Company: Canada Revenue Agency (CRA)
Company background: Canada's federal tax administration and enforcement agency, with approximately 42,000 employees, the vast majority of which reside in Ottawa, Ontario.
Contact: Jason Andrew Oliver
Title: Senior Compliance Analyst and Data Scientist
Country: CANADA
Award Category: Professional Growth Award
Tell us how you or your team have used SAS training resources to learn a new skill or answer your questions?
I studied the SAS Text Mining and Analysis – Practical Examples book, to learn how to do TMA (Text Mining & Analytics) in SAS Ent. Miner, including text topic modeling and clustering. This resource proved invaluable for text-mining leads received from tipsters, and training predictive TMA models.
How has what you learned benefited your work or career? How has training advanced your team's success using SAS?
The study and application of TMA has allowed me to create custom text topic models (in SAS Ent. Miner) to categorize tipster/leads text into categories of non-compliant behaviour, to ultimately pair this with more traditional risk assessment formulas.
What was your/your team's favorite course, resource or learning engagement?
I would say the two GALFs (Gov't Analytics Leadership Forum) of autumn 2022; the first was held in person in Ottawa, all about privacy / AI&ML ethics and the second was to do with the push to the Cloud and SAS Viya, from a public sector perspective.
How have you used SAS resources to train your team?
We developed our own custom CRA-oriented SAS Viya package in early 2021, and gave two pilot virtual training sessions to ~75 people across the country in May-June 2021. We continue to offer this training. We included hands-on exercises with answer keys, to improve knowledge retention.
How has this benefited your organization? Can you quantify any of the benefits?
This has helped my organization advance their data culture, which is one of their strategic imperatives, and created an impetus for moving up on the AMM [Analytics Maturity Model], promulgated by the OECD FTA - of which our Commissioner is the Chair.
What advice would you give to new SAS users?
Look at SAS solutions as complementing, not "competing" with each other. See them as modular; regard them as part of a "data supply chain". For instance, I use SAS Ent. Guide for descriptive and inferential stats; then I use Viya for log reg and dec. trees.
