Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380927145> ?p ?o ?g. }
- W4380927145 endingPage "121321" @default.
- W4380927145 startingPage "121321" @default.
- W4380927145 abstract "Algorithmic trading plays a significant role in the trade of crude oil and natural gas futures. In this paper we propose a novel deep reinforcement learning (DRL) algorithm, dubbed two-branch deep Q-network (TBDQN), to automatically produce consistently profitable and robust trading signals in crude oil and natural gas futures markets. The first branch exploits long-short-term memory (LSTM) module to discover potential features hidden behind many technical indicators; the second branch extracts intrinsic features from futures contracts, trading positions and OHLCV using deep neural network. The extracted features are fused together to form the state vector of Q-leaning. In order to facilitate the training of the TBDQN model learning, we design a novel reward function by incorporating both immediate and long-term rewards. Compared to other popular methods, the proposed algorithm demonstrates excellent performance on the evaluation criteria of annualized return and Sharpe ratio in the oil and gas futures markets, which proves the effectiveness of our method." @default.
- W4380927145 created "2023-06-17" @default.
- W4380927145 creator A5024882473 @default.
- W4380927145 creator A5039141051 @default.
- W4380927145 creator A5039543260 @default.
- W4380927145 date "2023-10-01" @default.
- W4380927145 modified "2023-10-14" @default.
- W4380927145 title "TBDQN: A novel two-branch deep Q-network for crude oil and natural gas futures trading" @default.
- W4380927145 cites W1977838234 @default.
- W4380927145 cites W1982346081 @default.
- W4380927145 cites W1992857537 @default.
- W4380927145 cites W1995236272 @default.
- W4380927145 cites W1999996900 @default.
- W4380927145 cites W2020064457 @default.
- W4380927145 cites W2032876243 @default.
- W4380927145 cites W2075661246 @default.
- W4380927145 cites W2101544483 @default.
- W4380927145 cites W2109510860 @default.
- W4380927145 cites W2119112357 @default.
- W4380927145 cites W2128728535 @default.
- W4380927145 cites W2154368556 @default.
- W4380927145 cites W2468860014 @default.
- W4380927145 cites W2610600445 @default.
- W4380927145 cites W2746553466 @default.
- W4380927145 cites W2793864397 @default.
- W4380927145 cites W2802180511 @default.
- W4380927145 cites W2923276499 @default.
- W4380927145 cites W2947621381 @default.
- W4380927145 cites W2966035953 @default.
- W4380927145 cites W3007690081 @default.
- W4380927145 cites W3031552882 @default.
- W4380927145 cites W3081889057 @default.
- W4380927145 cites W3113503753 @default.
- W4380927145 cites W3123095408 @default.
- W4380927145 cites W3126577088 @default.
- W4380927145 cites W3192412192 @default.
- W4380927145 cites W3199351510 @default.
- W4380927145 cites W3214475726 @default.
- W4380927145 cites W4200351803 @default.
- W4380927145 cites W4210695383 @default.
- W4380927145 cites W4225163341 @default.
- W4380927145 cites W4248217291 @default.
- W4380927145 cites W4292491451 @default.
- W4380927145 cites W4313420296 @default.
- W4380927145 doi "https://doi.org/10.1016/j.apenergy.2023.121321" @default.
- W4380927145 hasPublicationYear "2023" @default.
- W4380927145 type Work @default.
- W4380927145 citedByCount "1" @default.
- W4380927145 crossrefType "journal-article" @default.
- W4380927145 hasAuthorship W4380927145A5024882473 @default.
- W4380927145 hasAuthorship W4380927145A5039141051 @default.
- W4380927145 hasAuthorship W4380927145A5039543260 @default.
- W4380927145 hasConcept C10138342 @default.
- W4380927145 hasConcept C106159729 @default.
- W4380927145 hasConcept C106306483 @default.
- W4380927145 hasConcept C108583219 @default.
- W4380927145 hasConcept C127413603 @default.
- W4380927145 hasConcept C139938925 @default.
- W4380927145 hasConcept C14036430 @default.
- W4380927145 hasConcept C154945302 @default.
- W4380927145 hasConcept C162324750 @default.
- W4380927145 hasConcept C182306322 @default.
- W4380927145 hasConcept C188116033 @default.
- W4380927145 hasConcept C2780821815 @default.
- W4380927145 hasConcept C2987168347 @default.
- W4380927145 hasConcept C41008148 @default.
- W4380927145 hasConcept C50644808 @default.
- W4380927145 hasConcept C548081761 @default.
- W4380927145 hasConcept C59427239 @default.
- W4380927145 hasConcept C78458016 @default.
- W4380927145 hasConcept C78762247 @default.
- W4380927145 hasConcept C86803240 @default.
- W4380927145 hasConcept C97541855 @default.
- W4380927145 hasConceptScore W4380927145C10138342 @default.
- W4380927145 hasConceptScore W4380927145C106159729 @default.
- W4380927145 hasConceptScore W4380927145C106306483 @default.
- W4380927145 hasConceptScore W4380927145C108583219 @default.
- W4380927145 hasConceptScore W4380927145C127413603 @default.
- W4380927145 hasConceptScore W4380927145C139938925 @default.
- W4380927145 hasConceptScore W4380927145C14036430 @default.
- W4380927145 hasConceptScore W4380927145C154945302 @default.
- W4380927145 hasConceptScore W4380927145C162324750 @default.
- W4380927145 hasConceptScore W4380927145C182306322 @default.
- W4380927145 hasConceptScore W4380927145C188116033 @default.
- W4380927145 hasConceptScore W4380927145C2780821815 @default.
- W4380927145 hasConceptScore W4380927145C2987168347 @default.
- W4380927145 hasConceptScore W4380927145C41008148 @default.
- W4380927145 hasConceptScore W4380927145C50644808 @default.
- W4380927145 hasConceptScore W4380927145C548081761 @default.
- W4380927145 hasConceptScore W4380927145C59427239 @default.
- W4380927145 hasConceptScore W4380927145C78458016 @default.
- W4380927145 hasConceptScore W4380927145C78762247 @default.
- W4380927145 hasConceptScore W4380927145C86803240 @default.
- W4380927145 hasConceptScore W4380927145C97541855 @default.
- W4380927145 hasFunder F4320337111 @default.
- W4380927145 hasLocation W43809271451 @default.
- W4380927145 hasOpenAccess W4380927145 @default.
- W4380927145 hasPrimaryLocation W43809271451 @default.