eCommerce Analytics

While working on a proposal the other day for a prospective customer, I decided that I’d go the extra length for him in an attempt to demonstrate where exactly the company could make up some ground in its effort to realize a bit more bang for its buck in its email marketing program. That is, the company wanted to make more money from its existing customer base. When I looked at the company’s email marketing statistics, I was surprised to find that their clickthroughs per purchase was much higher than any company I’d seen.

Read Clickthroughs Per Purchase is the Gold Standard for Targeted Email »

The blogosphere is awash in tips for doing email targeting.  Some are good (almost anything advocating testing email performance) but some are just flat out wrong.  Here are three commonly held tenets of email targeting that you should ignore.

Read 3 Email Targeting Myths »

One question that we constantly come up against is why online retailers shouldn’t blast their entire customer base with every email promotion they create. Granted, most companies use some form of segmentation to track email responses (the usual 0-12 month buyers vs. 12-24 buyers is a common example) , but besides being defined by arbitrary recency and monetary spend cut-offs, these groups have no real bearing how the customers contained in those groups will respond to a given ad. My colleague Matt wrote a nice entry about this back in July (see Does your email response rate depend on how many emails you send?), but I recently came across some new metrics that I think help drive the point home.

Read Timing and targeting: why you shouldn’t blast all your customers with every offer »

Just finished getting through the backlog of my Don Dodge RSS feed today and I’m happy to report that venture capitalists seems to think that businesses like Istobe are about to break out. Let me qualify that. Venture capitalists seem to think that using data to improve e-commerce is an industry that clearly needs some maturing and that maturing time is nigh. Istobe represents that maturing, combining hundreds of models and data integration routines into a package that lets you target the right customer with the right product at the right time.

Investors believe that the maturation in this industry will occur in the next five years. Well, so does Istobe. We believe that it’s time to put your data to use. If you don’t use it, data is no more than the new shelfware: that software you just had to have before you realized you lacked the in-house talent to unlock its value. Istobe is your outsourced in-house data analysis talent that lets you ask simple questions and get answers without analysis, questions like: I need to sell this overstock of shirts, to whom should I market them? In reply, Istobe gives you a list of your customers that are most likely to buy your shirts and the probability that they will buy. This is the new paradigm in predictive modeling that Gartner calls the data mining packaged application. Let’s just take a quick look at the moment in time at which we are poised.

Data collection methods are clearly refined

Nowadays, everyone is sitting on a pile of customer data that they don’t know what to do with. As Rob Hayes, partner at First Round Capital, says in the Stefanie Olsen article from which Dodge draws his inspiration, “Everyone talks about all the data that’s being created and how valuable it is, but the way you make it available is by doing something actionable with it.” The glut of data is due, in part, to years of CRM implementations and the current CRM zeitgeist. You can’t turn around without being inundated by a flood of marketing for “next generation” CRM systems. In fact, I used to be one of those marketers at a not-too-small company that builds Dynamics CRM.

Of course, online everything has made data more prevalent as well. Returning some kind - any kind - of functionality in exchange for your profile is no longer new hat. Every widget and social network known to man requires you to divulge information before you start using it. And then it collects your clickstream as you use the app. Heck, I’ve got at least 50 different login/pass pairs that I need to remember now.

Purchases, as well, fall into this category. With online shopping increasing at a terrifying clip, all of your purchases are more seamlessly collected and tied to your profile and your clickstream, meaning that now, more than ever; pre-purchase behavior and purchaser characteristics - on a large scale - are at a marketer’s fingertips.

Data analysis tools have matured but haven’t turned the corner

So there are various types of data out there right now that need tying together and, ultimately, analysis. But have the tools to merge and make sense of that data improved? Not appreciably. Really, when you get right down to it, the tools used to perform data analysis are still catch-all tools that can build any model you want or merge any type of data you want. But they can’t help you with specific business problems. In other words, the tools exist for database experts (data integration) and PhD statisticians (statistical modeling tools).

For years, these tools have gotten easier for experts to use but haven’t gotten any easier for business users. This means that your $300K worth of in-house data integrators and PhD statisticians have become slightly more productive over time but translating their language into the language of business is as difficult as ever. And turning the data they spit out into a meaningful business strategy is just as tough.

With today’s news that the retail sector is experiencing a slowdown, now is a better time than ever for multi-channel retailers to do two things: turn to cheaper forms of advertising (email) and use quick-return customer analytics to compete with gargantuan discounters like Wal-Mart that threaten to swallow retail whole. The truth is that Wal-Mart will continue to invest in analytics during the tough economy because they will see immediate ROI from understanding which customers are poised to buy, which items they want, and how much those customers are willing to spend. I can think of two, good reasons for smaller multi-channel retailers to follow suit.

