º£½ÇÉçÇø

Modelling of shoppers’ attention patterns and behaviour in convenience stores

We wish to model the behaviour of shoppers searching for a specific product (or set of products), as indicated by which product(s) they purchase. We propose to use shopper body pose/skeleton information to identify specific activities, such as turning to view an item on a shelf, reaching for items, putting objects back, moving around obstacles, exploratory movements vs. direct homing in on product locations. We will use eye-tracking, in a controlled study, to determine what places in the store and which objects people look at when searching for specific products. We will model and detect cases of distraction, where shoppers are affected by (viewing or reaching for) items that they do not buy. We will analyze behaviour of shoppers doing foraging, which is the collection of multiple articles. Do they optimize the path between purchased articles, or do they do independent search patterns for each individual product? We will also investigate whether shoppers’ attention patterns can be clustered into groups, allowing personalized models to be created.

Graduate students from the Department of Electrical and Computer Engineering

Yinan Wang - PhD
Farzaneh Askari - PhD
Rezvan Sherkati - PhD
Xiangyu Li - MSc
Sansitha Panchadsaram - MSc

Principal Investigator: James Clark

Adapting retail practices to the post-pandemic landscape

Graduate student internship supported by Mitacs via the Accelerate program

The pandemic has impacted consumer behavior dramatically by spending less time shopping, shopping in larger quantities and minimizing physical contact. In this project, the MRIL will be working with Alimentation Couche-Tard to understand and predict the current behavior of customers to help them adapt their retail practices to the post-pandemic world. By leveraging both historical (pre-pandemic) and present-time data (during and post-pandemic), researchers at the MRIL will develop state-of-the-art machine-learning and artificial intelligence algorithms. More specifically, novel demand forecasting, tracking and influencing methods (e.g., nudging interventions, sending app notifications to customers) will be tested in terms of prediction accuracy and their possible application to personalization purposes. The main objective is to identify key features related to purchasing behaviour that can help retailers better predict customer demand in these uncertain times. 

MSc student from the Department of Electrical and Computer Engineering

Niloofar Tarighat

Student co-supervisors: Maxime Cohen and James Clark

Retail innovation lab: data science for socially responsible food choices

IVADO-funded project

Led by a multidisciplinary team, this project will apply artificial intelligence techniques to study, implement, and validate systems for guiding customers to make healthy food choices in a convenience store setting, while being cognizant of privacy concerns.

PhD student from the Department of Electrical and Computer Engineering

Rezvan Sherkati

Student co-supervisors: Maxime Cohen and James Clark

Planogram Optimization

IVADO-funded project

We aim to identify the effect of product location on demand. In particular, we are interested in the impact of the vertical location of the products on sales. To do so, we are running an experiment over six Couche-Tard stores. The insights of the project can provide guidelines for the practitioners on how to design the planograms and how to determine the reservation value of the spaces in the store.

PhD student from Desautels Faculty of Management

Zahra Jalali

Student co-supervisors: Mehmet Gumus and Maxime Cohen

Healthy Choice Nudging

How can retailer incentivize customer to make healthier food choices? Price, convenience, and taste are known to be among the main drivers behind such choices. Unfortunately, healthier food options are often expensive and infrequently promoted. Recent efforts in deploying healthy nudges to incentivize customers toward healthier food choices have been observed. We conducted a field experiment with a global convenience store chain to better understand how different add-on bundle promotions influence healthy food choices. We considered three types of add-on bundles.

1. An unhealthy bundle (when customers purchased a coffee, they could add a pastry for $1). 
2. A healthy bundle (offering a healthy snack as an add-on),
3. a choice bundle (offering either a pastry or a healthy snack).

In addition to our field experiment, we conducted an online lab study to strengthen the validity of our results.

PhD student from Desautels Faculty of Management

Nymisha Bandi

Student co-supervisors: Saibal Ray and Maxime Cohen

Data visualization and social distancing

This project aims to reconstruct the customer shopping journey and identify the busiest zones of the store by analyzing point-of-sales data and camera-tracking trajectories (anonymized and privacy-preserving). Such valuable information will help retailers re-organize the store planogram to satisfy desired requirements, such as social distancing.

Undergraduate students from the Department of Electrical and Computer Engineering

Maxime Cardinal
Alexis Franche
Alexa Normandin
Oliver James Murphy

Student co-supervisors: Derek Nowrouzezahrai and Maxime Cohen

Developing an augmented reality app for cellphones that could be used in convenience stores

The goal of the project is to design and implement an IOS App (Apple) with Augmented Reality technology for the Couche-Tard store at º£½ÇÉçÇø. This will allow commodity product recognition using computer vision and display of associated product information. The project will involve development of software, programs to do 3D object scanning, creation of an object database, and object detection, as well as design of the user interface. The various parts of the system will be integrated in a single package.

Undergraduate students from the Department of Electrical and Computer Engineering

Chen Liu
Yuelin Liu
Xinran Li
Xiangyu Li

Student supervisor: James Clark

Visual Product Search

The goal of this project is to design a mobile app that leverages modern deep learning-based computer vision image classification algorithms. The app will allow customers to identify a product -- given an image of the item taken from the customer's smartphone, while in the store -- and provide a summary of the product (i.e., nutritional information, price, etc.)  Additionally, customized features will be included to enhance the user’s shopping experience.  Some examples of possible features include: product recommendations, budgeting tools, and dietary restriction verification.

Undergraduate students from the Department of Electrical and Computer Engineering

Brad McBain
Sami Hilal
Ragheed Qasmieh
Brendan Marks

Student co-supervisors: Derek Nowrouzezahrai and Maxime Cohen