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: Curious Thinker
Tell us how you are inspired by the work you do?
That I have the opportunity to supplement the conventional with the unconventional when it comes to tax compliance analytics insights. I also derive a good deal of inspiration from the OECD FTA publications, which cover tax analytics anecdotes from overseas - and I think of SAS as an enabler.
How has SAS played a part in your journey?
SAS stoked my passion for lifelong learning, even post SAS certification in 2020, I obtained my CFE (Certified Fraud Examiner) in 2021, followed by my INFORMS CAP. I was inspired by what Carl Hammersburg (SAS Seattle) did for fraud analytics with SAS. This is integral to the type of work I do.
What products do you use and how do you use them?
I use SAS Viya to do categorized log reg and dec. tree modeling (i.e. by region, or by taxpayer segment), I use SAS Ent. Guide for descriptive and inferential stats, and I use to SAS Ent. Miner for deep learning and model comparison. I also use SAS-DataFlux for auto-matching of third-party data.
What is your greatest lesson learned that you'd like to share with others?
Strive for the most parsimonious and explainable model – chances are that your audience, the people you need to persuade, will be laypeople - and will not be so “wowed” by fancy deep learning (neural net) dissections. Just like you wouldn't pepper your slide deck with overly elaborate graphs. Occam!
