In e-commerce, the watchlist enables users to track items over time and hasemerged as a primary feature, playing an important role in users’ shopping journey . Watchlist items typically have multiple attributes whose values maychange over time (e.g., price, quantity) Since many users accumulate dozens of items on their watchlist, and since shopping intents change over time,recommending the top watchlist items in a given context can be valuable . Our goal is to prioritize which watchlistitems the user should pay attention to next by predicting the next items theuser will click . Our proposed recommendation model,Trans2D, is built on top of the Transformer architecture, where we furthersuggest a novel extended attention mechanism (Attention2D) that allows to learn complex item-item, attribute-attention patterns fromsequential-data with multiple item attributes

Author(s) : Uriel Singer, Haggai Roitman, Yotam Eshel, Alexander Nus, Ido Guy, Or Levi, Idan Hasson, Eliyahu Kiperwasser

Links : PDF - Abstract

Code :

Keywords : items - watchlist - attention - attributes - item -

Leave a Reply

Your email address will not be published. Required fields are marked *