Web analytics offer statistics reflecting collective behaviors—numbers of views, clicks, conversions, etc.— to assist an organization in optimizing ads, media buys, search terms, and overall site design. The “visitor type” forms a profile. The more closely your Web visitor conforms to a profile discovered by predictive analytics, the more likely that visitor will behave in a manner which can be anticipated.

Although many Web marketers have heard about predictive analytics, too few can explain their practical value. Here are four proven ways to apply predictive analytics and increase the ROI of online marketing.

• Make product recommendations. Millions of consumers worldwide have experienced the product-recommendation function on sites such as Amazon and Netflix. The principle is simple: The site presents suggestions based on what people who looked at similar pages (or bought similar products) have also viewed or purchased.

  Execution, however, is more complex. The greater the number of products involved, the more complicated the predictive calculation. The calculation is based on either an algorithm or regression model. Recently Netflix offered a $1 million prize to anyone who could improve its recommendation function. A collaborative effort among three development groups won the money—but Netflix was a winner as well, because the new prediction capabilities resulted in a 10% improvement over its previous model.

• Allocate retention dollars. It’s much cheaper to retain a customer than to acquire a new one. Predictive analytics will lead to a smarter, more effective retention budget. If a customer is likely to stay without prompting, any retention budget money is wasted. Also consider, there’s an entire category of customers who might respond with the behavior you don’t want: leaving. Within your database, customers fall into four distinct groups:
  • Visitors who leave regardless of your efforts
  • Those that stay without retention promotions
  • The type who leave as a consequence of your promotion
  • The group who is most likely to stay as a result of your retention efforts.

  Predictive analytics can direct retention dollars where they belong: to those who stay when offered a meaningful incentive. Adding a layer of Web behavioral data to existing efforts generally provides a 10%-15% lift over traditional churn modeling.

• Test and target ads. Suppose online ads and other marketing messages could be as precisely targeted as product recommendations? Applying predictive analytics to visitor profiles will deliver more-relevant messages and increase the depth of engagement.

  For example, a company search service for colleges and student loans started testing its online advertising. The advertisements appeared in a separate browser window while waiting for a Web page to load. Payment of services was $25 for each information-request form visitors submitted. By comparing visitor behaviors with previously compiled profiles, the site was able to make educated guesses about which ads different visitors would find engaging. In an A/B test of the site’s legacy system based on aggregate data versus a new model leveraging predictive analytics, the results were staggering: The predictive model increased the information-request rate by 25%, resulting in a 3.6%-5% increase in revenue, or about $1 million in additional revenue every 14 months.

• Use follow-up e-mails for cross-sales or remarketing. Many companies already send targeted e-mail offers to visitors who look at, but do not purchase, products on their site. In real life, however, many visitors may regard these e-mails as spam, making it important to carefully target the messages to those most likely to be receptive.

  A study by a large brokerage firm compared the impact of follow-up e-mails against a control group that received none. The result was a wash: During a 90-day period, both groups had the same purchase rates. The problem was the messages in the study were untargeted and offended as many customers as they inspired, negating any positive influence the campaign might have had.

  To improve effectiveness, follow-up e-mail campaigns should segregate prospects into groups similar to those identified in customer retention programs. Only those prospects with the desired profile, matched through predictive analytics, should be contacted.

Integrating analytics and automation – Whether it’s Predictive and/or web analytics, they do not generate revenue. To generate a measurable ROI, automating marketing activities is the key to turning insights into action in a repeatable, cost-effective manner. Bring the results of analytics to fruition by integrating all of the marketing efforts into one suite of activities that can be easily managed and monitored for maximum effectiveness:

• Web analytics using visitor-level data feeds predictive analytics with the granular information.
• Predictive analytics solutions score current Website visitors based on models derived from past visitors.
• Execution solutions deliver the message to whichever inbound or outbound interaction point your customers use.

Predictive analytics on Web data drill deeper, uncovering individual customer, prospect, and visitor insights. This type of analytics provides a strategy to target and personalize the Website, advertisements and e-mail campaigns, for much greater impact. When data is segmented by search terms, geographical location (based on IP addresses), or registered customer information, and linked to actual behaviors (views, clicks, orders), it becomes possible to address a key marketing question: Who is most likely to be interested in which of your services, products, or content?

Back to Articles