By Jake Bailey, RichRelevance
As online retailers, we’re all too familiar with the reality that conversion rates have remained stagnant at two to three percent throughout the first decade of e-commerce history.
Yet thanks to the abundance of information, tools and features we’ve added to our pages, the path to purchase increasingly begins at the retail website. This increase in site traffic has given us an opportunity most have yet to realize—the introduction of meaningful advertising revenue through shopping media.
Starting today, IBM’s Watson supercomputer will go up against a pair of human Jeopardy champions. Regardless of whether man or machine comes out on top, it will be a banner day for a machine learning technique called ensemble learning. Ensemble learning is based on the notion that tens or hundreds of independent algorithms, each aimed and working in a particular kind of context are better than one bigger, more complex algorithm. This idea lies at the heart of both Watson’s approach to generating Jeopardy questions and RichRelevance’s approach to generating relevant product recommendations and advertising.
Darren Vengroff to detail RichRelevance’s new open source project designed to spur innovation in retail personalization at top recommender conference of the year
San Francisco, CA – Feb. 9, 2011 –– RichRelevance®, the leading provider of dynamic e-commerce personalization for the world’s largest retailers, today announced that Chief Scientist, Darren Vengroff, has been selected to speak at IUI2011 Workshop on Context-awareness in Retrieval and Recommendation (CaRR) on February 13 in Palo Alto, California. Vengroff will debut his peer-reviewed paper entitled “RecLab: A System For eCommerce Recommender Research with Real Data, Context and Feedback” at a 12:30 pm PST general session open to all conference attendees. The paper will discuss how RecLab, a new open source project headed by Vengroff, enables academics, researchers and developers to dynamically test and validate their recommendation algorithms in a live e-commerce environment to spur industry innovation. Following the presentation, the paper will available for download from the ACM Digital Library.
“Context is a hot topic in recommender systems these days, and justifiably so,” said Vengroff. “What we recommend to a shopper in one context, such as when they are browsing, can and should be very different than what we recommend once they have already chosen an item and are on the shopping cart page. RecLab supplies a wide variety of context information, in the form of where users are on the site, where they have been in the past, what they have searched for and purchased, to how they reacted to past recommendations, just to name a few. CaRR 2011 offers an exciting opportunity to formally introduce RecLab to the research community.”
The CaRR Workshop attracts leading researchers and academics from around the globe. The conference aims to involve the recommendations community in an active discussion in order to find new, creative ways to handle context-awareness. The workshop is especially intended for researchers working on multidisciplinary tasks who want to discuss problems and synergies. For more information on the program and for further details, please visit: http://www.dai-labor.de/carr2011/program/.
About RichRelevance
RichRelevance powers personalized shopping experiences for the world’s largest and most innovative retail brands, including Wal-Mart, Sears, Overstock.com and others. Founded and led by the e-commerce expert who helped pioneer personalization at Amazon.com, RichRelevance helps retailers increase sales and effectively monetize site traffic by providing the most relevant products, content and offers to shoppers as they switch between web, store and mobile. RichRelevance has delivered more than $1 billion in attributable sales for its clients to date, and is accelerating these results with the introduction of a new form of personalized advertising called shopping media which allows brands to engage shoppers where it matters most – at the point of purchase on the largest retail sites in world. RichRelevance is located in San Francisco, with offices in Seattle and London. For more information, please visit www.richrelevance.com.
The RichRelevance Analytics group recently conducted a series of studies for several of our larger, premium retail clients to explore customer behaviors and identify the greatest opportunities for optimization. The results of one such study*—which I am sharing here today, revealed some pretty astounding insights for this particular customer’s online shoppers.
Home page “schmome page.” The home page is for all intents and purposes the premier online brand presence for a merchant. It gets rendered more than any other distinct URL within the merchant domain and is often the gateway for the most loyal customers. Yet with only 4% of inbound sessions and 1% of total page views, you now know why that home page promotion didn’t do so well. These numbers paled in comparison to the search page, which was the landing page for almost 40% of all sessions followed by the category page at 26%, which narrowly edged out the item page at 25%. The lesson here? A simple UI or merchandising enhancement of virtually any dynamic page template will always be a more efficient allocation of resources than investment in the home page.
This week, Greg Linden noticed a conference paper that reveals that YouTube is using Amazon.com‘s recommendation engine to power its own recommendations. Last week, Fast Company ran an article about how a former Amazon.com engineer is trying to help discover a better recommendation engine than his former employer. And we rediscovered a tutorial from way back in December of 2010 on how to get your hands dirty building your own recommendation system using NumPy.
David “Selly” Selinger is CEO of RichRelevance, an e-Commerce personalization technology company.
AdExchanger.com: Why do you call RichRelevance “the intersection of e-Commerce and Madison Avenue”?
DS: Large retail sites represent the last frontier for ultra-premium ad inventory that brand advertisers have historically not had access to. RichRelevance is empowering our enterprise-class retailer customers including Target and Overstock.com to create incremental streams of revenue by providing premium advertisers access to engaged consumers on shopping media (relevant retail sites) closest to the point of purchase.