Meta-Prod2Vec

Vasile, Flavian; Смирнова, Елена; Conneau, Alexis

doi:10.1145/2959100.2959160

Cited by 142 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To re-purpose them we replace sequences of words with sequences of customers viewing a product (see Figure 7). Previous work has looked at embedding products based on sequences of customer interactions [3,10,22]. It is possible to aggregate product embeddings to produce a customer embedding.…”

Section: Embedding Customers Using Browsing Sessionsmentioning

confidence: 99%

Customer Lifetime Value Prediction Using Embeddings

Chamberlain

Cardoso

Liu

et al. 2017

Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

We describe the Customer LifeTime Value (CLTV) prediction system deployed at ASOS.com, a global online fashion retailer. CLTV prediction is an important problem in e-commerce where an accurate estimate of future value allows retailers to e ectively allocate marketing spend, identify and nurture high value customers and mitigate exposure to losses. e system at ASOS provides daily estimates of the future value of every customer and is one of the cornerstones of the personalised shopping experience. e state of the art in this domain uses large numbers of handcra ed features and ensemble regressors to forecast value, predict churn and evaluate customer loyalty. Recently, domains including language, vision and speech have shown dramatic advances by replacing handcra ed features with features that are learned automatically from data. We detail the system deployed at ASOS and show that learning feature representations is a promising extension to the state of the art in CLTV modelling. We propose a novel way to generate embeddings of customers, which addresses the issue of the ever changing product catalogue and obtain a signi cant improvement over an exhaustive set of handcra ed features.

show abstract

Section: Embedding Customers Using Browsing Sessionsmentioning

confidence: 99%

Customer Lifetime Value Prediction Using Embeddings

Chamberlain

Cardoso

Liu

et al. 2017

Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…The first type of methods includes factor models that learn a low-rank decomposition of sparse user-item interactions matrix [3,12,21]. The missing entries are then extrapolated as the inner product between the resulting user and item latent vectors.…”

Section: Introductionmentioning

confidence: 99%

Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks

Смирнова

Vasile

2017

Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems

Self Cite

143

101

View full text Add to dashboard Cite

Recommendations can greatly benefit from good representations of the user state at recommendation time. Recent approaches that leverage Recurrent Neural Networks (RNNs) for session-based recommendations have shown that Deep Learning models can provide useful user representations for recommendation. However, current RNN modeling approaches summarize the user state by only taking into account the sequence of items that the user has interacted with in the past, without taking into account other essential types of context information such as the associated types of user-item interactions, the time gaps between events and the time of day for each interaction. To address this, we propose a new class of Contextual Recurrent Neural Networks for Recommendation (CRNNs) that can take into account the contextual information both in the input and output layers and modifying the behavior of the RNN by combining the context embedding with the item embedding and more explicitly, in the model dynamics, by parametrizing the hidden unit transitions as a function of context information. We compare our CRNNs approach with RNNs and non-sequential baselines and show good improvements on the next event prediction task.

show abstract

“…Future work should also be er integrate the temporal information (time gaps, daily and weekly pa erns,…) in our cookie/pair representation. A possibility could be to integrate the time-gaps in doc2vec as additional information as in Vasile et al [7], or to use RNNs as proposed by Smirnova and Vasile [6]. Further work should investigate the use of RNNs for the task of similarity learning.…”

Section: Resultsmentioning

confidence: 99%

Siamese Cookie Embedding Networks for Cross-Device User Matching

Tanielian

Tousch

Vasile

2018

Companion of the the Web Conference 2018 on the Web Conference 2018 - WWW '18

Self Cite

View full text Add to dashboard Cite

Over the last decade, the number of devices per person has increased substantially. is poses a challenge for cookie-based personalization applications, such as online search and advertising, as it narrows the personalization signal to a single device environment. A key task is to find which cookies belong to the same person to recover a complete cross-device user journey. Recent work on the topic has shown the benefits of using unsupervised embeddings learned on user event sequences. In this paper, we extend this approach to a supervised se ing and introduce the Siamese Cookie Embedding Network (SCEmNet), a siamese convolutional architecture that leverages the multi-modal aspect of sequences, and show significant improvement over the state-of-the-art.

show abstract

Meta-Prod2Vec

Cited by 142 publications

References 24 publications

Customer Lifetime Value Prediction Using Embeddings

Customer Lifetime Value Prediction Using Embeddings

Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks

Siamese Cookie Embedding Networks for Cross-Device User Matching

Contact Info

Product

Resources

About