Digital assistant in a point of sales
Emilia Lesiak, Grzegorz Wolny, Bartosz Przybył, Michał Szczerbak
TL;DR
This study evaluates a fully animated, VUI-powered digital assistant deployed at a retail point of sale to assess effects on customer engagement and service efficiency, with a focus on multilingual interactions. Using a three-month in-store experiment, it combines a Unity 3D avatar, a Rasa X–driven NLU engine, and time-series data from sensors and store metrics to analyze engagement, interaction quality, and sales implications. Findings indicate mixed effects: multilingual support increases non-native language interactions, but promotional pokes and the overall impact on foot traffic and sales are inconclusive, hindered by usability challenges such as push-to-talk and limited end-to-end capabilities. The study highlights technical, user-centric, and business insights, recommending future work on contextual memory, integration with generative AI under safeguards, improved user interfaces, and scalable deployment to unlock tangible retail value.
Abstract
This article investigates the deployment of a Voice User Interface (VUI)-powered digital assistant in a retail setting and assesses its impact on customer engagement and service efficiency. The study explores how digital assistants can enhance user interactions through advanced conversational capabilities with multilingual support. By integrating a digital assistant into a high-traffic retail environment, we evaluate its effectiveness in improving the quality of customer service and operational efficiency. Data collected during the experiment demonstrate varied impacts on customer interaction, revealing insights into the future optimizations of digital assistant technologies in customer-facing roles. This study contributes to the understanding of digital transformation strategies within the customer relations domain emphasizing the need for service flexibility and user-centric design in modern retail stores.