Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386729596> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4386729596 abstract "Personalization plays a critical role in helping customers discover the products and contents they prefer for e-commerce stores.Personalized recommendations differ in contents, target customers, and UI. However, they require a common core capability - the ability to deeply understand customers’ preferences and shopping intents. In this paper, we introduce the MCM (Multi-task pre-trained Customer Model), a large pre-trained BERT-based multi-task customer model with 10 million trainable parameters for e-commerce stores. This model aims to empower all personalization projects by providing commonly used preference scores for recommendations, customer embeddings for transfer learning, and a pre-trained model for fine-tuning. In this work, we improve the SOTA BERT4Rec framework to handle heterogeneous customer signals and multi-task training as well as innovate new data augmentation method that is suitable for recommendation task. Experimental results show that MCM outperforms the original BERT4Rec by 17% on on NDCG@10 of next action prediction tasks. Additionally, we demonstrate that the model can be easily fine-tuned to assist a specific recommendation task. For instance, after fine-tuning MCM for an incentive based recommendation project, performance improves by 60% on the conversion prediction task and 25% on the click-through prediction task compared to a baseline tree-based GBDT model." @default.
- W4386729596 created "2023-09-15" @default.
- W4386729596 creator A5030316883 @default.
- W4386729596 creator A5040937538 @default.
- W4386729596 creator A5041122666 @default.
- W4386729596 creator A5082110272 @default.
- W4386729596 date "2023-09-14" @default.
- W4386729596 modified "2023-09-26" @default.
- W4386729596 title "MCM: A Multi-task Pre-trained Customer Model for Personalization" @default.
- W4386729596 cites W2171279286 @default.
- W4386729596 cites W2512971201 @default.
- W4386729596 cites W2626454364 @default.
- W4386729596 cites W2984100107 @default.
- W4386729596 doi "https://doi.org/10.1145/3604915.3608868" @default.
- W4386729596 hasPublicationYear "2023" @default.
- W4386729596 type Work @default.
- W4386729596 citedByCount "0" @default.
- W4386729596 crossrefType "proceedings-article" @default.
- W4386729596 hasAuthorship W4386729596A5030316883 @default.
- W4386729596 hasAuthorship W4386729596A5040937538 @default.
- W4386729596 hasAuthorship W4386729596A5041122666 @default.
- W4386729596 hasAuthorship W4386729596A5082110272 @default.
- W4386729596 hasBestOaLocation W43867295961 @default.
- W4386729596 hasConcept C107457646 @default.
- W4386729596 hasConcept C111368507 @default.
- W4386729596 hasConcept C113174947 @default.
- W4386729596 hasConcept C119857082 @default.
- W4386729596 hasConcept C12725497 @default.
- W4386729596 hasConcept C127313418 @default.
- W4386729596 hasConcept C134306372 @default.
- W4386729596 hasConcept C136764020 @default.
- W4386729596 hasConcept C154945302 @default.
- W4386729596 hasConcept C162324750 @default.
- W4386729596 hasConcept C175444787 @default.
- W4386729596 hasConcept C183003079 @default.
- W4386729596 hasConcept C187736073 @default.
- W4386729596 hasConcept C2780451532 @default.
- W4386729596 hasConcept C2781249084 @default.
- W4386729596 hasConcept C33923547 @default.
- W4386729596 hasConcept C41008148 @default.
- W4386729596 hasConcept C557471498 @default.
- W4386729596 hasConceptScore W4386729596C107457646 @default.
- W4386729596 hasConceptScore W4386729596C111368507 @default.
- W4386729596 hasConceptScore W4386729596C113174947 @default.
- W4386729596 hasConceptScore W4386729596C119857082 @default.
- W4386729596 hasConceptScore W4386729596C12725497 @default.
- W4386729596 hasConceptScore W4386729596C127313418 @default.
- W4386729596 hasConceptScore W4386729596C134306372 @default.
- W4386729596 hasConceptScore W4386729596C136764020 @default.
- W4386729596 hasConceptScore W4386729596C154945302 @default.
- W4386729596 hasConceptScore W4386729596C162324750 @default.
- W4386729596 hasConceptScore W4386729596C175444787 @default.
- W4386729596 hasConceptScore W4386729596C183003079 @default.
- W4386729596 hasConceptScore W4386729596C187736073 @default.
- W4386729596 hasConceptScore W4386729596C2780451532 @default.
- W4386729596 hasConceptScore W4386729596C2781249084 @default.
- W4386729596 hasConceptScore W4386729596C33923547 @default.
- W4386729596 hasConceptScore W4386729596C41008148 @default.
- W4386729596 hasConceptScore W4386729596C557471498 @default.
- W4386729596 hasLocation W43867295961 @default.
- W4386729596 hasOpenAccess W4386729596 @default.
- W4386729596 hasPrimaryLocation W43867295961 @default.
- W4386729596 hasRelatedWork W2045871438 @default.
- W4386729596 hasRelatedWork W2136016921 @default.
- W4386729596 hasRelatedWork W2348159088 @default.
- W4386729596 hasRelatedWork W2369936857 @default.
- W4386729596 hasRelatedWork W2463229044 @default.
- W4386729596 hasRelatedWork W2499363748 @default.
- W4386729596 hasRelatedWork W2809363009 @default.
- W4386729596 hasRelatedWork W2956112762 @default.
- W4386729596 hasRelatedWork W2968745142 @default.
- W4386729596 hasRelatedWork W3134230178 @default.
- W4386729596 isParatext "false" @default.
- W4386729596 isRetracted "false" @default.
- W4386729596 workType "article" @default.