Air Canada is the largest provider of scheduled passenger services in the Canadian market as well as in the Canada-U.S. transborder and the international markets to and from Canada. We carried more than 37 million customers in 2022, to 185 direct destination world-wide. This represents close to 1,000 flights daily.The company grew to close to 36,000 active employees in 2022.
Aeroplan’s membership has already exceeded its 7M active members target. The Customer & Loyalty Analytics team has the privilege to aim at better understanding these customers and Aeroplan Member behaviours so that we can serve them better!
Best Acceleration Use Case
Best Data Democratization Program
Best Approach for Building Trust in AI
The Customer and Loyalty Analytics Team works closely with our Marketing Team in order to design and run route marketing campaigns, so that flights are fully booked.
Before each campaign that will promote a given destination (or set of destinations), there is a need to understand who are the customers who have travel there before, what audience is the most likely to be interested in travelling there in the future, and what is the profile of that target audience so that we can communicate with relevancy. Over and over, the C&L Analytics Team would run these analyses, destination recommender systems, and standard profiles on an ad hoc, campaign by campaign, basis.
Since the input from our Marketing Stakeholders is quite minimal (e.g. destinations, booking dates & travel dates), and that algorithms were already developed, this process was a recipe approach and not the best usage of Data Scientist time.
There was a potential for automating and consolidating all these advanced analytics processes and standardizing the outputs to gain efficiency.
We leveraged Dataiku’s visual flows and apps in order to generalize, parametrize, automate, and consolidate these processes.
The final product is an app that allows our Marketing Stakeholders to trigger these processes by themselves by entering the required destinations, booking dates, and travel dates in the app and push the run button.
Descriptive analytics are then automatically run to understand the previous audience and set our baseline. Then, the recommender system will identify who will likely be interested in traveling to these destinations, and a standard profile will be created to better understand who these customers are.
Once processes are run, all outputs are being showcased in the app and in a PowerBI Dashboard, including all potentially interested customer targets, who they are, their travel behaviours, and how they interact with us, so that Marketing can run a targeted campaign – without direct Analytics intervention.
Our Marketing Stakeholders have quicker access, in a self-serve mode, to more Route Marketing pre- campaign Insights, on more campaigns (given scalability) to enable enhanced design and targeting.
By automating the tasks, Data Scientists can focus on more added value projects, like enhancing performance of the destination recommender system or building new signals that will feed into the standard profiles as profiling variables, with the goal of increasing relevancy of our marketing communications.
Business Area Enhanced: Marketing/Sales/Customer Relationship Management
Use Case Stage: In Production
Marketing stakeholders now have access to target audience insights, on-demand, on a self-serve mode, as soon as they need it, without depending on the C&L Analytics Team backlog. The process used to take several weeks of back-and-forth between the two teams.
This quicker access to insights empowers them to make better design decisions for upcoming campaigns.
Opportunity cost saving: our Data Scientists now have more time to invest in more added value projects!
Value Brought by Dataiku:
Dataiku enabled the orchestration of the processes, allowing us to automate, create the flow, and build a business user interface with a Dataiku App , in order to put the trigger in the hands of our marketing stakeholders.