A carregar...
Publicação
Hyperml and deep interest network to build a recommender system for modatta: measuring the effectiveness of targeting users with new offers
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 2.86 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
Modatta aims at giving users control over their data and marketers the opportunity to target users with the right campaigns. Therefore, this paper proposes the use of Deep Learning to find users’ representations, so their data is kept private, but they can still learn about their interests. A Recommender System for predicting new interests is built to create a more complete representation of the users, which allows Modatta to find the offers that are of their most interest. After implementing the targeting strategy, this study shows how to evaluate the effectiveness of a campaign that could be conducted by Modatta.
Descrição
Palavras-chave
Machine learning Deep learning Hyperbolic embeddings Data monetization Recommender system Targeted marketing Campaign effectiveness Business analysis