Causal inference and model explainability tools for retail
This work addresses interpretability and causal inference gaps for retail analysts, but it is incremental as it reviews and applies existing methods to a specific domain.
The paper tackled the lack of interpretability and causal validation in retail analytics by applying model interpretability and causal inference to a real-world dataset, finding that explainable models reduce SHAP value variance and double machine learning corrects causal effect signs.
Most major retailers today have multiple divisions focused on various aspects, such as marketing, supply chain, online customer experience, store customer experience, employee productivity, and vendor fulfillment. They also regularly collect data corresponding to all these aspects as dashboards and weekly/monthly/quarterly reports. Although several machine learning and statistical techniques have been in place to analyze and predict key metrics, such models typically lack interpretability. Moreover, such techniques also do not allow the validation or discovery of causal links. In this paper, we aim to provide a recipe for applying model interpretability and causal inference for deriving sales insights. In this paper, we review the existing literature on causal inference and interpretability in the context of problems in e-commerce and retail, and apply them to a real-world dataset. We find that an inherently explainable model has a lower variance of SHAP values, and show that including multiple confounders through a double machine learning approach allows us to get the correct sign of causal effect.