Causal Forecasting for Pricing

TL;DR

This paper introduces a new demand forecasting method that combines causal inference with transformer models, improving demand estimates in pricing scenarios, especially when policies change.

Contribution

It integrates Double Machine Learning for causal inference with transformer-based forecasting, a novel combination for demand prediction in pricing contexts.

Findings

Better causal effect estimation in synthetic data

Outperforms existing methods in off-policy real-world data

Slightly less accurate in on-policy settings

Abstract

This paper proposes a novel method for demand forecasting in a pricing context. Here, modeling the causal relationship between price as an input variable to demand is crucial because retailers aim to set prices in a (profit) optimal manner in a downstream decision making problem. Our methods bring together the Double Machine Learning methodology for causal inference and state-of-the-art transformer-based forecasting models. In extensive empirical experiments, we show on the one hand that our method estimates the causal effect better in a fully controlled setting via synthetic, yet realistic data. On the other hand, we demonstrate on real-world data that our method outperforms forecasting methods in off-policy settings (i.e., when there's a change in the pricing policy) while only slightly trailing in the on-policy setting.