Context-Aware Drive-thru Recommendation Service at Fast Food Restaurants

TL;DR

This paper introduces TxT, a Transformer-based recommendation model leveraging contextual features for drive-thru scenarios, demonstrating superior performance and system efficiency in a real-world fast food environment.

Contribution

The paper proposes a novel Transformer Cross Transformer (TxT) model that uses contextual features for drive-thru recommendations, and develops an efficient unified big data system for deployment.

Findings

TxT outperforms existing recommendation models in Burger King's environment.

A unified big data system improves efficiency and reduces costs.

The approach generalizes to other customer interaction channels.

Abstract

Drive-thru is a popular sales channel in the fast food industry where consumers can make food purchases without leaving their cars. Drive-thru recommendation systems allow restaurants to display food recommendations on the digital menu board as guests are making their orders. Popular recommendation models in eCommerce scenarios rely on user attributes (such as user profiles or purchase history) to generate recommendations, while such information is hard to obtain in the drive-thru use case. Thus, in this paper, we propose a new recommendation model Transformer Cross Transformer (TxT), which exploits the guest order behavior and contextual features (such as location, time, and weather) using Transformer encoders for drive-thru recommendations. Empirical results show that our TxT model achieves superior results in Burger King's drive-thru production environment compared with existing recommendation solutions. In addition, we implement a unified system to run end-to-end big data analytics and deep learning workloads on the same cluster. We find that in practice, maintaining a single big data cluster for the entire pipeline is more efficient and cost-saving. Our recommendation system is not only beneficial for drive-thru scenarios, and it can also be generalized to other customer interaction channels.