Maximize Conversions with Personalized Real-Time Offers
By Team ZineOne June 3, 2020
How Intelligent Personalization Optimizes Offers to Preserve Business Margins
“Order now and save 10%!” We’ve all been the recipient of this effective engagement tactic. By offering a time-sensitive discount, retailers can successfully incentivize customers to complete online transactions—but at what cost to their business?
When presenting customers with an online discount, retailers must ask key questions to ensure that they balance incentives with profit. What is the customer’s current purchase propensity? What’s the discount amount most likely to influence a transaction for this particular customer? What’s the value of the merchandise in the customer’s cart? The best way to account for these and other considerations is with machine learning (ML) models that can perform purchase propensity and margin analyses while the site visitor is still browsing to show them optimized and personalized offers in real-time. Let’s consider the following example to understand how an intelligent personalization engine makes this work:
1 | Customer visits the online storefront
Jason is browsing a retailer’s site for a new pair of running shoes. He’s looked through their products a few times before in the preceding weeks and thinks he is close to making his final decision about the pair of shoes he wants.
As soon as Jason lands on the retailer’s website, the personalization engine recognizes Jason and the fact that he is looking at a certain pair of running shoes at that moment. It also takes into account that he has been browsing and reading reviews for running shoes for a significant period of time, clearly showing his intent and interest.
2 | Customer adds items to the cart but does not check out
Jason thinks he’s found the right fit—a pair of lightweight, long-distance running shoes. He adds the shoes to his virtual cart, where he is able to see the final price. A bit put off by the $85 total, he switches back to the products page and continues browsing.
The purchase propensity ML model of the personalization engine deduces that the chances of Jason buying the shoes are in the mid ranges, but considering that he has added the shoes to his cart but not tapped on the purchase button shows that he is close to making a decision but still hesitating. Perhaps he is price sensitive and might be receptive to a discount to fully commit himself to own this pair of shoes. But what is the right amount of discount that will convince Jason to make the purchase and at the same time not erode the margins for the retailer?
An intelligent personalization platform can perform a margin analysis based on the real-time value of the visitor’s virtual cart and their previous transactions to come up with an optimized offer, which in Jason’s case is $12 off —this is the highest possible offer to influence Jason’s conversion while still preserving the store’s profit margins.
However, the store is running a special offer: free shipping on orders of $75 or more. Applying a $12 deal to Jason would disqualify him from these savings. An intelligent personalization platform can have business controls in place to prohibit interference with other online rewards. As a result, the $12 calculation is reduced to an optimized $10 offer.
3 | An optimized offer is delivered to the customer
Before Jason can leave the site without transacting once again, a pop-up message appears on his screen: “Jason: Order in the next 10 minutes and receive $10 off your order!” The countdown begins.
This offer is personalized only to Jason based on his cart value and real-time in-session activity on the site. It is bold enough to grab Jason’s attention and the countdown clock adds a new layer of urgency to the conveniently discounted price.
4 | Checkout is successfully completed
Satisfied with the $10 discount and urged on by the 10-minute limit, Jason uses the unique code displayed in the offer to complete the purchase.
The code shown to Jason can be redeemed only once, and only within the next 10 or so minutes. This allows Jason to successfully check out at a price point that delights him, and maintains profit margins for the retailer.
From purchase propensity calculations to margin and cart profitability analyses, ZineOne’s powerful ML models calculate and act on customer and business inputs in real-time. And now, our Experience Gallery makes it simple and quick for business users and marketers to enable such personalized real-time offers. Schedule a free demo to learn more about how the ZineOne’ Intelligent Customer Engagement platform strategically incentivizes online purchases while continually maintaining profits.
Request a Demo
We look forward to getting to know your business!