Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380047478> ?p ?o ?g. }
- W4380047478 abstract "Sequence modelling has shown tremendous potential in solving real-world sequence prediction tasks like speech recognition, time series forecasting, and context identification. However, most of these sequence models are trained on univariate datasets and cannot leverage the information available in a multivariate setting. Moreover, the prediction/decision made by these models is not interpretable; consequently, the end users are unaware of the different steps involved in reaching that prediction/decision and cannot determine if the model aligns with the business and ethical values. This work investigates the performance of different sequence learners trained in a multivariate setting for the sales forecasting task. Specifically, different sequence models, including vanilla LSTM, stacked LSTM, bidirectional LSTM, and convolution neural networkbased-LSTM, have been trained on the Walmart dataset, and a comparative analysis of their performance using mean squared error (MSE) and weighted mean absolute error (WMAE) metric is reported. For training the learners in a multivariate setting, relevant features have been identified using exploratory data analytics. Furthermore, these sequence models are made interpretable using the Local Interpretable Model Agnostic Explanation (LIME) model to explain away the key variables involved in the prediction task. Empirical results obtained on the Walmart sales dataset established that the performance of the stacked LSTM model is superior to other learners. Additionally, the stacked model being the most generalizable, is complemented by the LIME module to explain away its predictions using the relevant features." @default.
- W4380047478 created "2023-06-10" @default.
- W4380047478 creator A5046608189 @default.
- W4380047478 creator A5075023352 @default.
- W4380047478 date "2023-05-17" @default.
- W4380047478 modified "2023-09-24" @default.
- W4380047478 title "Interpretable Sequence Models for the Sales Forecasting Task: A Review" @default.
- W4380047478 cites W1840208138 @default.
- W4380047478 cites W2018378938 @default.
- W4380047478 cites W2117014758 @default.
- W4380047478 cites W2401614582 @default.
- W4380047478 cites W2586631406 @default.
- W4380047478 cites W2657631929 @default.
- W4380047478 cites W27682692 @default.
- W4380047478 cites W2774513877 @default.
- W4380047478 cites W2809925683 @default.
- W4380047478 cites W2889059162 @default.
- W4380047478 cites W2905990309 @default.
- W4380047478 cites W2907701858 @default.
- W4380047478 cites W2949449669 @default.
- W4380047478 cites W2954503794 @default.
- W4380047478 cites W2968809506 @default.
- W4380047478 cites W2976041489 @default.
- W4380047478 cites W3004114474 @default.
- W4380047478 cites W3007075806 @default.
- W4380047478 cites W3011806746 @default.
- W4380047478 cites W3012096460 @default.
- W4380047478 cites W3017116930 @default.
- W4380047478 cites W3031373376 @default.
- W4380047478 cites W3109365969 @default.
- W4380047478 cites W3110420963 @default.
- W4380047478 cites W3116286104 @default.
- W4380047478 cites W3174474688 @default.
- W4380047478 cites W3187293469 @default.
- W4380047478 cites W3192016882 @default.
- W4380047478 cites W3196770257 @default.
- W4380047478 cites W3202667440 @default.
- W4380047478 cites W3205470944 @default.
- W4380047478 cites W4206062825 @default.
- W4380047478 cites W4213160724 @default.
- W4380047478 cites W4226324245 @default.
- W4380047478 cites W4285154365 @default.
- W4380047478 cites W4293192654 @default.
- W4380047478 cites W4294559022 @default.
- W4380047478 cites W4319344949 @default.
- W4380047478 cites W4321599356 @default.
- W4380047478 doi "https://doi.org/10.1109/iciccs56967.2023.10142614" @default.
- W4380047478 hasPublicationYear "2023" @default.
- W4380047478 type Work @default.
- W4380047478 citedByCount "0" @default.
- W4380047478 crossrefType "proceedings-article" @default.
- W4380047478 hasAuthorship W4380047478A5046608189 @default.
- W4380047478 hasAuthorship W4380047478A5075023352 @default.
- W4380047478 hasConcept C105795698 @default.
- W4380047478 hasConcept C119857082 @default.
- W4380047478 hasConcept C124101348 @default.
- W4380047478 hasConcept C127413603 @default.
- W4380047478 hasConcept C139945424 @default.
- W4380047478 hasConcept C151730666 @default.
- W4380047478 hasConcept C153083717 @default.
- W4380047478 hasConcept C154945302 @default.
- W4380047478 hasConcept C161584116 @default.
- W4380047478 hasConcept C176217482 @default.
- W4380047478 hasConcept C199163554 @default.
- W4380047478 hasConcept C201995342 @default.
- W4380047478 hasConcept C21547014 @default.
- W4380047478 hasConcept C2778112365 @default.
- W4380047478 hasConcept C2779343474 @default.
- W4380047478 hasConcept C2780451532 @default.
- W4380047478 hasConcept C33923547 @default.
- W4380047478 hasConcept C41008148 @default.
- W4380047478 hasConcept C54355233 @default.
- W4380047478 hasConcept C86803240 @default.
- W4380047478 hasConceptScore W4380047478C105795698 @default.
- W4380047478 hasConceptScore W4380047478C119857082 @default.
- W4380047478 hasConceptScore W4380047478C124101348 @default.
- W4380047478 hasConceptScore W4380047478C127413603 @default.
- W4380047478 hasConceptScore W4380047478C139945424 @default.
- W4380047478 hasConceptScore W4380047478C151730666 @default.
- W4380047478 hasConceptScore W4380047478C153083717 @default.
- W4380047478 hasConceptScore W4380047478C154945302 @default.
- W4380047478 hasConceptScore W4380047478C161584116 @default.
- W4380047478 hasConceptScore W4380047478C176217482 @default.
- W4380047478 hasConceptScore W4380047478C199163554 @default.
- W4380047478 hasConceptScore W4380047478C201995342 @default.
- W4380047478 hasConceptScore W4380047478C21547014 @default.
- W4380047478 hasConceptScore W4380047478C2778112365 @default.
- W4380047478 hasConceptScore W4380047478C2779343474 @default.
- W4380047478 hasConceptScore W4380047478C2780451532 @default.
- W4380047478 hasConceptScore W4380047478C33923547 @default.
- W4380047478 hasConceptScore W4380047478C41008148 @default.
- W4380047478 hasConceptScore W4380047478C54355233 @default.
- W4380047478 hasConceptScore W4380047478C86803240 @default.
- W4380047478 hasLocation W43800474781 @default.
- W4380047478 hasOpenAccess W4380047478 @default.
- W4380047478 hasPrimaryLocation W43800474781 @default.
- W4380047478 hasRelatedWork W1543180583 @default.
- W4380047478 hasRelatedWork W2051490903 @default.
- W4380047478 hasRelatedWork W2116574033 @default.
- W4380047478 hasRelatedWork W2607189545 @default.