Data about our browsing and buying patterns are everywhere. From credit card transactions and online shopping carts, to customer loyalty programs and user-generated ratings/reviews, there is a staggering amount of data that can be used to describe our past buying behaviors, predict future ones, and prescribe new ways to influence future purchasing decisions. In this course, four of Wharton’s top marketing professors will provide an overview of key areas of customer analytics: descriptive analytics, predictive analytics, prescriptive analytics, and their application to real-world business practices including Amazon, Google, and Starbucks to name a few. This course provides an overview of the field of analytics so that you can make informed business decisions. It is an introduction to the theory of customer analytics, and is not intended to prepare learners to perform customer analytics.
Course Learning Outcomes:
After completing the course learners will be able to...
Describe the major methods of customer data collection used by companies and understand how this data can inform business decisions
Describe the main tools used to predict customer behavior and identify the appropriate uses for each tool
Communicate key ideas about customer analytics and how the field informs business decisions
Communicate the history of customer analytics and latest best practices at top firms
From the lesson
Application/Case Studies
How do top firms put data to work? In this module, you’ll learn how successful businesses use data to create cutting-edge, customer-focused marketing practices. You’ll explore real-world examples of the five-pronged attack to apply customer analytics to marketing, starting with data collection and data exploration, moving toward building predictive models and optimization, and continuing all the way to data-driven decisions. At the end of this module, you’ll know the best way to put data to work in your own company or business, based on the most innovative and effective data-driven practices of today’s top firms.
Professor of Marketing, Statistics, and Education, Chairperson, Wharton Marketing Department, Vice Dean and Director, Wharton Doctoral Program, Co-Director, Wharton Customer Analytics Initiative The Wharton School
Peter Fader
Professor of Marketing and Co-Director of the Wharton Customer Analytics Initiative The Wharton School
Raghu Iyengar
Associate Professor of Marketing The Wharton School
Ron Berman
Assistant Professor of Marketing The Wharton School
Well I hope everyone enjoyed the content that I delivered to you.
Just to remind you, I started with this right from the opening and
I've done it entirely through the sides.
Remember the five pronged attack, to apply customer analytics to marketing.
Number one, it always starts with the data.
So one of the things I always talk about,
whether I'm talking to a large firm like Google or Amazon or a small start up.
You have to build your infrastructure to collect the right data.
Or another way to think about it is, in today's world of technology,
if you don't measure it, it's like it never happened.
And that really is the competitive advantage of many firms today.
Better decisions through better data.
And this is why the statisticians like myself, or the marketing analyst,
can't sit in some silo in the back room where the CIO and the CFO
are making one set of decisions, and you're making another set of decisions.
Without the right data, you can't make better decisions through analytics.
Number 2, data exploration.
While it's not just as I talked about during the lectures to validate the fancy
statistical model, how about, you've gotta figure out what you're looking for.
We've all heard the expression, looking for
a needle in a haystack, or just flying blind.
Well, without exploration of the data, you might miss lots and lots of interesting
insights, that you are statistical model would never even tell you to look for.
This isn't a classroom setting.
You have to apply these methods to real problems, and sometimes,
you need to explore the data to find out what might be interesting.
The third part, building predictive models.
So, we talked about a lot of different types of predictive models.
Number one, churn models.
Predicting when a customer's going to leave you.
A very important type of model.
Most people might say,
it's really what led to the blossoming of customer analytics.
And this is whether it's in the insurance industry and they wanna predict,
literally, time of literal death.
Or you're working for a website and
they wanna predict when you're going to churn from the site.
Or even if you're Proctor and Gamble, and
you wanna know when someone's gonna switch from your brand to a competitor's brand.
Churn is one major area, where customer analytics is applied in a predictive
sense, cuz it's always about churning in the future.
Another form of prediction that we talked about is,
prediction your dollar value in the future.
So a lot of people make the mistake of saying, well, I'll look at the past year,
I'll take the average spend that someone has made, and
that'll be their spend in the future.
Well, maybe not.
As a matter of fact, as we talked about, you could make three predictions,
all of which contradict with each other.
One is, well, spending will go down over time,
cuz someone gets very excited once they start with you, and then they decline.
Maybe.
Another prediction could be, well, if someone stays with you,
they're more loyal, and then their spending would go up over time.
That's another prediction.
A third prediction would be,
people that it's your job as the firm to try to maximize that spending.
As a matter of fact, I'm not a believer in number one,
that people are just stationary as we talked about.
I'm not a believer in number two, that people just increase some sort of magic.
It's your job to predict and to optimize people's spending over time.
Number four, optimization.
We talked about lots of forms of optimization.
The most common ones in marketing today, price optimization.
How do you set price customer by customer to maximize the firm's profitability?
Second, something very popular today.
Advertising.
How do you decide, who to advertise to, with what cadence?
All of that is very important.
Three.
Email.
How do you decide which people to contact and when?
All of these things are an important part of a person's toolkit,
who works in customer analytics.
And last, we talk about lots of firm decisions.
Let me talk about and review,
just my favorite one from the lecture slides that you saw.
Probably my favorite one is Amazon.
So we all know about, many of us know about Amazon Prime,
where you not only get free shipping, but they'll ship it to you in one to two days.
But as you remember from the example I gave you,
how would you like it if Amazon could ship to you by the end of the day?
By the end of the given day, if you order by noon,
they'll have the product to you by 5 PM.
Now how do they do that?
They predict what it is you're going to buy, before you every buy it.
Now, they're not gonna ship it to your home before you buy it.
That'd be a little creepy.
But they can ship it locally to near where you are, so
that by the time you order it, they're ready to ship it to you locally.
So again, remember,
if you wanna take anything away from this module, remember the five basic forces.
Better data.
Explore the data.
Predict the future.
Optimize against the future and make actual decisions using it.
If you make empirically based decisions, you'll be better off, and you'll better
off in your boss's mind, and you'll make better decisions in the future.