The Cooper Journal: Entries about Web

A better algorithm isn't enough to fix Netflix's recommendations

by Stefan Klocek on August 7, 2009 | Comments (7)

There has been a lot of hype recently as Netflix announced provisional winners of their million dollar contest to improve their recommendation algorithm. The goal was to improve matching by 10%. Since it took over 50,000 entrants the better part of three years trying to improve past 10% this is probably a trick they can only pull off once. Given that their current recommendation engine does a miserable job of recommending movies for me, even a 10% increase isn't likely to be particularly satisfying.

I've rated just shy of 800 movies on Netflix;and just over 150 items on Amazon, yet Amazon's recommendations are usually satisfying while Netflix struggles to accurately recommend any movies I'd like to see. This isn't a case of esoteric movie tastes, in fact I'm fairly mainstream, largely preferring the entertainment of a summer blockbuster to the intellectualism of an indie documentary. The books I like are the opposite: non-fiction, obscure, expensive, limited runs, or out-out-of-print, in short; not popular. And still, Amazon recommends the right books.

Pandora is a music service which delights me by consistently recommending new music to me which I like. Netflix can't give me great recommendations. Amazon and Pandora do. Why?

Clearly the algorithm is a critical part of any good recommendation engine. But there seem to be limits to what can be accomplished just by tweaking the math. If Netflix can only squeeze a 10% improvement out of the calculation for recommendations, where can they turn to get additional increases in quality?

Tweaking what happens before and after the algorithm seems to be the only other opportunities. Both of these are ultimately interaction design solutions. Let's take a look at a few approaches to recommendations used by Netflix, Amazon and Pandora and see how they lead to different results.

Thinking outside the boxee

by Nate Fortin on April 15, 2009 | Comments (4)

Yup that’s right. First they had the idea to get the Internet on your TV (remember WebTV?) then it was all about TV on the Internet (Hulu, CBS, CNN, etc. ) and now we’ve got TV on the Internet put back on your TV (boxee).

For those of you not already in the know, boxee is a multi-platform media center with a 10-foot interface for aggregating video, music and photos that exist both offline and online. Others have failed in this space, but the boxee offering pushes the paradigm of content distribution and consumption in some interesting ways.

Interaction design for startups: A conversation with Andrew Hoag, founder of inviteme.to

by Emma van Niekerk on February 13, 2009 | Comments (0)

inviteme.to is an early stage startup that allows people to coordinate offline social activities with their friends. Founder Andrew Hoag, tired of organizing the "goat rodeo" preceding any event with his friends, found a niche desperately in need of attention, and decided to do something about it. He approached Cooper in April 2008 to work on the design and user interaction for his web-based product.

The people behind inviteme.to

Andrew: We got started 8 months ago and have two full time people and a couple of contractors and outside staff helping us. As for background, I come from the business side, working in enterprise, security and software for 7 years. Most recently I’ve been advising consumer internet startups before launching inviteme.to. My technical co-founder is a developer that came from a large travel site, Sidestep, which you may have heard of. For now it’s just the two of us working full time with a bunch of people helping us out.

Checkout checkup: Sites that get it right

by Suzy Thompson on January 16, 2009 | Comments (2)

Recent reports on the holiday shopping season show that despite the tough economy resulting in a sharp decline in spending overall, the shift from brick and mortar to online shopping continues. Because “going to another store” in the online world is as easy as a mouse click, retaining customers throughout the shopping and buying process is critical. Does your site have what it takes to give customers a satisfying shopping experience and earn their loyalty?

Between some friends’ regrettably-timed birthdays and the holidays themselves, the past month has provided me ample opportunity to interact with and admire recent advances in online shopping and checkout design. From that admittedly unscientific sample, here are some thoughts on key aspects of the checkout experience to consider, as well as my take on the winners at each step.

Searching and inspecting

They say you never get a second chance to make a first impression. As your customers’ first encounter with your site, the searching and inspecting experience is critical. Think of your site’s browse and detail pages as a top-notch personal shopper, and design them to mirror the qualities and behaviors of superstars in that role:

Flexible: Make sure your site supports multiple modes of shopping (such as browsing within broad categories as well as focused searching based on specific criteria), and enables users to easily recover if they click into the wrong item or just want to continue shopping.
Good listener: Many customers have a pretty good idea of what they’re looking for - is your site designed to listen? Filters that expose a wide selection of available criteria, work together, and support multiple values are great ‘listeners’. If you’re not sure what options to provide, monitor the use of your search box to identify filter candidates.
Efficient: Performance matters, so be sure you’ve tuned your page updates to deliver lightning-fast results.
Forthcoming: Ensure that your browse pages provide users enough information to quickly disqualify undesired items and develop strong interest in appropriate items, and that detail pages include all information needed to close the sale. While a picture is worth 1,000 words, it can’t say anything if it’s too small - an image size that’s ample for displaying a collection of small items like shoes or belts could induce squinting and frustration when presenting full-length dresses. On browse pages, provide a control for adjusting image size, and include interactive swatches of color options to reduce the need to drill in. On detail pages, provide multiple views and close-ups with minimal navigation.

