Matches in SemOpenAlex for { <https://semopenalex.org/work/W3083721190> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W3083721190 endingPage "012016" @default.
- W3083721190 startingPage "012016" @default.
- W3083721190 abstract "Abstract Customer churn prediction is one of the biggest challenges for companies nowadays. Since the loss of customers directly affects the organization’s reputation, financial and growth plans. Customer behaviours may change due to any uncontrollable factors or unexpected circumstances, resulting in changing patterns of data. This may aggravate the prediction performance of the classifiers generated from supervised learning technique considered as Passive learning. This paper has thus proposed applying the technique of reinforcement learning for customer churn prediction. The model of Deep Q Network (DQN) is implemented and adapted for learning on the selected customer churn dataset used for classification tasks. We simulate a different distribution dataset with shuffle sampling to embrace pattern changes. The performance of the selected classifiers, compared to DQN, has been evaluated with four measures: accuracy, precision, recall, and F1. The results showed that as Active learner, DQN outperformed the selected classifiers, XGBoost, Random forest, and kNN, when data have been enlarged and evolving with emerging new patterns." @default.
- W3083721190 created "2020-09-11" @default.
- W3083721190 creator A5019535179 @default.
- W3083721190 creator A5034606101 @default.
- W3083721190 date "2020-08-01" @default.
- W3083721190 modified "2023-10-18" @default.
- W3083721190 title "Applying Reinforcement Learning for Customer Churn Prediction" @default.
- W3083721190 cites W1978501154 @default.
- W3083721190 cites W2973862992 @default.
- W3083721190 cites W2986022878 @default.
- W3083721190 doi "https://doi.org/10.1088/1742-6596/1619/1/012016" @default.
- W3083721190 hasPublicationYear "2020" @default.
- W3083721190 type Work @default.
- W3083721190 sameAs 3083721190 @default.
- W3083721190 citedByCount "3" @default.
- W3083721190 countsByYear W30837211902021 @default.
- W3083721190 countsByYear W30837211902023 @default.
- W3083721190 crossrefType "journal-article" @default.
- W3083721190 hasAuthorship W3083721190A5019535179 @default.
- W3083721190 hasAuthorship W3083721190A5034606101 @default.
- W3083721190 hasBestOaLocation W30837211901 @default.
- W3083721190 hasConcept C119857082 @default.
- W3083721190 hasConcept C136389625 @default.
- W3083721190 hasConcept C144024400 @default.
- W3083721190 hasConcept C154945302 @default.
- W3083721190 hasConcept C169258074 @default.
- W3083721190 hasConcept C36289849 @default.
- W3083721190 hasConcept C41008148 @default.
- W3083721190 hasConcept C48798503 @default.
- W3083721190 hasConcept C50644808 @default.
- W3083721190 hasConcept C97541855 @default.
- W3083721190 hasConceptScore W3083721190C119857082 @default.
- W3083721190 hasConceptScore W3083721190C136389625 @default.
- W3083721190 hasConceptScore W3083721190C144024400 @default.
- W3083721190 hasConceptScore W3083721190C154945302 @default.
- W3083721190 hasConceptScore W3083721190C169258074 @default.
- W3083721190 hasConceptScore W3083721190C36289849 @default.
- W3083721190 hasConceptScore W3083721190C41008148 @default.
- W3083721190 hasConceptScore W3083721190C48798503 @default.
- W3083721190 hasConceptScore W3083721190C50644808 @default.
- W3083721190 hasConceptScore W3083721190C97541855 @default.
- W3083721190 hasIssue "1" @default.
- W3083721190 hasLocation W30837211901 @default.
- W3083721190 hasOpenAccess W3083721190 @default.
- W3083721190 hasPrimaryLocation W30837211901 @default.
- W3083721190 hasRelatedWork W3022038857 @default.
- W3083721190 hasRelatedWork W3116896278 @default.
- W3083721190 hasRelatedWork W3204641204 @default.
- W3083721190 hasRelatedWork W4225360065 @default.
- W3083721190 hasRelatedWork W4249746146 @default.
- W3083721190 hasRelatedWork W4282839226 @default.
- W3083721190 hasRelatedWork W4283016678 @default.
- W3083721190 hasRelatedWork W4308191010 @default.
- W3083721190 hasRelatedWork W4318350883 @default.
- W3083721190 hasRelatedWork W4322727400 @default.
- W3083721190 hasVolume "1619" @default.
- W3083721190 isParatext "false" @default.
- W3083721190 isRetracted "false" @default.
- W3083721190 magId "3083721190" @default.
- W3083721190 workType "article" @default.