Recommendation Engine

We've been saying this pretty much forever.  Bizreport just wrote "If your e-commerce site doesn't already feature site search then perhaps a recent survey, conducted by comScore, will convince you to implement it ready for the holiday season."  More on the overall results of the survey are in a Search Engine Land article.

And the number of people using site search is climbing!  The survey found 40% of shoppers use search, whereas only 20% were browser.  This underpins the importance of adapting your customers online experience, no matter how they get to you, or how they find things on your site.  Search, Navigation, Recommendations - they are all important.  User generated content, catalog content, supporting editorial content - all important, all potentially deal clinchers for your shoppers.  And another nugget about how important relevant search results is, after using the site search box 94% click on between one and 10 product listings according to the study.

And fixing site search in time for the holiday shopping is still possible with no heavy lifting from your stressed out, "don't ask me to change the site before January" IT guys.  If you have search, let the crowd help you offer more relevant results.  Again, no tuning, no heavy lifting.  If you don't have site search at all, we offer a hosted site search option as well.  It is easier than you think.

I did my catch-up reading (the old fashion physical reading) over this past Memorial Day. One feature article in Time Magazine, on recommendation engines, jumped out at me. Here’s the online version.

Time reporter Lev Grossman correctly points out the laughable issues with the first generation recommendation engines and personalization using collaborative filtering. Just because people bought the iPad and Coke together doesn’t mean the two products are related.

The article hits home on what statisticians and cognitive scientists have known for years:

• There are small lies, damn lies, and then statistics
• Humans are only predictable within a narrow context or topic

Within any large data set, such as internet purchases and behaviors, you can always find two things being connected even when they are just random. There is a fine line between serendipity and randomness. To separate them, you have to know if there is any hidden affinity between the two. The latest cognitive discoveries show that people are animals of context. Relationships among products or content are not determined by who we are as individuals, but rather are biologically "forced" upon us by the contexts in which the products or content are being considered. Across unrelated topics or contexts, people are very unpredictable even you know them well – I've known my wife for years but everything I buy for her seems to be wrong.

However, there is a reliable way to predict people – one that is based on the collective wisdom of like-minded peers. These are not your normal Facebook friends. They are your contextual peers. If you are shopping for a red washer, all of the people in the world who are looking for similar colorful washers should be your implicit contextual "friends" at this moment. Their collective interests under the context of "red washer" can help you short-circuit the content overload on the internet.

Interestingly, the narrower the contexts, the more predictable people become. This brain pattern recognition ability happens to offer us the perfect tool to discover the truly hard-to-find long tail products and content!

There is a wealth of content available online, and as we know all too well, it can get overwhelming to try to keep up. The Baynote team regularly reads the following industry blogs and media sites that are tackling the hot issues and trends that touch our business and our customers. Please let us know what you think of our shortlist and if you have recommendations for other sites that we have overlooked.

Collective Intelligence

1)      Tom Austin, Gartner – Tom is a group vice president and Gartner fellow who covers how IT can enhance the performance of individuals, teams and organizations.  His blog includes insightful analysis on the impact that various forms of technology have on productivity. He has been placing a lot of focus on Pattern-Based Strategy, which enables business leaders to actively seek, amplify, examine and exploit new or novel business patterns.

2)      Forrester’s Customer Intelligence Blog – Authored by Forrester analysts Dave Frankland, Julie Katz, and Suresh Vittal, this blog provides details on the latest research and trends affecting marketers that are focused on mining customer data from online behaviors.

3)      MediaPost Behavioral Insider – Steve Smith’s blog takes a fresh look at behavioral marketing, analyzing the latest strategies for marketers to better understand their customers and make strategic decisions that are based on proven approaches.

4)      Destination CRM – This online daily edition of CRM Magazine reports on the latest information on customer relationship management.

Real-Time Web

5)      Steve Gillmor, TechCrunchIT —  Recognized as the leading journalist on the real-time Web, Gillmor has reported on every key player in real-time, either through written blog posts, or in online video episodes with The Gillmor Gang. The Gillmor Gang is a technical show that interviews IT industry executives at major companies that have deep knowledge in the technology that they focus on.

6)      Pete Cashmore, Mashable – The founder and CEO of Mashable, one of the most popular blogs worldwide, Cashmore writes a weekly column for CNN.com as well as regular posts on Mashable. He has been following real-time Web closely lately in his CNN column.

7)      John Borthwick – Currently the CEO of Betaworks, Borthwick’s blog posts study the development of the real-time Web. As an entrepreneur, Borthwick is involved in various companies that touch on the real time Web, and in his own words, is interested in understanding “how media evolves as it collides with real time conversations.”

e-Commerce

8)      Jeffery Roster, Gartner – Jeffery is a research vice president at Gartner as part of the Industry Market Strategies Worldwide unit covering the retail and wholesale industries. His blog posts provide insight into research he is working on, as well as his reflections on industry events including NRF.

