Unilever Canada, SOSCIP & Mitacs: A Dynamic Trio

The dynamic partnership of SOSCIP and Mitacs continues to accelerate the pace of sustainable business growth of Unilever Canada Inc. in Ontario by identifying and securing top talent with expertise in machine learning and AI to support their business teams in making faster and better decisions.

Through their investment and active participation with SOSCIP & Mitacs, Unilever Canada has taken a leading role in establishing itself firmly at the crossroads of research and innovation. With SOSCIP’s and Mitacs’ ability to connect industry to academic expertise, talent, and compute resources, Unilever has been able to leverage a variety of internal and external data sources to reveal patterns and new connections of market behaviour through engagement with its products and purchasing habits. The ability to recognize and explore these patterns, especially after the unexpected trends created by the pandemic, is critical for the success of business units across Unilever Canada.

By tapping into the data analytics, machine learning, and optimization expertise available in academia, Unilever has been able to complement their in-house data science expertise to build and augment their data models and develop recommendations for their business teams. Drawing on decades of experience with leading academics, SOSCIP and Mitacs helped mature Unilever Canada’s relationships with Toronto Metropolitan University (previously Ryerson University), Western University, University of Ottawa, and the University of Toronto. These collaborations started in 2017 with a series of short projects that saw a total investment of over $400,000 from Unilever Canada and Mitacs, compute resources provided by SOSCIP valued at over $500,000 in the last 5 years. These collaborations have already made a significant impact to the Data and Analytics team at Unilever Canada and enabled new partnerships that allowed Unilever Canada to build on past successes.

“Unilever Canada is currently leveraging the Mitacs Accelerate program and SOSCIP compute resources at a much bigger scale than ever before,” says Gary Bogdani, Head of Data and Analytics for Unilever Canada.  On the strength of SOSCIP’s and Mitacs’ relationships with the academic community in Ontario, Unilever has identified and worked with fourteen researchers over the last five years. On the latest project that started in 2022, Unilever Canada will invest close to $400,000 this year alone and bring in eight researchers from multiple academic institutions across Canada to work on various areas of product, customer and market intelligence. SOSCIP will also be providing its compute resource for the project valued at $53,000 over the next year.

Alongside curated partnerships and access to relevant expertise, the collaborations with academia have enabled Unilever Canada to create a talent pipeline. “Unilever Canada is now more able than ever to find the right people to help grow sustainably and with confidence,” says Bogdani. “We have put in the investment to really embed ourselves in the academia and throughout the innovation ecosystem,” says Bogdani, whose Data and Analytics unit is a central component of Unilever Canada’s success story. “We know that by directly engaging the next generation of talent we’re ensuring we stay ahead of the curve in areas of strategic interest to our business.”

 

About Unilever

Unilever is one of the world’s leading suppliers of Beauty & Personal Care, Home Care, and Foods & Refreshment products, with sales in over 190 countries and products used by 3.4 billion people every day. Unilever has around 400 brands found in homes all over the world. In Canada, the Unilever portfolio includes brand icons such as: Axe®, Ben & Jerry’s®, Breyers®, Degree®, Dove® personal care products, Hellmann’s®, Klondike®, Knorr®, Magnum®, Nexxus®, Popsicle®, Schmidts®, Seventh Generation®, Shea Moisture®, TRESemmé®, and Vaseline®. All of the preceding brand names are owned or used under license by Unilever Canada Inc. For more information, visit www.unilever.ca.

 

About SOSCIP

Launched in 2012, the SOSCIP consortium is a ground-breaking collaboration between Ontario’s research-intensive post-secondary institutions and industry members across the province.

Working together with our partners, SOSCIP is driving the uptake of AI and data science solutions and enabling the development of a knowledge-based and innovative economy in Ontario by supporting technical skill development and delivering high-quality outcomes.

SOSCIP supports industry-led research projects through partnership-building services and access to leading-edge advanced computing platforms, fueling innovation across every sector of Ontario’s economy.

 

About Mitacs

Mitacs is a national, not-for-profit organization that has designed and delivered research and training programs in Canada for 20 years. Working with an extensive network of postsecondary partners, and both federal and provincial governments, we build collaborations that support industrial and social innovation in Canada. Mitacs has worked with thousands of private sector and not-for-profit organizations as well as 78 universities and 77 college, CÉGEP and polytechnic partners to fuel strategic relationships that power Canadian innovation excellence.

To learn more about the organization, please visit https://www.mitacs.ca/en.

 
 

Specific details on the industry-academic collaborative projects referenced in this article can be viewed below:

(2017) Social Media Impact Tool: Measuring ROI for Social Media Engagement

Overview: Currently there are no effective tools to capture and measure return on investment (ROI) in social media in conjunction with more traditional data points that come from sources such as Flyer Tracking and Point of Sale (POS) systems. Using visual analytics techniques, this project will develop and evaluate a set of ROI metrics that will incorporate available data points about shoppers and their purchasing patterns and will help Unilever Canada to (1) understand shoppers’ online behaviour, (2) reveal causal links between social media engagement and purchasing habits, and (3) establish effective ROI metrics for social media engagement.

 

(2018-2019) Improved Commentary Prediction on Financial Data

Overview: Companies rely on financial reports which are generated through various transactions to understand the discrepancies between actual performance and financial forecast. Accordingly, generating commentaries on financial data might be considered as a routine operation for many companies. Unilever proposes the development of a graphical user interface to allow end-users to interact with the model. We propose to improve the developed model in various ways: enhance the learning process, develop highly accurate models, investigate time series classification approaches with deep neural networks, apply natural language processing techniques to process commentaries, etc.

 

(2018-2019) Trade promotion forecasting and optimization

Overview: The first output of this project will be to develop and evaluate models that statistically predict the impact of Unilever promotions on category and product share across different retailers. This effort will lead to the creation of trade promotion optimization techniques that enables planning of promotional activities. The second output is to simulate potential outcomes of various combinations of promotional programs across different retailers in such a way as to inform investment decisions early in the planning process. Finally, the project aims to develop a systematic approach for allocation of promotional spend that permits continuous adjustment as market and competitor conditions change.

 

(2019-2020) Demand estimation in consumer-packaged goods market using BLP method

Overview: Leveraging the entirety of point of sale and loyalty data collected across a category, as well as additional socio-economic and other supporting data sources, apply statistical modelling to identify the own-price elasticity of demand and cross-price elasticity of demand at regular and promoted price points across Unilever’s portfolio within that category. Subsequently measuring the promotional cannibalization of Unilever’s temporary price reduction activities across the market to assess the promotional events with the highest return on investment and revenue optimization potential.

 

(2020-2021) Unilever Canada Collective Intelligence Platform

Overview: Project “Prophet” aims to build a demand forecasting pipeline that collects data and applies machine learning models to make accurate predictions of future demands under unstable scenarios. In particular, this project will focus on efficient forecast of Unilever’s base SKUs and involve model development based on time-series, machine learning and possibly combinations of the two, data engineering to identify critical features hinting future trends, and deployment of the models to the existing business process. The Machine learning-based demand forecasting for supply chain optimization method will be integrated in the Collective Intelligence (CI) program of Unilever Canada.