Grant: Idea to Innovation
McGill University
$51,880.84
Multi-Armed Bandit Technologies for Automated Inventory Management and Pricing Decisions in Food Retail (Phase I)
FY 2022-23
Summary
Despite food retail generating $14TN+ CAD in revenue globally (2021) and helping feed billions across the world, the market segment largely remains reliant on archaic processes. Today, over one-third of all food is thrown away and most food retailers experience low profit margins in the range of 1-3%. Furthermore, supply chain disruptions (delays) often exacerbate financial and operational challenges, especially, for smaller businesses. Amidst rising food prices, improving food retail business efficiency is an economic necessity. Moreover, poor inventory management leads to unsustainable practices such as excess refrigeration, delivery, and food waste, which alone represents 6-8% of global greenhouse gas emissions. Manual optimization is exceptionally difficult due to large complexity, greatly complicated by variable delays between decisions and their outcome. Our goal is to exploit AI technology for inventory and pricing optimization to improve operational sustainability and efficiency.Recently, we developed novel multi-armed bandit methods and a software package to determine optimal decision-making strategies for situations where delay is observed. Billions of simulations validated that our methods can offer over 40% better decision-making performance than traditional multi-armed bandit methods in the presence of delay. The methods work by evaluating possible decision outcomes and using them to calculate expected outcomes.The NSERC I2I grant will allow us to augment and validate our technology in a real market scenario in food retail to better address retail customer needs. Our technology will improve both human-in-the-loop and autonomous decision-making for sustainable inventory management by providing effective recommendations and explanations concerning purchase amounts and pricing (including discounts for consumers). This will lead to improved margins in food retail and lower prices for consumers, as well as more sustainable practices which minimize food waste, cut down on unnecessary deliveries, and reduce energy consumption.
Program
Idea to Innovation
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
576543-2022
Name nom
Varro, Daniel D
Department département
Computer Science
Organization id
61
Institution établissement
McGill University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2022
Competition year année de concours
2022
Award amount
51880.84
Program id
I2IPJ
Program name en
Idea to Innovation
Program name fr
De l'idée à l'innovation
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
900
Area of application group en
Commercial services
Area of application group fr
Services commerciaux
Area of application en
Commercial services
Area of application fr
Services commerciaux
Research subject code
2800
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Artificial intelligence (computer vision, use2603)
Research subject fr
Intelligence artificielle (vision artificielle, utiliser 2603)
Installment
inst:1
Partie
1
Nb partie
1
Application title
Multi-Armed Bandit Technologies for Automated Inventory Management and Pricing Decisions in Food Retail (Phase I)
Application summary
Despite food retail generating $14TN+ CAD in revenue globally (2021) and helping feed billions across the world, the market segment largely remains reliant on archaic processes. Today, over one-third of all food is thrown away and most food retailers experience low profit margins in the range of 1-3%. Furthermore, supply chain disruptions (delays) often exacerbate financial and operational challenges, especially, for smaller businesses. Amidst rising food prices, improving food retail business efficiency is an economic necessity. Moreover, poor inventory management leads to unsustainable practices such as excess refrigeration, delivery, and food waste, which alone represents 6-8% of global greenhouse gas emissions. Manual optimization is exceptionally difficult due to large complexity, greatly complicated by variable delays between decisions and their outcome. Our goal is to exploit AI technology for inventory and pricing optimization to improve operational sustainability and efficiency.Recently, we developed novel multi-armed bandit methods and a software package to determine optimal decision-making strategies for situations where delay is observed. Billions of simulations validated that our methods can offer over 40% better decision-making performance than traditional multi-armed bandit methods in the presence of delay. The methods work by evaluating possible decision outcomes and using them to calculate expected outcomes.The NSERC I2I grant will allow us to augment and validate our technology in a real market scenario in food retail to better address retail customer needs. Our technology will improve both human-in-the-loop and autonomous decision-making for sustainable inventory management by providing effective recommendations and explanations concerning purchase amounts and pricing (including discounts for consumers). This will lead to improved margins in food retail and lower prices for consumers, as well as more sustainable practices which minimize food waste, cut down on unnecessary deliveries, and reduce energy consumption.