Intelligent Design: Transform Your Website into a Sales Engine with Machine Learning

Machine learning: The phrase evokes images of computers playing chess or IBM’s Watson destroying two legendary Jeopardy! champions in a three-day tournament. The truth is, though, machine learning is no longer a novelty; it’s now an integral part of our daily lives. Every time you receive a product recommendation from Amazon, your email server weeds out spam before it reaches your inbox or you enjoy a playlist on Pandora, you’re seeing machine learning in action. In a nutshell, machine learning is the science of training computers to recognize data patterns and make adjustments automatically when those patterns change. While on the surface this may not sound very exciting, nothing could be further from the truth. In fact, machine learning is the key to transforming your website into a lean, mean selling machine.

Understanding machine learning in 100 words or less

Machine learning uses algorithms to build models from data; as more data is collected, the algorithms are “trained” to adapt to changes. There are two ways in which machine learning can be implemented: supervised and unsupervised. Supervised learning algorithms are used to create models that establish relationships between types of data — the relationship between purchase data and user clickstream data, for example. Unsupervised learning uses algorithms to gain insights into customer behaviors and preferences by looking for patterns within the data. Both of these methodologies are designed to make marketing and e-commerce more exact, more personal and more profitable.

Putting machine learning to work

Netflix, Pandora and Amazon are all familiar examples of machine learning in action. All three use recommender systems powered by complex algorithms. These systems collect data about your browsing activities, past selections and any ratings or reviews you may have provided. Then they segment you into clusters with other customers who have demonstrated similar interests or behaviors and use this data to suggest items that might appeal to you based on the browsing and purchasing habits of these other customers. You see this on Netflix as the category titled “Because you watched...” and on Amazon as “Customers who viewed this also viewed...” To gain a deeper understanding of how these algorithms work, let’s take a closer look at Amazon. To Amazon, you are a very long row of numbers in a massive table of data. Your row represents everything you’ve looked at, clicked on, purchased (or, equally as important, not purchased) or reviewed on the site. The other rows in this gargantuan table encompass the same thing for the millions of other customers who shop on Amazon. With every click, visit and purchase, more data is added to your row, which allows Amazon to constantly mold and shape the products it recommends to you and the special offers you receive based on an ever-evolving stream of information about you that is being collected and stored. Another innovative example is True Fit, a retail software start-up that is on a mission to apply data analytics to increase customer confidence in online clothing purchases while decreasing the number of returns for e-railers. Well-known fashion retailers, including Nordstrom, Macy’s and Guess, have implemented True Fit’s algorithms on their e-commerce sites. When customers shop on these sites, they’re asked to create a profile that includes their height, weight and perhaps most importantly, the size and brand of their favorite piece of clothing. Using that data, True Fit is able to recommend the correct size for a specific brand and article of clothing. Even more importantly, as customers continue to use the True Fit system, it learns more about their personal style and preferences and steers them toward purchases they’ll be more likely to keep and enjoy rather than return.

How machine learning drives smarter marketing

You don’t need the resources of major e-commerce giants like Amazon or Netflix to take advantage of machine learning to to improve your e-commerce site and your online marketing efforts. By enhancing your existing site with systems that allow you to create a virtual marketing intelligence brain, you can create a more personalized – and therefore higher quality – shopping experience for your customers. By establishing this type of marketing intelligence ecosystem, you can mine the data provided by customers every time they visit your site to answer vital questions that will help you fine-tune your site and your online marketing strategy – questions like these:

• How likely is a given website visitor to convert?
• What behaviors characterize customers who are likely to buy?
• What behaviors characterize customers who are likely not to buy?
• How can new visitors be identified as high-potential long-term customers?
• Which type of web traffic has the most value?
• Which products or services appeal most to a given segment of customers?
• Given the contents of a particular customer’s shopping cart, which additional products are high-potential recommendations?
• How can website visits be optimized to provide the best possible experience for each individual customer?