Winner: Endless

This site rocks my world with a half-dozen filter categories that work in tandem, allow multiple values, can be reset with a single click, and update results in the blink of an eye. Replacing the ‘more colors’ bar with a row of interactive color swatches would earn them an A+.

Economizer: A Cooper service concept

by The Editors on December 15, 2008 | Comments (12)

People are looking for ways to economize in these uncertain times. We can all see the evidence of environmental crisis brewing alongside the economic downturn, and it's easy to feel powerless in the face of such global forces. With politicians and businesses seeking avenues to a sustainable future, Cooper wondered how design might help individuals cut costs while also encouraging behavior that was environmentally responsible.

This all started when Environmental Defense approached Cooper, asking us to imagine new ways to make it easier for people to save resources. We performed research throughout the Bay Area, then collaborated with Environmental Defense to model our findings and identify design opportunities. From this point of inspiration, we continued on our own, crafting a quick eco-friendly concept: Economizer, a service that helps consumers save money while making sustainable choices. The service consists of a core set of internet-aware services with optional components such as hardware data collectors, social networking applications, and dedicated smart phone interfaces.

Economizer: Scenario 1 on Vimeo
(Watch this video in fullscreen mode by clicking the icon in the lower right of the player.)

Folkware

by Chris Noessel on September 24, 2008 | Comments (5)

In his recent article for TechCrunch, salesforce.com CEO and chairman Marc Benioff frames the web 1.0 revolution as “Anyone can transact” with great 1-to-many online transactional applications like Google and Amazon. The 2.0 revolution was “Anyone can participate” with a host of many-to-many online applications like LiveJournal, Flickr, and YouTube that really put the focus on user-generated content.

Google Chrome: The interface is beside the point

by Tim McCoy on September 4, 2008 | Comments (7)

There's been a lot chatter around the office and internet about Chrome, the recently launched (or leaked) Google Web browser. I've got to say that much of it misses the aspect of the application that I find most inspirational. Google Chrome exists for one reason and one reason only: To provide a framework for web-based applications to look, feel, and act like desktop applications.

It doesn't seem that Google has real interest in replacing IE or Firefox as the dominant web browser. (The tech business press can't see beyond this point). Instead, Google wants to see the technological underpinnings of Chrome adopted by mainstream browsers. The Chrome team is explicitly inviting other browsers to use their code base — they've open sourced everything — and they have explicitly acknowledged adopting best-of-breed UI features from others.

So how does Chrome elevate web apps to desktop app status? Six ways: Separate processes for each tab; Google Gears for local storage, offline functionality and "native app" behaviors; application shortcuts; a modern JavaScript virtual machine; and minimal-to-absent browser interface, aka "chrome". Let's look at each one in more detail, with snippets from Scott McCloud's fantastic graphic novella product tour.

The airline industry needs to check their own baggage

by Nick Myers on July 10, 2008 | Comments (2)

I wasn't surprised to read that the airline industry was rated the worst in customer ratings. It seems like every week there's a news story about one of the major airlines raising their fees or adding another miscellaneous cost on top of their base ticket prices. I'm slightly sympathetic to the fact that the airlines are dealing with ever-increasing oil expenses, but not all airlines are dealing with their struggles in the same way.

I was pretty outraged when American, United, and US Airlines announced plans to charge an extra $15 per checked bag. This is already on top of the $25 for a second checked bag that they (and in fairness most other airlines) already charge. Why couldn't they simply add $15 to the price of their tickets? Because they can't compete on price with low cost carriers like Southwest and are feeling the squeeze from both sides.

Now more and more travelers will abandon checking luggage and cram all number of accessories into smaller carry-on bags, thereby causing long lines through security and long boarding times while they struggle to shove their bags overhead with little assistance. This will ultimately lead to delays and more misery.

The bottom line is that for flying, people mainly care about cost and if you've flown on Southwest, American, United or Virgin America there's not a great deal of difference in service — so why pay more? If anything, I enjoy flying on Southwest and Virgin America more because the employees tend to be friendlier and the personal entertainment on longer flights breaks up the time.

Until airlines like American can prove that their higher prices reflect a better and more enjoyable service I'll keep picking the lowest price I can find. I don't mind sucking it up even if I end up in a middle seat between two big burly guys with no elbow room. We've all been there.

Instead of these airline companies being creative with accounting, they need to get creative with designing better experiences like Alaska Airlines is doing or consider re-engineering planes to fly with alternative fuels like Virgin highlighted recently when they used 5% biofuel. I might pay $15 more if I think it's worth it but I definitely won't pay an extra $15 to have a more miserable experience when I know I can pay less elsewhere.

