading strategy