Machine Learning Times
Machine Learning Times

1 year ago
Wise Practitioner – Predictive Analytics Interview Series: Richard Boire at Boire Analytics


By: Eric Siegel, Program Co-Chair, Predictive Analytics World for Financial

In anticipation of his upcoming conference presentation at Predictive Analytics World for Financial Las Vegas, May 31-June 4, 2020, we asked Richard Boire, President at Boire Analytics, a few questions about their deployment of predictive analytics. Catch a glimpse of his presentation, Human vs. Machine: Data Scientists Aren’t Going Extinct, and see what’s in store at the PAW Financial conference in Las Vegas.

Q: In your work with predictive analytics, what behavior or outcome do your models predict?

A: In the many years that I have been developing and deploying predictive models, there are numerous outcomes or behaviors that have been predicted. The variety of these outcomes depends of course on the business problem we are trying to solve. But during my career, I have focused on customer or consumer type models both in marketing as well as risk. This has allowed us to develop tools which look at predicting customer profitability.

Q: How does predictive analytics deliver value at your organization — what is one specific way in which it actively drives decisions or operations?

A: For marketing, it’s all about cost efficiency as we strive to improve response rates both digitally and non-digitally. Can I reduce the marketing cost per customer or web visitor and yet still achieve my revenue objective.

Q: Can you describe a quantitative result, such as the predictive lift of your model or the ROI of an analytics initiative?

A: One of my very first predictive models for a Canadian bank before they hired all their data scientists delivered $120K in additional profit for one campaign. The bank typically runs close to a hundred marketing campaigns a year. Obviously these results provided the main impetus in the bank developing its own internal data science competency. In insurance, our risk models for automobile insurance created better pricing strategies which allowed these companies to significantly reduce their loss ratios.

Q: What surprising discovery or insight have you unearthed in your data?

A: With all the attention now paid to AI or deep learning, we have done much research by comparing traditional type models to deep learning type models but within our domain area of consumer behavior/customer behavior. Our results are mixed as one would expect. AI needs tremendous volumes of data and strong data patterns or what is often referred to as a strong signal to noise ratio. In many of our models, both these conditions are not met and traditional models perform just as well. Yet, there are cases where we had large volumes of data (fraud and risk models) and where we demonstrated that AI models produced superior results.

Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.

A: Automation and machines will continue to improve and replace many of the tasks currently being done by the data scientist. But the role of the data scientist will evolve into an even more significant and important role within the organization. Why? Demand for generalists and hybrids as data scientists versus specialists will be the real need in an increasingly automated environment.


Don’t miss Richard’s presentation, Human vs. Machine: Data Scientists Aren’t Going Extinct, at PAW Financial on Wednesday, June 3, 2020 from 11:40 to 11:40 AM. Click here to register for attendance.

By: Eric Siegel, Program Co-Chair, Predictive Analytics World for Financial

This content is restricted to site members. If you are an existing user, please log in on the right (desktop) or below (mobile). If not, register today and gain free access to original content and industry news. See the details here.

Comments are closed.