Visually-Aware Personalized Recommendation using Interpretable Image Representations.

Visually-aware recommender systems use visual signals present in the underlying data to model the visual characteristics of items and usersu0027 preferences towards them. the domain of clothing recommendation, incorporating itemsu0027 visual information (e.g., product images) is particularly important since clothing item appearance is often a critical factor in influencing the useru0027s purchasing decisions. Current state-of-the-art visually-aware recommender systems utilize image features extracted from pre-trained deep convolutional neural networks, however these extremely high-dimensional representations are difficult to interpret, especially in relation to the relatively low number of visual properties that may guide usersu0027 decisions. In this paper we propose a novel approach to personalized clothing recommendation that models the dynamics of individual usersu0027 visual preferences. By using interpretable image representations generated with a unique feature learning process, our model learns to explain usersu0027 prior feedback in terms of their affinity towards specific visual attributes and styles. Our approach achieves state-of-the-art performance on personalized ranking tasks, and the incorporation of interpretable visual features allows for powerful model introspection, which we demonstrate by using an interactive recommendation algorithm and visualizing the rise and fall of fashion trends over time.