Harvest your current customers
Most would say that the thick of a poor economy is a poor time to invest in new marketing projects. If these projects are tied to new customer acquisition, I might agree. It’s damned expensive to acquire customers and you tend to forget what you already have while you’re out prospecting, buying lists, etc. Sometimes, the answer is in front of you. In a poor economy, isn’t it imperative that you retreat to your base? Multi-channel retailers need to figure out ways to:

A. Not lose your current customers to competition (like Wal-Mart)
B. Harvest your existing customers by making them feel as though you understand them

Really, achieving B is the answer to question A. A redoubling of your customer service effort will always make your customers more loyal and less likely to jump ship. But we have to remember that larger players can always offer deeper discounts in an effort to combat your superior customer understanding. One way around this is to deepen your customer understanding on the marketing front with timely, personalized emails to your customer base. Ultimately, if you can address your customers’ needs first - make your customers offers at the cusp of when they need those products - then you are likely to win their business. This is the advantage that predictive models based on your customers behaviors provide you: the ability to beat your larger competition on timing as opposed to discounting.

Quick ROI
Customer analytics like those that Istobe proposes are great because the analysis takes advantage of data that you, as a multi-channel retailer, already possess. You’ve already got a record of your cusotmers’ purchases. In other words, there is no up-front infrastructure or talent investment. What this ultimately means is that your ROI emerges quickly. How quick? Well, let’s just say that you’re in the black (or, green) around month two. This is especially true if you’re already used to sending your customer data to a co-op database (like Abacus or NextAction); you’ve already made your data collection and transfer investment. Now it’s simply about turning those investments to a different use - customer development not acquisition - by focusing how that data helps you pull in the monetary margins in your current customer base.

These days even the most technophobic consumers have inboxes full of marketing from companies they have interacted with. As responsible marketers, we have ensured that these customers have opted in to our communications and we know that we must promptly remove them from our house file when they no longer want to hear from us. However, according to Marketing Sherpa’s Email Marketing Benchmark Guide 2008 (summary here), ensuring opt-in may no longer be enough to keep our company’s image clean.

In a survey of over 4000 consumers, half consider email to be spam if it arrives too frequently, even if it comes from a known sender. This has serious consequences for email marketers using “carpet-bombing” strategies to spur customers to purchase. Even if consumers have opted in and know a company well, they may come to think it as a spammer if they are receiving marketing emails every day or every week.

The sentiment that, regardless of permission, frequent email marketing is spam will only grow as inboxes become even more flooded. Marketers will be forced to migrate to a “surgical-strike” strategy where customers are targeted with highly personalized messages only at the most likely time to buy, and probably no more than once a month.

In an environment where consumer trust is hard to gain and can vanish with one misstep, nobody wants to be seen as a spammer. Unfortunately, the risk of marketing too frequently is now beginning to outweigh the benefit. If email marketers do not adapt through better targeting, they may find themselves relegated to the junk folder for good.

I noticed that the RRW Consulting blog alluded to an article on Friday that I have been promoting to my peers: a research report by the Aberdeen Group (abstract here) that discusses the importance of email personalization. The one-to-one marketing emphasis in the article is precisely the kind of email targeting that we espouse here at Istobe. Today, I want to expand on one aspect of the Aberdeen report that we spend extra time on at Istobe: the importance of the buying cycle in determining what kind of email message to send your customers.

In the Aberdeen article, Ian Michiels mentions that web analytics provide great clues to assessing where customers are in the buying cycle. For example, if a customer invests a vast amount of time clicking about a product group, that customer is likely doing research and is in the market to buy a product in that area. A discount offer, Michiels says, would likely get this customer - who is now highly qualified and advanced in the buying cycle - to act on their desire and make a purchase.

I totally agree with this sentiment. But as Chris mentioned in detailing his experience with GPS systems at Amazon, there is another way to do this. Customers can clue you into what they want via their clickstream. But even if you don’t have clickstream data, transaction histories, once supercrunched, can give you a leg up on finding customers who will likely buy next. In other words, this supercrunching can help you locate the customers that will likely buy before they locate you.

How does this work? Well, other customers have come before them and laid out patterns that aren’t perceptible to you and I but are very perceptible to Istobe’s predictive models. Istobe’s models throw out those customers that are not likely to buy again and then work with those who are. From there, Istobe’s models assign the products that are likely to be purchased by these likely buyers.

