aiqbench analysis
This paper addresses the critical gap in retail analytics by integrating causal inference and model explainability (SHAP) to derive actionable sales insights from complex, multi-divisional datasets. By employing double machine learning techniques that account for confounders, the study demonstrates how to validate causal links and correct effect signs, moving beyond standard predictive models that lack interpretability.
Causal inference and model explainability analysis of a real world sales dataset
arXiv:2512.12605v2 Announce Type: replace Abstract: 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.
Abstract: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.
Machine Learning (cs.LG)
arXiv:2512.12605 [cs.LG]
(or arXiv:2512.12605v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2512.12605 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 255 words
Related coverage
Current AIs out-persuade professionals in lab settings but (probably) not in the world
LessWrong · Oct 5, 2026
[AINews] DeepSeek v4.1-Flash: 763B-P8B-D16B novel causal Encoder–Decoder architecture with vision marks the Return of the Whale
Latent Space · Sep 12, 2026
Debating RSI, the US-China Gap, and Jaggedness with JS Denain of Epoch AI
Interconnects · Sep 22, 2026
[AINews] High Taste Testers Ep. 1
Latent Space · Oct 17, 2026