With any luck, one of the travel sites will be updated so that I can search flights and compare the full cost for my travel knowing that I'll be gone for two weeks and will definitely be checking one bag if not two. Then the larger airlines will maybe take note and change their travel plans.

What do you think? Join the conversation in Comments

The Web, Information Architecture, and Interaction Design

by Jonathan Korman on September 1, 2005 | Comments (1)

The impact of digital technology—from the Web to mobile phones to the silicon in your toaster—has meant a proliferation of terms for the work people do to define digital products and services. People talk about "customer experience," "user-centered design," and so forth. This talk can confuse even people who do that work for a living, as you often find different people using different terms to mean the same thing—or using the same term to mean very different things!

Many people say that this reflects a breakdown of disciplinary distinctions in designing for the new world of the digital. "It's all just design." I disagree. I see a few major types of problems in the digital world, and I believe that each of these has its own set of tools and methods that work well to solve that type of problem.

Common Myths about Web Design

by Alan Cooper & Robert Reimann on March 1, 2004 | Comments (1)

The hype that surrounded the Web and its concomitant New Economy led to many popular myths concerning the design of Web content and Web-based applications. We can forgive this kind of mythology, which is typical of most popular technical innovations. When commercial and industrial use of electricity became a reality at the end of the nineteenth century, it was commonly believed to have miraculous powers not only to transform business and society, but also to cure almost any conceivable ailment by "restoring the life force." Like electricity, the Web has transformed our society to some degree, even in the relatively short time span since its introduction. However, it took 50 years for our use of electricity to mature, and it will doubtless take as many years for us to realize the full benefits and socioeconomic ramifications of the Web.

Some of the most common myths about Web design follow. These myths have found their way into business and technical organizations, and are—to some degree or other—taken at face value by management, marketing, engineering, and sometimes even Web designers themselves. The sooner you can disabuse your organization of these myths, the better.

Not All Web Sites Are Alike

by Jonathan Korman on April 1, 2003 | Comments (0)

With the Web now completely ubiquitous and familiar, and the frenzy of getting on the Web for novelty’s sake long past, companies routinely turn to the Web to address many types of challenges. A Web site can offer a simple brochure for communicating with customers, a way to disseminate information to people within a large organization, a tool for running complex business processes, and much more. Because different sites try to address different problems, creating them requires different kinds of planning and development.

Although it may sound like a truism, many people have a hard time talking about the distinctions between different kinds of Web development, which makes it difficult to decide how to proceed. This article offers a quick survey of various Web projects and of the techniques that address them.

Learning From the Mistakes of Internet Banks

by Chris Weeldreyer on July 1, 2002 | Comments (0)

Retail banks are realizing that Internet banking is not living up to the hype that surrounded it a few years ago. At that time, analysts predicted that demand would follow the trends in general Internet usage and grow to hundreds of millions of users by the middle of this decade. Some brave entrepreneurs were even betting that the age of the branch-based deposit institution was over, and that upstart "Internet-only" banks would be able to capitalize on hot new technology to steal all the customers. Yet adoption rates are low, and customer interest is flagging. Why? Online banking is a good example of how bricks-and-mortar institutions can stumble when they try to solve new economy problems with old world approaches.

Navigating isn't fun

by Alan Cooper on October 1, 2001 | Comments (0)

The artless Websites created during the Web's infancy were of necessity built only with simple HTML tags, and were forced to divide up their functionality and content into a maze (a web?) of separate pages. This made a navigation scheme an unavoidable component of any Website design, and of course, a clear, visually arresting navigation scheme was better than an obscure or hidden one. But many Web designers have incorrectly deduced from this that users want navigation schemes. Actually, they'd be happy if there were no navigation at all.

Beating the Checkout Blues

by Wayne Greenwood on June 1, 2001 | Comments (0)

Your online store is a good example of the breed. You've got good products at good prices, the site navigation is straightforward, the product information is rich, appropriate, and easy to find, and everyone likes the clean, uncluttered visual design of the site. So why do more than half of your customers abandon their full shopping carts?

Depending on which research report you read, roughly 25% to 75% of online shoppers abandon their shopping carts before consummating the deal. Despite the disparity in numbers, all the research firms agree on one thing: that's way too many.

The Iteration Trap

by Alan Cooper on January 1, 2001 | Comments (0)

High-tech companies are in a hurry—as well they should be—but many hurt themselves by trying to move products out the door too quickly. I often hear executives repeat homilies like "Ship early, ship often," and "Launch and learn." They assume that there is no penalty for simply slapping something together, shipping it, and then upgrading their product or site in a rapid iteration cycle. Unfortunately, there is a big, hidden cost associated with this tactic.

Rapid development environments like the World Wide Web have promoted the idea of simply iterating many versions of a product or service until something works. Arguably, the Web is in its nascent stage and companies are still experimenting to see what works and what doesn't, yet this should not be an excuse for iteration without planning, nor should "speed to market."