I won’t argue that this method is more statistically powerful than clickstream data, which is a solid indicator of future behavior. But I will argue that clickstream data takes vast amounts of resources to capture and use, a difficult proposition for online retailers who are just dipping their toes into analytics. And using transactional data to predict who will buy next is a more proactive approach. So what do you get from that proactivity? Probably a two- to three-month head start on your competition. You can focus on targeting your “most likely” customers with act-now offers while your competition waits for these customers to visit their web site.

Something that we constantly talk about around Istobe is why more small companies aren’t interested in implementing customer analytics. Especially given that these companies are pressed now more than ever to keep up with big companies that run customer analytics algorithms as part of their hourly routine. And in an era when a tome like Supercrunchers proclaims a new dawn for predictive models in business. Even with a value proposition that demonstrates a solid return per thousand customers, we often have problems convincing customers that our mojo is good and that data mining is more than just voodoo. Well, today I prepared a really simple sample revenue calculation to quantify the value of Istobe’s predictive models. Take a look at how much more an Istobe-based email campaign makes on a yearly basis.

The rule of any business venture is it must either make money or cut costs for clients. If MIT Sloan didn’t drill this into us, we got a refresher into this the other day when Doug, Chris, and I met with Chris Merrill, founder of Thrive Networks, The Orchid List, and Owner of Ass Industries. He broke that down pretty plainly for us when talking about our need to educate our customers. Well, here is as plain a case as I can make for the revenue increase that Istobe brings to the table when we mine customer data to determine what product they want to buy next.

The Revenue Increase

Assuming a company that emails 500,000 customers weekly, 50 emails a year, and $1.90 per email open, the Istobe predictive models allow a company to make $412,300 more than just basic email blasts and nearly $80,000 more than a baseline targeting approach. There is a full calculation below but let’s talk about what some of the numbers are before you examine them.

The Setup

First, let’s take a very conservative number of 4% as the increase in predictive power of our models over a general baseline. In this case, we assume the baseline to be the company offering the same product that a customer already bought. As creatures of habit, consumers are typically likely to buy the same thing from a company that they just bought. Let’s take dog food at a grocery store for example. Whoever buys dog food probably has a dog and there is a good chance that they’ll keep buying dog food. It’s a safe bet. The same goes for internet retail. If I buy a shirt from an internet retailer, it’s likely I’ll go back there to at least look for another shirt - assuming I didn’t hate the first shirt and the customer service was adequate. Now, the pitfalls of offering the same product is something I won’t go into in detail here; suffice it to say that offering the same thing that a customer is likely to buy again and again from your company is not the best business move. Really, your company should be looking to expand the share of your customers’ wallets. And this means offering them new products that they currently buy elsewhere. Like I said, a topic for another day. So Istobe does about 4% better than offering the dumb alternative, which is offering the same product again. 4% doesn’t sound like a lot but let’s play this through.

Now, let’s assume that a client uses our predictions to send out targeted email. It’s been assumed that normal behavioral targeting enhances your open rate by 40%. This means that just offering your customers the product that they bought last time increases your open rates by up to 40%. Well, I’m not so sure that I trust those studies so let’s just play it conservative and say that targeting spurs a 20% open rate increase. What that means ultimately is that Istobe predictions improve the targeting - the 20% increase - by 4%.

As a base open rate, we’ll use 3.5%. That’s a pretty conventional rate when sampled from our customers. When you apply the Istobe predictive power (4% increase) and the lift from general 1:1 targeting (20%), Istobe’s open rate is 4.4% and the baseline targeting rate is 4.2%. The normal open rate, remember, is 3.5%. This means that, if we take 1000 customers, Istobe will get 44 opens, baseline targeting will get 42, and the traditional email blast will get 35.

Here, we’ll use $1.90 per open as the amount of money that our fictitious company earns per open. Ultimately, not all opens are sales and this figure essentially backs out the complications associated with the website, ordering mechanisms, sizing problems, etc. In other words, it’s a way to understand how much each open is worth on average.

When you take into account that each email open is worth $1.90, and that Istobe has 44 opens per 1000 customers, Istobe’s predictions make our fictitious company $82.99 per 1000 customers per week. Baseline targeting makes $79.80 and regular email blasts make $66.50. Calculated for 500,000 emails per week for the course of a year, we get the figures that I began with at the top.

