An interpretable latent variable model for attribute applicability in the Amazon catalogue

TL;DR

This paper introduces MaxMachine, an interpretable probabilistic model that learns binary latent representations for product attribute applicability, addressing challenges like lack of ground truth data and the need for interpretability in large-scale catalog prediction.

Contribution

The paper presents MaxMachine, a novel layered probabilistic model that captures attribute co-occurrence and allows incorporation of prior knowledge, improving applicability predictions.

Findings

Outperforms baseline in 17 out of 19 product groups

Provides qualitatively reasonable predictions

Enables stacking for more abstract representations

Abstract

Learning attribute applicability of products in the Amazon catalog (e.g., predicting that a shoe should have a value for size, but not for battery-type at scale is a challenge. The need for an interpretable model is contingent on (1) the lack of ground truth training data, (2) the need to utilise prior information about the underlying latent space and (3) the ability to understand the quality of predictions on new, unseen data. To this end, we develop the MaxMachine, a probabilistic latent variable model that learns distributed binary representations, associated to sets of features that are likely to co-occur in the data. Layers of MaxMachines can be stacked such that higher layers encode more abstract information. Any set of variables can be clamped to encode prior information. We develop fast sampling based posterior inference. Preliminary results show that the model improves over the baseline in 17 out of 19 product groups and provides qualitatively reasonable predictions.