9)      Forrester eBusiness & Channel Strategy Professionals Blog – Forrester analyst, Sucharita Mulpuru contributes to this blog every once in a while, and we always find her posts to be very relevant to Baynote. Sucharita publishes the annual Holiday Retail Forecast, and is a recognized authority on technology developments that affect the online commerce industry and vendors that facilitate online marketing and merchandising.

10)   Get Elastic – An e-commerce blog maintained by Elastic Path’s Emerging Media Analyst and eCommerce consultant, Linda Bustos.

11)   Shop.org – An open forum for shop.org members to post their knowledge and experiences with e-commerce.

Search

12)   Gilbane Search Blog – Linda Moulton of analyst and consulting firm, Gilbane Group, blogs regularly about trends and technologies in enterprise search.

13)   Search Engine Watch Blog – This blog by Nathania Johnson provides tips and information about searching the Web, analysis of the search engine industry and help to site owners trying to improve their ability to be found in search engines.

Technology & Innovation

14)   Sramana Mitra on Strategy – An entrepreneur and a strategy consultant in Silicon Valley for over 15 years, Sramana  also writes a weekly column for Forbes and is currently authoring Entrepreneur Journeys, a series of books focused on demystifying entrepreneurship. Her blog posts profile various entrepreneurs, and provides a comprehensive look at the innovation that is happening in Silicon Valley today.

15)   Read/Write Web – One of the world’s top 20 blogs, Richard MacManus, Marshall Kirkpatrick, and their team do an excellent job of analyzing all products that relate to the Internet, and the top trends that impact changes in Internet-related technology. RRW is a great place to remain updated on the latest and greatest Internet innovations.

Customer Service

16)   Ragsdale’s Eye on Service – John Ragsdale is the Vice President of Technology Research for the Technology Services Industry Association (TSIA). He shares the latest in technology innovation, industry events, and his expert commentary on the latest issues effecting customer service executives on his blog.

The central focus of Gartner’s Symposium/ITxpo this week in Orlando is all about implementing what they’ve recently dubbed as a “pattern-based strategy”.

According to Gartner, a pattern-based strategy “provides a framework to proactively seek, model and adapt to leading indicators, often-termed ‘weak’ signals that form patterns in the marketplace.”  For the past several years Baynote has been committed to helping companies identify these patterns with technology that lets them tap into the collective intelligence of customers visiting their websites. This is something that transactional based systems such as business intelligence (BI) and complex event processing (CEP) simply haven’t been able to deliver. Here’s why:

1) For years BI, CEP (more recently) and other related technologies have helped organizations become much more efficient by automating their interactions with customers. However, in the process of creating huge economies of scale, they forced companies to lose the “mom and pop” touch that consumers expect when they walk into a local hardware store or restaurant. In failing to create digital mom and pop experiences, online retailers and publishers have placed unnecessary emphasis on promoting popular products and content, thereby losing out on profits to be gained from merchandising their long tail products.

2) In addition, these so-called “predictive” applications have historically prioritized the wrong set of indicators, often identifying consumer trends weeks, if not months, after the fact. For example, e-commerce transactions lag other more relevant indicators, such as online comparison shopping, by months. Only by tapping into the power of the collective is it possible to see early signals, spot trends and develop strategies around them before your competitors catch on. This holds particularly true for long tail products. Our customer US-Appliance tapped into the implicit behaviors of its website visitors to merchandise colored washers/dryers months before Home Depot and Best Buy began promoting similar products in their stores.

In Gartner’s recent report, entitled “Introducing Pattern-Based Strategy”, they view “the collective” as being critical to developing a pattern-based strategy. We couldn’t agree more with their position:

The collective comprises individuals, groups, communities, mobs, markets and firms that shape the direction of society and business. The collective is not new but technology has made the collective more powerful — and enabled change to happen more rapidly. The explosion of social software has enabled groups and individuals to rapidly form and rally to a cause — often resulting in significant societal changes.

The result for business is a cacophony of rapidly evolving demands, expectations, inputs and transactions, as well as an opportunity to not only react, but to seek signals of change from the collective. Market trends, some subtle, others strong, are masked by noise, and many enterprises are failing to proactively detect the patterns they rely on to direct future strategy and support investment decisions. In addition to failing to detect these patterns, enterprises are not utilizing new resources to proactively seek signals of change nor do they understand their power to influence individuals and communities.