The Calculations

We talk a lot about the nuts and bolts of predictive analytics on this blog - how we build customer analytics models, how we interpret them, and how we establish whether or not they’re working in production. However, one item we have yet to tackle - and a very important item at that - is how to integrate data mining and/or predictive models into your organization and your company’s routines. Indeed, the black box in the middle should be the necessary data integration (getting the data into the right format for the models) and running a bevy of models against the data to see which one projects as the most effective. But it’s the before and after this black box that really make or break any attempt to incorporate predictive models into a company’s processes: data collection and incorporating data mining results into your processes.

Do you need to collect more data than you already have?
The main problem that companies run into is the need to collect more data in order to build the necessary predictive models. For example, if a company wants a model that tells them which of their products a specific customer might buy next, does it already collect the data necessary to support a model that does that? Ultimately, the question is: Is it worth the time and cost needed to invest in collecting more data that may not yield any better results when supercrunched? New collection methods take months to set up and sour clients on predictive models before the fun has even begun.

We believe that it’s important to try to work first with the data that our clients have and add new sources of data over time. This is a handy tip for business users who really want data mining to work in their organization: start small by using the data you have and get more sophisticated as you go. I know it may be tempting to put in that clickstream collection database right now so that you can use online behavior to segment and market to your customers. But trust me, get the buy-in from your organization first by proving that predictive customer analytics work. Then ask for the stars.

Are you ready to completely change the way that you do direct marketing?
Some companies would have you subscribe to a whole new way of doing business in order to use their models. Customer-centricity is my favorite new business philosophy. Though I firmly agree with the need for firms to be customer-centric, is it realistic to expect companies that use offers, coupons, and holidays to draw new and existing customers to their websites - and have for years - to change their direct marketing approach to accommodate a new set of tools? Not really. Company culture and routines are slow-developing and even slower-changing.

So the question at the end is really: What are you going to do with all this newfound predictive power? How are you going to fit in customer-centric model results - We’re 99% sure that Brad Pitt will buy two Baby Bjorns with lumbar support - to your next email blast that has a summer theme and features hats and sunscreen? And what about the extra creative necessary to relay that customer-centric message? You’re going to have to make a new email blast featuring the Baby Bjorn with lumbar support, in addition to the summer-themed email.

Well, I’m pretty sure that the summer themed email blast was probably going to draw some business but I’m also positive that luring customers with what they want when they want it is a lucrative way to market. The best practice is to initially skim the cream off of the predictions, to take those that have the highest probabilities of succeeding, and run with them. Collect a group of customers that has the highest probability of buying the Baby Bjord - Mr. Pitt among them - and send an intermittent email to just that group. Now watch your open rates and clickthroughs soar.

On Monday, I began a discussion about how Istobe evaluates the ROI from email marketing campaigns based on our predictive models. At the end of my post, I promised a discussion about other factors that we take into account when evaluating the lift. And…voila. Today we unveil those factors: the email influence zone and opt-outs, and we discuss how Istobe accounts for them in our lift calculations.

Email influence zone
Sometimes referred to as decay rate in the catalog industry, the email influence zone (EIZ) - not unlike the catalog influence zone (CIZ) - is essentially the time period after an email is sent. And we assume that each succeeding day after the email is received has less effect than the day before. Thus, the moniker decay rate. Catalogers have believed for years that their catalogs have a carry-over influence: the catalog accounts for many web purchases. In fact, this is very reason that catalogers are loathe to cut the number of catalogs that they ship. Even to those customers who have never purchased from the catalog itself. We believe this is also true of email marketing.

Basically, the idea behind the EIZ is that an email offer has an effect on online purchases that have no other obvious origin and which relate to the product that we predicted. For example, if our models predict that shoes are the likely next product for a particular customer and that customer purchases shoes online five days after receiving an email that advertises shoes, then we can assume that the email - and our product recommendation - influenced the customer’s purchase. Our model gets credit for a small percentage of this purchase even though the purchase didn’t come directly from an email click-through. The EIZ period that we calculate differs per client depending on the frequency with which our clients send emails.

Opt-outs on the Istobe watch
If we’re going to give ourselves some of the credit for purchases that occur in non-email channels, we also have to take a hit for bad events that occur during our watch. The bad event that Istobe tracks carefully is email opt-out. We track whether the opt-out rate goes up during our watch. If it does, we have to assume that next-best offer has somehow turned customers off. If the opt-out rate does go up, we deduct a portion of our lift because we believe that we were responsible for that incline in opt-out rate. We’re responsible for that small piece of customer attrition.

Taken together with the variables I spoke about last time, these are just four factors that we constantly adjust in determining how successful we are on behalf of clients. And we’re always looking for new ways to perceive actual lift. If you have new ideas for evaluating predictive-model efficacy, please email me. I’d love to talk about them.