Intelligence Collected: The Baynote Blog
Best Practices in Social Commerce
By Jen Burns in Events, Featured on June 14, 2013
PetFlow, a 3yr old company set to hit $65MM in online sales in 2013, covered “how social marketing became the rocket fuel for a small startup.” The co-founder and IRCE speaker, Alex Zhardanovsky, claimed he was nervous, but the results he shared on his company’s success were both humorous and engaging. Facebook: Not the Place to Acquire New Customers PetFlow shared their frustrations with Google AdWords and Facebook advertisements ... Read More »
The Pulse of Online Shopping at IRCE 2013
By Jen Burns in Events, Featured on June 12, 2013
At IRCE last week, Gian Fulgoni, Chairman of ComScore covered the results of their recent report: The UPS Pulse of the Online Shopper. The report which surveyed over 3,000 participants, gave great insight in to the pre- and post-purchase expectations of online shopping. Here are the report’s major insights: Tablets and Mobile devices Today stores are displaying more and more “tablet” offerings like the kindle, e-reader, and phablet. Gian ... Read More »
Beware the Bias
By Marti Tedesco in Machine Learning on May 31, 2013
One of the beauties of big data and machine learning is that is it supposed to be completed agenda-less. The system collects data of all types and the machine learning algorithms watch and establish meaningful patterns and outputs as a result of the abundant data. Seems simple enough. Unfortunately, as with most things, it’s not that simple.First, most systems, at least in ecommerce, don’t collect enough data fast enough ... Read More »
May Personalization Roundup
By Dan Darnell in Personalization on May 29, 2013
We’ve seen a steady flow of articles discussing machine learning, online privacy and personalization. While each of these topics is interesting in and of itself, the confluence of these three topics is where the digital debate is headed. What data should algorithms consume in order to provide consumers with a personalized experience without infringing on personal privacy? What role do humans play in determining how technology leverages data? The ... Read More »
A Personalization Manifesto – Why Bother? Part III of III
By Dan Darnell in Featured, Personalization on May 23, 2013
Personalization means delivering relevant content to a shopper based on what is known about them. Relevance is defined as that content that is most appropriate to the user’s needs. We know the goal of personalization is to deliver content which best meets the user’s needs. But what about the business needs? Ecommerce companies must also focus on maximizing key metrics like engagement, revenue, conversion rate and average order value. ... Read More »
A Personalization Manifesto – Personalize Based On User Type Part II of III
By Dan Darnell in Featured, Personalization on May 21, 2013
Before any real personalization can happen, a retailer needs to first ask, how well do I know this shopper? In most cases, the shopper will be an unknown or anonymous visitor. These are users that you have never seen before or that you do not recognize. Using in the moment context and intent is the best approach in this situation. The Baynote personalization engine understands intent by looking at ... Read More »
A Personalization Manifesto – Personalize for the “Now” Part I of III
By Dan Darnell in Featured, Personalization on May 16, 2013
It is a common fallacy that ecommerce personalization must and should treat everyone as completely unique individuals. Yes, I know we all think that we are completely unique people. But the reality of it is that we are more alike in or choices and preferences than we think. What is different about each of us though, are the patterns of how we behave – or the context in each ... Read More »
Video Recommendations at Face Value
By Jen Burns in Featured, Recommendations on May 14, 2013
Our good friends over at Invodo know that 57% of consumers rely on product videos to confidently complete a purchase. Video content exists as a medium for many things, but for retailers or other information providers, it helps consumers with a purchase, an experience or both. Video recommendations are similar to product recommendations, but are more interactive and a good tactic to use ... Read More »
Algorithms, Merchandising and Psychology – Part 2
By Robin Morris in A Word from the Engineers, Featured on May 9, 2013
In my last post, we discussed the recommendation algorithm, the merchandizing layer and the presentation layer as well as the fact that I am working on a KPI-optimizing algorithm that differs from a collaborative filtering algorithm. In running A/B tests on these differing approaches, we’ve found that the sites divide into two types: Type 1: The proportion of users who use the ... Read More »
Algorithms, Merchandising and Psychology – Part 1
By Robin Morris in A Word from the Engineers, Featured on May 7, 2013
I was going to write this blog about feature hashing, a massively useful trick when building classifiers and predictive models. It saves the time and complexity of building a dictionary and allows the hashed feature vector to be smaller than the number of possible features. It is smaller because the number of actual features in a particular data set is often much smaller than the number of possible features ... Read More »