A recommender system for Pingo Doce & Go Nova
Miguel Ângelo Salgueiro Bezerra · New University of Lisbon's Repository (New University of Lisbon) · 2021
Using the Design Science framework, and acknowledging the success of recommenders in e-commerce settings, this paper proposes the design and implementation of a recommender in a physical retail store(Pingo Doce & Go Nova). It allows to assess if the recommender can influence customers’ decisions, increase sales, the number of unique products acquired, and understanding the customers. To develop it, the data was collected, curated, recommendation strategies were designed (loyalty, novelty, and related) and the customers were split into groups. The recommender will be deployed in the storeapp and, after, the results from the metrics will be analyzed.