What is it about?
In this paper we compare several machine learning algorithms for the task of next shopping basket recommendations to users. The Recommender System that obtained the best results is currently being used on a website that allows users to create cross-stores shopping lists and figure out the shortest and cheapest (if using a car) path to fulfill the list.
Featured Image
Photo by Viki Mohamad on Unsplash
Why is it important?
Next basket recommendation is a critical task in market basket data analysis. It is particularly important in grocery shopping, where grocery lists are an essential part of shopping habits of many customers. In this work, we first present a new grocery Recommender System available on the MyGroceryTour platform. The main advantage of the presented Recommender System is that our intelligent recommendation is personalized, since a separate traditional machine learning or deep learning model is built for each customer considered. Such a personalized approach allows us to outperform the prediction results provided by general state-of-the-art deep learning models.
Perspectives
One of the limitations of our approach lies within the platform itself. Indeed, MyGroceryTour does not allow people to buy the products directly. Thus, we have no assurance that the users actually bought the items included in their grocery lists. We also cannot track stocks indifferent stores to potentially notify the users of shortages prior to adding products to their grocery lists. Our Recommender System is also sensitive to the cold start problem and it is not yet able to predict the exact quantity of each item recommended for inclusion to the user’s next basket. We plan on addressing these limitations in our future work, in which we will also explore the impact of seasonality on grocery shopping habits, which could lead to improved recommendations as well
Nail Chabane
Universite du Quebec a Montreal
Read the Original
This page is a summary of: Intelligent personalized shopping recommendation using clustering and supervised machine learning algorithms, PLoS ONE, December 2022, PLOS,
DOI: 10.1371/journal.pone.0278364.
You can read the full text:
Contributors
The following have contributed to this page
