Feature-richness in the ecommerce space has now become critical for today’s sophisticated shopper, who is presented with a multitude of sites that they can enter and abandon with mere clicks of a mouse. When an online shopper has a good first experience with a website, sixty percent of the time he/she will return to that website to buy more (“Trends in Online Shopping,” Global Nielsen Consumer Report, 2009). Amazon still leads the way in terms of product breadth, feature richness and depth of content available across eCommerce sites; consumers start at Amazon because they anticipate a positive experience at a good price.

Download Speak Geek – Vol. 2

Of the available features on the market—ranging from customer reviews, product recommendations, dynamic carts, transactional mail and so on—those that use technology supported by advanced analytics can deliver the most rich and engaging user experience. Without a platform of intuitive technology many features on a site become rigid—non-adaptable to users on an individualized basis and unable even to reflect macro consumer trends.

In RichRelevance’s latest tech brief (part of our Speak Geek series), we take a look at how our core technology, “ensemble learning,” addresses shopping behavior—using live data to flexibly adjust within the context of a particular site to the needs of each shopper. The technology provides a single, highly versatile platform from which multiple recommendations-based features can be built—one that encourages shoppers to linger longer on a merchant’s site, enabling retailers to build loyalty …important because sixty percent of online shoppers mostly buy from a single site—demonstrating a unique level of loyalty that online retailers need to capitalize on.

Tweet This Post

When we launched richrelevance, we chose the tagline “next generation personalized recommendations” because the status quo solutions – all first generation products – were not delivering on the promise of a faster, easier, and more enjoyable shopping experience. Our new class of hyper relevant product recommendations was architected to address some of the fundamental issues that plague traditional approaches to product recommendations. I became familiar with the challenges of personalized recommendations while at Amazon where I ran the R&D team focused on personalization. Over the years at Amazon, and again at Overstock.com, I learned a few key lessons that would … Continue Reading

Tweet This Post

Retailing Today just published an article I wrote. In summary, I address how second-generation product recommendations compare to the first-generation in terms of performance, multichannel potential, and personalization quality. The full article is available here. Hope you find helpful!

Driving sales in a tough economy

May 4, By David Selinger

The era of abundant consumer spending is over –– and retailers should prepare now for a possible long-term shift in consumers’ values and attitudes. A recent survey of online consumers by JupiterResearch found that nearly half … Continue Reading

Tweet This Post

I am just coming home from a fun and interesting time @ E-Tail 2009. I got to see many of our friends and partners, from the folks at PayPal and Akamai who throw a heck of a party to those folks at Responsys who definitely know how to spice up a lunch with a little “game show”.

Among many interesting speakers, Andrew Kordek, the manager of emerging e-mail technologies … Continue Reading

Tweet This Post

Richard MacManus published a post on ReadWriteWeb on Monday (which was re-published in the NYTimes) titled “A Guide to Recommender Systems;” this post is a reply.

I’m excited to see a conversation around recommender systems that delves deeper into the different approaches to recommending products. There are some folks who follow the misconception that all recommendation engines are created equal—they most definitely are not. Although Richard’s analysis may have oversimplified the problem in identifying only four approaches to recommendations (personalized, social, item, and combination), he does affirm the critical point that there are very different ways to … Continue Reading

Tweet This Post