FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894499144> ?p ?o ?g. }

• W2894499144 abstract "This industry talk covers the deep learning architecture developed at Realtor.com to recommend real estate listings to our userbase. The recommendation of homes is a different problem than most other domains both in the sense that listings are unique and that there are additional geographic and time constraints that increase the sparsity of interactions and make recommendation of individual listings more challenging. In particular time on market in a hot area can be limited to weeks or even days, and listing cold-start is critical to providing up to date market information. Thankfully the structured feature data for listings is incredibly rich and provides a framework from which to map listings into a meaningful vector space. User first impressions are also incredibly important in this highly competitive field, and offline recommendation or models that don't adapt during the users session are less desirable. In order to solve this recommendation problem we have developed a model based off of session based recommendation [1]. The architecture utilizes state of the art techniques from Natural Language Processing, including the AWD-LSTM language model developed by Salesforce [2]. To solve for cold-start of listings a structured data based denoising autoencoder was adapted from the methodology described in the winning entry of the Puerto Segurno Safe Driver Kaggle Competition [3]. This model is not used in the common way of generating fixed feature vectors, but rather the entire head of the autoencoder model, from the feature inputs to the middle layer commonly used as the vector output, is first trained to encode listing features, and then becomes the input to the AWD-LSTM architecture. This style of transfer learning is common in Computer Vision, and has recently been utilized in NLP to achieve state of the art results for text classification [4]. By including the head we are able to further optimize the listing encoder network and embeddings to take user interactions into account. As in traditional session based recommendation users are represented as the sequence of listings that they view, however those listings are fed into the model as the sequence of features. The final system consists of several components. The first attempts to calculate and maintain the users' feature vector and model hidden weights in near realtime, providing a representation for the user within the system. This representation is used by several downstream components, most notably the search rerank and recommendation modules which calculate users' interest in listings both in the context of the output of more traditional elasticsearch queries via cosine similarity of user/listing vectors and through approximate nearest neighbor vector space searches for relevant listings which form the input set for a pointwise scoring model trained on time on listing as done by YouTube [5]." @default.
• W2894499144 created "2018-10-05" @default.
• W2894499144 creator A5023954126 @default.
• W2894499144 date "2018-09-27" @default.
• W2894499144 modified "2023-09-25" @default.
• W2894499144 title "Adapting session based recommendation for features through transfer learning" @default.
• W2894499144 cites W2262817822 @default.
• W2894499144 cites W2784121710 @default.
• W2894499144 doi "https://doi.org/10.1145/3240323.3241728" @default.
• W2894499144 hasPublicationYear "2018" @default.
• W2894499144 type Work @default.
• W2894499144 sameAs 2894499144 @default.
• W2894499144 citedByCount "1" @default.
• W2894499144 countsByYear W28944991442019 @default.
• W2894499144 crossrefType "proceedings-article" @default.
• W2894499144 hasAuthorship W2894499144A5023954126 @default.
• W2894499144 hasConcept C111919701 @default.
• W2894499144 hasConcept C136764020 @default.
• W2894499144 hasConcept C150899416 @default.
• W2894499144 hasConcept C154945302 @default.
• W2894499144 hasConcept C2776175482 @default.
• W2894499144 hasConcept C2779182362 @default.
• W2894499144 hasConcept C41008148 @default.
• W2894499144 hasConcept C49774154 @default.
• W2894499144 hasConceptScore W2894499144C111919701 @default.
• W2894499144 hasConceptScore W2894499144C136764020 @default.
• W2894499144 hasConceptScore W2894499144C150899416 @default.
• W2894499144 hasConceptScore W2894499144C154945302 @default.
• W2894499144 hasConceptScore W2894499144C2776175482 @default.
• W2894499144 hasConceptScore W2894499144C2779182362 @default.
• W2894499144 hasConceptScore W2894499144C41008148 @default.
• W2894499144 hasConceptScore W2894499144C49774154 @default.
• W2894499144 hasLocation W28944991441 @default.
• W2894499144 hasOpenAccess W2894499144 @default.
• W2894499144 hasPrimaryLocation W28944991441 @default.
• W2894499144 hasRelatedWork W2112668038 @default.
• W2894499144 hasRelatedWork W2593019443 @default.
• W2894499144 hasRelatedWork W2765107853 @default.
• W2894499144 hasRelatedWork W2807706688 @default.
• W2894499144 hasRelatedWork W2941215368 @default.
• W2894499144 hasRelatedWork W2995971828 @default.
• W2894499144 hasRelatedWork W3087157779 @default.
• W2894499144 hasRelatedWork W3202548321 @default.
• W2894499144 hasRelatedWork W4248013214 @default.
• W2894499144 hasRelatedWork W4283522607 @default.
• W2894499144 isParatext "false" @default.
• W2894499144 isRetracted "false" @default.
• W2894499144 magId "2894499144" @default.
• W2894499144 workType "article" @default.