Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
The Great AI Myth: These 3 Misconceptions Fuel It
 Originally published in Forbes, July 29, 2024. The hottest thing...
How to Sell a Machine Learning Project
 Originally published in Built In, February 6, 2024. Never...
The 3 Things You Need To Know About Predictive AI
 Originally published in Forbes, June 29, 2024. Some problems are...
Alphabet Uses AI To Rush First Responders To Disasters—Takeaways For Businesses
 Originally published in Forbes, July 7, 2024. The National Guard...
SHARE THIS:

9 years ago
Wise Practitioner – Predictive Analytics Interview Series: Rebecca Pang at CIBC

 

In anticipation of her upcoming conference presentation, Rebecca Pang imageDriving the Omnichannel Experience with Predictive Analytics at Predictive Analytics World San Francisco, April 3-7, 2016, we asked Rebecca Pang, Senior Director, Channel Strategy & Analytics at CIBC, a few questions about her work in predictive analytics.

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

A: With customer delivery and communication channels expanding, it is increasingly important for banks to engage the customers better and more efficiently by creating the kind of omni-channel experience that fit customers’ needs. We use predictive analytics (when combined with test and control) to predict client’s transaction behavior and financial implications by varying a number of levers to see which lever is most impactful.

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

A: Making changes in a network of >1000 branches with thousands of frontline staff can be costly. Using predictive analytics, we are able to test ideas rapidly and efficiently, evaluate results, pin-point success drivers, revise initiatives and predict results on a wider rollout. We have been using predictive analytics and test and control on various channel and sales initiatives.

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

A: In a particular pilot, we have achieved certain % of sales increase within a couple of months of conducting a number of sales and marketing levers. By segmenting what areas and what types of branches reacting or performing the best (say sales increase), we were able to estimate the impact would be for a wider rollout or how we should prioritize the roll out.

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

A: Often times we launch a pilot with an expectation that certain drivers (e.g., certain customer segments, certain branch characteristics, certain demographics factors) will react better than others based on common sense or conventional wisdom. Through a well-designed test, we were able to uncover surprising drivers (some are casual and some are likely not). With such discovery, we were able to refine the model objectively without relying on gut-feel.

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

A: The importance of developing the analytic muscle and test and control culture with internal information and online activity to understand behaviors and profiles of customers with a true 360 view (not only who they are, and what they do).

——————–

Don’t miss Rebecca’s conference presentation, Driving the Omnichannel Experience with Predictive Analytics on Monday, April 4, 2016 at 2:40 to 3:25 pm at Predictive Analytics World San Francisco. Click here to register to attend. USE CODE PATIMES16 for 15% off current prices (excludes workshops).

By: Eric Siegel, Founder, Predictive Analytics World

Eric Siegel is the founder of Predictive Analytics World (www.pawcon.com) — the leading cross-vendor conference series consisting of 10 annual events in New York, Chicago, San Francisco, Washington DC, London, and Berlin — and the author of the award-winning book, Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die – Revised and Updated Edition, (Wiley, 2016).

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.