Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119998081> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3119998081 abstract "We present results demonstrating that an appropriately configured deep learning neural network (DLNN) can automatically learn to be a high-performing algorithmic trading system, operating purely from training-data inputs generated by passive observation of an existing successful trader T. That is, we can point our black-box DLNN system at trader T and successfully have it learn from T's trading activity, such that it trades at least as well as T. Our system, called DeepTrader, takes inputs derived from Level-2 market data, i.e. the market's Limit Order Book (LOB) or Ladder for a tradeable asset. Unusually, DeepTrader makes no explicit prediction of future prices. Instead, we train it purely on input-output pairs where in each pair the input is a snapshot S of Level-2 LOB data taken at the time when T issued a quote Q (i.e. a bid or an ask order) to the market; and DeepTrader's desired output is to produce Q when it is shown S. That is, we train our DLNN by showing it the LOB data S that T saw at the time when T issued quote Q, and in doing so our system comes to behave like T, acting as an algorithmic trader issuing specific quotes in response to specific LOB conditions. We train DeepTrader on large numbers of these S/Q snapshot/quote pairs, and then test it in a variety of market scenarios, evaluating it against other algorithmic trading systems in the public-domain literature, including two that have repeatedly been shown to outperform human traders. Our results demonstrate that DeepTrader learns to match or outperform such existing algorithmic trading systems. We analyse the successful DeepTrader network to identify what features it is relying on, and which features can be ignored. We propose that our methods can in principle create an explainable copy of an arbitrary trader T via “black-box” deep learning methods." @default.
- W3119998081 created "2021-01-18" @default.
- W3119998081 creator A5027817163 @default.
- W3119998081 creator A5044365587 @default.
- W3119998081 creator A5061197713 @default.
- W3119998081 date "2020-12-01" @default.
- W3119998081 modified "2023-09-26" @default.
- W3119998081 title "Automated Creation of a High-Performing Algorithmic Trader via Deep Learning on Level-2 Limit Order Book Data" @default.
- W3119998081 cites W1498436455 @default.
- W3119998081 cites W1666205556 @default.
- W3119998081 cites W1956343032 @default.
- W3119998081 cites W2014748701 @default.
- W3119998081 cites W2018567859 @default.
- W3119998081 cites W2050440709 @default.
- W3119998081 cites W2064675550 @default.
- W3119998081 cites W2100761249 @default.
- W3119998081 cites W2125907855 @default.
- W3119998081 cites W2130306094 @default.
- W3119998081 cites W2162288466 @default.
- W3119998081 cites W2576201845 @default.
- W3119998081 cites W2885054548 @default.
- W3119998081 cites W2902459911 @default.
- W3119998081 cites W2963045584 @default.
- W3119998081 cites W2963751193 @default.
- W3119998081 cites W2964121744 @default.
- W3119998081 cites W2998195013 @default.
- W3119998081 cites W3125409615 @default.
- W3119998081 doi "https://doi.org/10.1109/ssci47803.2020.9308266" @default.
- W3119998081 hasPublicationYear "2020" @default.
- W3119998081 type Work @default.
- W3119998081 sameAs 3119998081 @default.
- W3119998081 citedByCount "2" @default.
- W3119998081 countsByYear W31199980812020 @default.
- W3119998081 countsByYear W31199980812022 @default.
- W3119998081 crossrefType "proceedings-article" @default.
- W3119998081 hasAuthorship W3119998081A5027817163 @default.
- W3119998081 hasAuthorship W3119998081A5044365587 @default.
- W3119998081 hasAuthorship W3119998081A5061197713 @default.
- W3119998081 hasBestOaLocation W31199980812 @default.
- W3119998081 hasConcept C10138342 @default.
- W3119998081 hasConcept C106159729 @default.
- W3119998081 hasConcept C108583219 @default.
- W3119998081 hasConcept C154945302 @default.
- W3119998081 hasConcept C162324750 @default.
- W3119998081 hasConcept C182306322 @default.
- W3119998081 hasConcept C24683644 @default.
- W3119998081 hasConcept C2779309563 @default.
- W3119998081 hasConcept C41008148 @default.
- W3119998081 hasConcept C50644808 @default.
- W3119998081 hasConcept C55282118 @default.
- W3119998081 hasConcept C77088390 @default.
- W3119998081 hasConcept C78508483 @default.
- W3119998081 hasConcept C90329073 @default.
- W3119998081 hasConceptScore W3119998081C10138342 @default.
- W3119998081 hasConceptScore W3119998081C106159729 @default.
- W3119998081 hasConceptScore W3119998081C108583219 @default.
- W3119998081 hasConceptScore W3119998081C154945302 @default.
- W3119998081 hasConceptScore W3119998081C162324750 @default.
- W3119998081 hasConceptScore W3119998081C182306322 @default.
- W3119998081 hasConceptScore W3119998081C24683644 @default.
- W3119998081 hasConceptScore W3119998081C2779309563 @default.
- W3119998081 hasConceptScore W3119998081C41008148 @default.
- W3119998081 hasConceptScore W3119998081C50644808 @default.
- W3119998081 hasConceptScore W3119998081C55282118 @default.
- W3119998081 hasConceptScore W3119998081C77088390 @default.
- W3119998081 hasConceptScore W3119998081C78508483 @default.
- W3119998081 hasConceptScore W3119998081C90329073 @default.
- W3119998081 hasLocation W31199980811 @default.
- W3119998081 hasLocation W31199980812 @default.
- W3119998081 hasOpenAccess W3119998081 @default.
- W3119998081 hasPrimaryLocation W31199980811 @default.
- W3119998081 hasRelatedWork W11904183 @default.
- W3119998081 hasRelatedWork W1698766 @default.
- W3119998081 hasRelatedWork W3781714 @default.
- W3119998081 hasRelatedWork W4559280 @default.
- W3119998081 hasRelatedWork W5029139 @default.
- W3119998081 hasRelatedWork W5711943 @default.
- W3119998081 hasRelatedWork W6545291 @default.
- W3119998081 hasRelatedWork W6680660 @default.
- W3119998081 hasRelatedWork W7102450 @default.
- W3119998081 hasRelatedWork W7413466 @default.
- W3119998081 isParatext "false" @default.
- W3119998081 isRetracted "false" @default.
- W3119998081 magId "3119998081" @default.
- W3119998081 workType "article" @default.