Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201637219> ?p ?o ?g. }
- W3201637219 endingPage "27" @default.
- W3201637219 startingPage "1" @default.
- W3201637219 abstract "This article proposes a deep learning solution to the online portfolio selection problem based on learning a latent structure directly from a price time series. It introduces a novel wealth flow matrix for representing a latent structure that has special regular conditions to encode the knowledge about the relative strengths of assets in portfolios. Therefore, a wealth flow model (WFM) is proposed to learn wealth flow matrices and maximize portfolio wealth simultaneously. Compared with existing approaches, our work has several distinctive benefits: (1) the learning of wealth flow matrices makes our model more generalizable than models that only predict wealth proportion vectors, and (2) the exploitation of wealth flow matrices and the exploration of wealth growth are integrated into our deep reinforcement algorithm for the WFM. These benefits, in combination, lead to a highly-effective approach for generating reasonable investment behavior, including short-term trend following, the following of a few losers, no self-investment, and sparse portfolios. Extensive experiments on five benchmark datasets from real-world stock markets confirm the theoretical advantage of the WFM, which achieves the Pareto improvements in terms of multiple performance indicators and the steady growth of wealth over the state-of-the-art algorithms." @default.
- W3201637219 created "2021-09-27" @default.
- W3201637219 creator A5003347359 @default.
- W3201637219 creator A5023856537 @default.
- W3201637219 creator A5029854551 @default.
- W3201637219 creator A5034037375 @default.
- W3201637219 creator A5046294611 @default.
- W3201637219 creator A5048450672 @default.
- W3201637219 creator A5088460546 @default.
- W3201637219 date "2021-09-03" @default.
- W3201637219 modified "2023-10-02" @default.
- W3201637219 title "Wealth Flow Model: Online Portfolio Selection Based on Learning Wealth Flow Matrices" @default.
- W3201637219 cites W1964964840 @default.
- W3201637219 cites W2001150023 @default.
- W3201637219 cites W2016203627 @default.
- W3201637219 cites W2016613525 @default.
- W3201637219 cites W2022333704 @default.
- W3201637219 cites W2064190404 @default.
- W3201637219 cites W2064675550 @default.
- W3201637219 cites W2104559023 @default.
- W3201637219 cites W2106052345 @default.
- W3201637219 cites W2120499560 @default.
- W3201637219 cites W2129160848 @default.
- W3201637219 cites W2129427957 @default.
- W3201637219 cites W2133282234 @default.
- W3201637219 cites W2145339207 @default.
- W3201637219 cites W2150865801 @default.
- W3201637219 cites W2158100334 @default.
- W3201637219 cites W2306941105 @default.
- W3201637219 cites W2371440349 @default.
- W3201637219 cites W2467879811 @default.
- W3201637219 cites W2621367454 @default.
- W3201637219 cites W2746758043 @default.
- W3201637219 cites W2766447205 @default.
- W3201637219 cites W2779291949 @default.
- W3201637219 cites W2806935515 @default.
- W3201637219 cites W2890096158 @default.
- W3201637219 cites W2891295326 @default.
- W3201637219 cites W2895558267 @default.
- W3201637219 cites W2897494692 @default.
- W3201637219 cites W2900880305 @default.
- W3201637219 cites W2902534617 @default.
- W3201637219 cites W2927690792 @default.
- W3201637219 cites W2936199759 @default.
- W3201637219 cites W2946136962 @default.
- W3201637219 cites W2962893376 @default.
- W3201637219 cites W2963177712 @default.
- W3201637219 cites W2972733119 @default.
- W3201637219 cites W2981684093 @default.
- W3201637219 cites W2996338638 @default.
- W3201637219 cites W3010282874 @default.
- W3201637219 cites W3015581296 @default.
- W3201637219 cites W3016284170 @default.
- W3201637219 cites W3101380508 @default.
- W3201637219 cites W4211017739 @default.
- W3201637219 cites W4237883889 @default.
- W3201637219 doi "https://doi.org/10.1145/3464308" @default.
- W3201637219 hasPublicationYear "2021" @default.
- W3201637219 type Work @default.
- W3201637219 sameAs 3201637219 @default.
- W3201637219 citedByCount "1" @default.
- W3201637219 countsByYear W32016372192023 @default.
- W3201637219 crossrefType "journal-article" @default.
- W3201637219 hasAuthorship W3201637219A5003347359 @default.
- W3201637219 hasAuthorship W3201637219A5023856537 @default.
- W3201637219 hasAuthorship W3201637219A5029854551 @default.
- W3201637219 hasAuthorship W3201637219A5034037375 @default.
- W3201637219 hasAuthorship W3201637219A5046294611 @default.
- W3201637219 hasAuthorship W3201637219A5048450672 @default.
- W3201637219 hasAuthorship W3201637219A5088460546 @default.
- W3201637219 hasConcept C106159729 @default.
- W3201637219 hasConcept C119857082 @default.
- W3201637219 hasConcept C126255220 @default.
- W3201637219 hasConcept C13280743 @default.
- W3201637219 hasConcept C137635306 @default.
- W3201637219 hasConcept C149782125 @default.
- W3201637219 hasConcept C154945302 @default.
- W3201637219 hasConcept C162324750 @default.
- W3201637219 hasConcept C185798385 @default.
- W3201637219 hasConcept C205649164 @default.
- W3201637219 hasConcept C2524010 @default.
- W3201637219 hasConcept C2780821815 @default.
- W3201637219 hasConcept C33923547 @default.
- W3201637219 hasConcept C38349280 @default.
- W3201637219 hasConcept C41008148 @default.
- W3201637219 hasConcept C81917197 @default.
- W3201637219 hasConceptScore W3201637219C106159729 @default.
- W3201637219 hasConceptScore W3201637219C119857082 @default.
- W3201637219 hasConceptScore W3201637219C126255220 @default.
- W3201637219 hasConceptScore W3201637219C13280743 @default.
- W3201637219 hasConceptScore W3201637219C137635306 @default.
- W3201637219 hasConceptScore W3201637219C149782125 @default.
- W3201637219 hasConceptScore W3201637219C154945302 @default.
- W3201637219 hasConceptScore W3201637219C162324750 @default.
- W3201637219 hasConceptScore W3201637219C185798385 @default.
- W3201637219 hasConceptScore W3201637219C205649164 @default.
- W3201637219 hasConceptScore W3201637219C2524010 @default.
- W3201637219 hasConceptScore W3201637219C2780821815 @default.