Val Sribar, group vice president of Research at Gartner, sites Amazon’s and Netflix’s use of recommendation engines as good examples of organizations leveraging collective intelligence to support their pattern-based strategies. Sribar agrees with Baynote that recommendation engines identify new patterns in behavior as customers browse and purchase. While Amazon and Netflix are highly popularized cases, we’ve helped hundreds of other well known brands tap into their collective customer networks to significantly increase revenue through cross-selling and upselling, and higher customer loyalty.

We’re excited to see Gartner take a leadership position on this important issue and look forward to working with them and our customers to bring best practices related to collective intelligence to the forefront of modern business strategy.

Baynote Product Recommendations enables our customers to more effectively merchandise their products across their entire site. However, many ecommerce vendors invest heavily in their merchandisers to create complimentary and comparative products to increase conversion rates and average order values.

Today I had an enlightening conversation with one such vendor. He spoke highly of his merchandisers and explained their extensive knowledge of the business. He questioned the need of a recommendation engine when he had access to such experienced merchandisers. Point well taken. This continues to be a hurdle for many recommendation companies trying to break into the ecommerce industry. Lets move the conversation away from an “either or” scenario. Combining your experienced merchandisers with automated intent driven recommendations incorporates the knowledge of your business experts with the collective intelligence of your website visitors.

We’ve spent many resources on our merchandising console within our reporting interface Baynote Insights to facilitate this goal of “merchandising harmony.” For the last few months our clients have been combining our recommendations technology with their merchandising expertise to deliver an enhanced user experience while increasing conversion rates and average order values. Why substitute when you can combine?

I’ve just returned from the Shop.org Annual Summit in

Las Vegas. Despite it being in Vegas and having mild distractions lurking around every corner, I managed to see a good deal of the conference content and not miss any of the sessions I was supposed to lead or participate in.

Many continue to ask whether eCommerce growth has peaked. With countless consecutive quarters of double-digit growth, one has to ask these kinds of questions. Well, the data suggests it has not peaked. According to Forrester analyst Sucharita Mulpuru, ecommerce will continue to grow at a rate of 25% annually for the next many years. The reason? Online retailers not tackling the basics.

As the holiday season approaches, and since it’s football season (thankfully), it’s only appropriate that we talk a bit about blocking and tackling fundamentals. Forrester and other pay mention to the following:

 

1) Completing the Transaction

Amazingly, some leading eCommerce websites are seeing transaction failures as high as 12-14%. For comparison purposes, the airline industry which is hardly the gold-standard in service sees has delayed/cancelled flight rates of about 6%. There are $ millions left on the virtual table as consumers are driven to alternative channels to make their purchase.

2) User Experience

Snazzy front ends that are engaging and interesting may draw some attention, but don’t forget the basics of making it easy to browse, search, add to cart, and purchase. ‘Pretty’ is good, but usable is better.

… and finally…

3) Product Recommendations

The only technology that Forrester recommended were recommendation engines.  Recommendation engines help retailers dynamically up-sell / cross-sell / merchandize their products.   With thousands of products and millions of visitors to an online retailer’s website and automated solution to this is a necessity, but measure the impact so you can truly understand the hard-dollar impact it’s making.

So make sure to do your homework and invest in the basics of selling, merchandizing, and completing transactions.Also, I wanted to give some credit to Jason Billingsly over at Elastic Path. He presented an eye-opening and incredibly engaging session on leveraging social media for eCommerce. If you have a chance, check out his session at Online Market World in

San Francisco in early October, you won’t be disappointed.

We had a good laugh recently, thanks to our friends over at ElasticPath who have managed to find some humor in the “crazy, messed-up world of eCommerce” and just launched four original parody videos on YouTube called:

- Customers Who Bought This Item Also Bought…

- Premature Redirection

- Zero Results Found

- If Only Search Engines Could Understand What We Want

We highly recommend viewing the other three parodies at http://www.getelastic.com/crazy-ecommerce to anyone who has ever been at the mercy of the eCommerce gods.

Come join us Wednesday, June 27 at the Santa Clara Convention Center for the WebGuild Searchnomics 2007 Conference and hear Baynote CEO Jack Jia speak on the Increased Revenue through People-Powered Site Search and Recommendations panel. We’d love to see you there! Register Now.

The Searchnomics Conference is a one-day event aimed at web and internet marketing professionals and dedicated to the search industry. At the conference you will learn about trends and best practices in:

• Search Engine Marketing
• Search Engine Optimization
• Design and Development
• Branding and Promotion
• Web Analytics
• New Innovations and Opportunities

Come be a part of this one-of-a-kind conference and learn from expert speakers in the field of search. Don’t forget to stop by the Increased Revenue through People-Powered Site Search and Recommendations panel featuring industry though-leaders including Baynote CEO, Jack Jia.

Register for Searchnomics here