The Business Challenge
Purolator is a progressive company and values continuous improvements and innovation approaches to improve its Supply Chain efficiencies, leveraging advanced analytics and AI approaches. With over 13,000 employees throughout North America, Purolator has over 175 operational facilities, 104 shipping centers, over 1,300 shipping agents, and over 215 Drop Box locations to support its client’s shipping needs. The company has a large fleet of courier vehicles, with over 323 hybrid-electric vehicles, 3,388 courier vehicles, 185 straight trucks, 491 trailers, 1,158 highway trailers and 462 tractors. Needless to say, the company has a high volume of daily shipments ranging from domestic to regional to national, including light to bulky shipments, and even handling dangerous goods. Ensuring packages are routed efficiently to the nearest shipping centers requires managing a large fleet of courier drivers, and shipping operations. Developing cost effective and efficient customer pricing strategies to ensure operating margins are efficiently managed when one has hundreds of thousands of shipments is a big data challenge.
Purolator’s CFO, Roslyn Samtleben, and CIO, Ricardo Costa, wanted to explore how AI and Advanced Data Analytics could be used to predict variable operating margin (VOM) and appreciate if AI could predict fail points in current operating systems or augment loss making shipment insights that could be predicted earlier and be able to shore up insights to guide both operating and revenue teams to have a window for earlier improvement call outs.
The Solution
SalesChoice worked with the Purolator’s internal Revenue Operations Team, reporting to Marketing and the AI Data Sciences and Analytics, reporting into the Information Technology organization, and the Finance Team, reporting into the CFO to determine if AI methods could be used to predict Variable Operating Margins (VOM), by analyzing all shipment and costing data over the past two years. SalesChoice was engaged to complete the following outcomes:
• Support the data lineage practices by assessing current state and developing a data lineage accountability and process ownership framework,
• Conduct research on AI Data Governance Frameworks to guide Purolator using AI proven best practices,
• Collect and validate the data sources could be used to solve this use case challenge.
• Build a customized AI model to support this use case
• Develop PowerBI visualizations to support a demonstrateable POC use case to advance AI modelling infrastructure(s) and asset management practices
• Advance AI Model into enhanced simulation enablements and production engineering requirements.
“Our brand is anchored in Ending Revenue Uncertainty, using AI,” says Dr. Cindy Gordon, CEO and Founder, SalesChoice Inc. “There are a lot of black box AI approaches in the market, and we wanted to ensure that our clients could trust our AI Data Science as a Service (DSaaS) AI modelling skills so we always start our AI Data Sciences client projects start with a data lineage and data confidence/quality/completeness review to ensure the Big Data AI projects can secure the desired outcomes that our clients are seeking to achieve. We also ensure we transfer our transfer consistently throughout our client engagement solution delivery practices so we are known for our depth in statistical analytics and research reporting to help educate our clients during the AI model build and value realization stages. We follow a strategic framework for advancing our Data Sciences as a Service (DSaaS) practice offerings.”
To end sales inefficiencies & revenue uncertainty, book your personalized demo to learn how we can save your company precious time, build your company an integrated Customer Relationship Management platform and advance your company into the Age of Data Sciences.
