Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964733886> ?p ?o ?g. }
- W2964733886 endingPage "107756" @default.
- W2964733886 startingPage "107744" @default.
- W2964733886 abstract "Customer services are critical to all companies, as they may directly connect to the brand reputation. Due to a great number of customers, e-commerce companies often employ multiple communication channels to answer customers' questions, for example, Chatbot and Hotline. On one hand, each channel has limited capacity to respond to customers' requests; on the other hand, customers have different preferences over these channels. The current production systems are mainly built based on business rules that merely consider the tradeoffs between the resources and customers' satisfaction. To achieve the optimal tradeoff between the resources and customers' satisfaction, we propose a new framework based on deep reinforcement learning that directly takes both resources and user model into account. In addition to the framework, we also propose a new deep-reinforcement-learning-based routing method-double dueling deep Q-learning with prioritized experience replay (PER-DoDDQN). We evaluate our proposed framework and method using both synthetic and a real customer service log data from a large financial technology company. We show that our proposed deep-reinforcement-learning-based framework is superior to the existing production system. Moreover, we also show that our proposed PER-DoDDQN is better than all other deep Q-learning variants in practice, which provides a more optimal routing plan. These observations suggest that our proposed method can seek the tradeoff, where both channel resources and customers' satisfaction are optimal." @default.
- W2964733886 created "2019-08-13" @default.
- W2964733886 creator A5007236824 @default.
- W2964733886 creator A5029508998 @default.
- W2964733886 creator A5035825042 @default.
- W2964733886 creator A5038352667 @default.
- W2964733886 creator A5073094689 @default.
- W2964733886 creator A5073501391 @default.
- W2964733886 date "2019-01-01" @default.
- W2964733886 modified "2023-09-30" @default.
- W2964733886 title "Which Channel to Ask My Question?: Personalized Customer Service Request Stream Routing Using Deep Reinforcement Learning" @default.
- W2964733886 cites W1560739766 @default.
- W2964733886 cites W2021247827 @default.
- W2964733886 cites W2070493638 @default.
- W2964733886 cites W2080142539 @default.
- W2964733886 cites W2125612430 @default.
- W2964733886 cites W2145339207 @default.
- W2964733886 cites W2166322089 @default.
- W2964733886 cites W2342491128 @default.
- W2964733886 cites W2358876993 @default.
- W2964733886 cites W2410426698 @default.
- W2964733886 cites W2512351403 @default.
- W2964733886 cites W2544063074 @default.
- W2964733886 cites W2604842920 @default.
- W2964733886 cites W2765204009 @default.
- W2964733886 cites W2776507577 @default.
- W2964733886 cites W2790625403 @default.
- W2964733886 cites W2795411881 @default.
- W2964733886 cites W2888466235 @default.
- W2964733886 cites W2891768968 @default.
- W2964733886 cites W2900028034 @default.
- W2964733886 cites W2911964244 @default.
- W2964733886 cites W2912731314 @default.
- W2964733886 cites W2915309887 @default.
- W2964733886 cites W2918400102 @default.
- W2964733886 cites W2962806975 @default.
- W2964733886 cites W2963549123 @default.
- W2964733886 cites W3102476541 @default.
- W2964733886 cites W3105058112 @default.
- W2964733886 doi "https://doi.org/10.1109/access.2019.2932047" @default.
- W2964733886 hasPublicationYear "2019" @default.
- W2964733886 type Work @default.
- W2964733886 sameAs 2964733886 @default.
- W2964733886 citedByCount "3" @default.
- W2964733886 countsByYear W29647338862021 @default.
- W2964733886 countsByYear W29647338862022 @default.
- W2964733886 countsByYear W29647338862023 @default.
- W2964733886 crossrefType "journal-article" @default.
- W2964733886 hasAuthorship W2964733886A5007236824 @default.
- W2964733886 hasAuthorship W2964733886A5029508998 @default.
- W2964733886 hasAuthorship W2964733886A5035825042 @default.
- W2964733886 hasAuthorship W2964733886A5038352667 @default.
- W2964733886 hasAuthorship W2964733886A5073094689 @default.
- W2964733886 hasAuthorship W2964733886A5073501391 @default.
- W2964733886 hasBestOaLocation W29647338861 @default.
- W2964733886 hasConcept C108583219 @default.
- W2964733886 hasConcept C127162648 @default.
- W2964733886 hasConcept C144024400 @default.
- W2964733886 hasConcept C144133560 @default.
- W2964733886 hasConcept C154945302 @default.
- W2964733886 hasConcept C162853370 @default.
- W2964733886 hasConcept C191511416 @default.
- W2964733886 hasConcept C2779041454 @default.
- W2964733886 hasConcept C2780378061 @default.
- W2964733886 hasConcept C31258907 @default.
- W2964733886 hasConcept C36289849 @default.
- W2964733886 hasConcept C41008148 @default.
- W2964733886 hasConcept C48798503 @default.
- W2964733886 hasConcept C97541855 @default.
- W2964733886 hasConceptScore W2964733886C108583219 @default.
- W2964733886 hasConceptScore W2964733886C127162648 @default.
- W2964733886 hasConceptScore W2964733886C144024400 @default.
- W2964733886 hasConceptScore W2964733886C144133560 @default.
- W2964733886 hasConceptScore W2964733886C154945302 @default.
- W2964733886 hasConceptScore W2964733886C162853370 @default.
- W2964733886 hasConceptScore W2964733886C191511416 @default.
- W2964733886 hasConceptScore W2964733886C2779041454 @default.
- W2964733886 hasConceptScore W2964733886C2780378061 @default.
- W2964733886 hasConceptScore W2964733886C31258907 @default.
- W2964733886 hasConceptScore W2964733886C36289849 @default.
- W2964733886 hasConceptScore W2964733886C41008148 @default.
- W2964733886 hasConceptScore W2964733886C48798503 @default.
- W2964733886 hasConceptScore W2964733886C97541855 @default.
- W2964733886 hasFunder F4320321001 @default.
- W2964733886 hasLocation W29647338861 @default.
- W2964733886 hasLocation W29647338862 @default.
- W2964733886 hasLocation W29647338863 @default.
- W2964733886 hasLocation W29647338864 @default.
- W2964733886 hasOpenAccess W2964733886 @default.
- W2964733886 hasPrimaryLocation W29647338861 @default.
- W2964733886 hasRelatedWork W2731899572 @default.
- W2964733886 hasRelatedWork W2959276766 @default.
- W2964733886 hasRelatedWork W3005560120 @default.
- W2964733886 hasRelatedWork W3037422413 @default.
- W2964733886 hasRelatedWork W3173482257 @default.
- W2964733886 hasRelatedWork W3209094908 @default.
- W2964733886 hasRelatedWork W3211352205 @default.
- W2964733886 hasRelatedWork W4206669594 @default.