A united framework for personalisation which encompasses cold start and implicit interaction data

Abstract

A digital medium environment is described to facilitate recommendations based on vectors generated using feature word embeddings. A recommendation system receives data that describes at least one attribute for a user profile, at least one item, and an interaction between the user profile and the at least one item. The recommendation system associates each user profile attribute, each item, and each interaction between a user profile and an item as a word, using natural language processing, and combines the words into sentences. The sentences are input to a word embedding model to determine feature vector representations describing relationships between the user profile attributes, items, and explicit and implicit interactions. From the feature vector representations, the recommendation system ascertains a similarity between different features. Thus, the recommendation system can provide customized recommendations based on implicit interactions, even for a user profile that is not associated with any historical interaction data.

Description

Background technique [0001] The computing device outputs recommendations for exposing items that may be of interest to the user, even if the user is unaware of the existence of the items. For example, a video streaming service may output movie or TV show recommendations, an online store output product recommendations, and so on. Many services have replaced traditional search engines with automatic recommendations as the primary means for discovering content items. Thus, the system strives to tailor recommendations to individual end users such that the recommended items are actually of interest. [0002] Traditional recommender systems utilize historical data describing explicit interactions between user profiles and items. Explicit interactions include item view-view relationships, which describe items viewed together in a single browsing session. Other explicit interactions include view-purchase relationships, which describe at least one item purchased after being viewed. ...

AI Technical Summary

Problems solved by technology

Thus, traditional schemes for digital recommendation fail to take into account important interaction data that would otherwise influence recommendation decisions

Therefore, traditional schemes for automatic item recommendation are limited to only considering certain types of interaction data, which often results in outputting irrelevant recommendations.

Images