Making it personal

The final question in the list above is one that deserves special notice because of the staggering potential for using machine learning to create a more personalized shopping experience – one of the key drivers for increasing online sales. Not only can the data collected via such marketing intelligence ecosystems be used to drive recommender systems, it can also be used to create personalized advertising based on market segments — or even individual profiles — that can be distributed across a variety of desktop, mobile and social platforms. This type of advertising can be tailored to any number of personal preferences and demographic information, including age, marital status, location, lifestyle choices, typical purchases, brand preferences and so on. Ads can be focused to such a granular level that they reflect specific colors a given customer prefers, and their individual purchase drivers, such as status or cost-effectiveness. Another exciting aspect of machine learning-based personalization is the development of individual customer profiles. You can even combine online and offline customer data to create a more complete picture of a given user. Types of data included in this profile might include online and in-store purchases, membership and activity in rewards programs, product ratings and clothing sizes. Just imagine how much more powerful your marketing efforts could be if you were armed with this level of information. One of the most important aspects of a successful marketing intelligence ecosystem is how data mined from customer activities is combined with sound business rules in order to make smart recommendations that are well received by customers and that do not compromise their trust in your brand. For example, most people who walk into a supermarket like bananas and will often buy some. So shouldn’t the recommender simply recommend bananas to every customer? No – because it wouldn’t help the customer, and it wouldn’t increase banana sales. So a smart supermarket recommender would always include a rule to exclude recommending bananas. At the other end of the spectrum, the recommender shouldn’t push high-margin items just because it’s beneficial to the seller’s bottom line. It’s like going to a restaurant where the server steers you toward a particular high-dollar entree. Is it really his favorite? Or did the chef urge the staff to push the dish because it comes with a side order of premium mark-up? To build trust, the best recommender systems strive for some degree of transparency by giving customers clues as to why a particular item was recommended and letting them adjust their profile if they don’t like the recommendations they’re receiving.

Science fact, not fiction

Machine learning can give your business a serious competitive edge by opening the door new opportunities in the marketplace. It can help you personalize and improve your customer experience dramatically and thereby drive sales and revenues. Creatives and developers alike are rapidly pioneering new and innovative ways for marketers to use machine learning — and the future of marketing built on these ideas has seemingly endless possibilities.

---

Six Lessons from the Google School of Logo Design for a Digital World

Recently, Google set the design world abuzz when they unveiled their new brand identity. Gone was the familiar, sophisticated serif font reminiscent of classic books and newspapers that rolled off the printing presses. In its place, a new mark that retains Google’s trademark rainbow of colors but with a new sans-serif typeface of the company’s own creation called “Product Sans.” Love it or hate it, Google’s reasoning behind their redesign and what they hope to achieve with this new logo offer some interesting insights that any company in today’s multi-screen, multi-device world should take into consideration.

1. Size matters.

In their article rolling out the redesign, Google cites the need to “create a scalable mark that could convey the feeling of the full logotype in constrained spaces” as one of the challenges that they wanted to address. The need to consider a variety of screen sizes has become incredibly important over the past few years with the growing adoption of small-screened devices – from mobile phones to wearables like smartwatches. The relatively tiny screens on these devices put space at a premium, and most brand marks that were created prior to the advent of these small screens struggle to adapt to a much smaller canvas. For a visual brand to be successful in today’s world, you must ensure that it can scale and adapt to work effectively on any screen size or device.

2. You must consider the whole ecosystem.

In the not-too-distant past, when designing a new visual identity, there were only a limited number of applications that had to be taken into consideration: business cards, letterhead, signage, collateral materials, ads, product packaging, etc. This is why many early websites were little more than digital brochures. Companies took what they already understood (printed brochures) and tried to port them over to a brand new medium (the Web). This was obviously not an optimal solution, and since then, web design has come a long way from the days of static brochure sites. In much the same way, it’s time for logo design to evolve by taking into account the full array of digital platforms in which brands must reside today, including websites, mobile apps and social media sites, just to name a few. Taken as a whole, these make up a complex ecosystem with different channels that build upon and feed off of others. As a result, Google’s new identity takes the form not of a singular logo but of a system comprised of three “elemental states” that are flexible enough to be used across all mediums and platforms:

• Google logotype: The sans serif logtype retains Google’s signature multi-color sequence.
• Dots: A dynamic distillation of the logotype that takes the form of four animated, perpetually moving dots that are used for interactive, assistive and transitional moments.
• Google G: A compact version of the Google logo that works in small contexts.

When evaluating your own logo and how it translates across different platforms and channels, it’s important to make sure that all of its elements and iterations work together seamlessly so that they feel connected to your core brand identity in order to protect the integrity of your brand throughout the ecosystem.

3. There’s more to logo design than choosing a typeface.

Talk to someone who does not understand the nuances of design, and they are likely to assume that the process of creating a logo is comprised of little more than selecting an attractive font and maybe adding an illustrated icon in front of it. In truth, however, logo design is its own unique and complex discipline. Just as Google did, any successful logo design process must consider the weight and legibility of that logo along with “spacing, clearance rules, and specification for in-product treatments.” It also must factor in big-picture thinking, such as how the logo will transform in various applications (when it must be displayed in black and white versus full color, for example) and whether it sets the right tone for the brand. Yes, using attractive letterforms is part of designing a quality logo, but this process goes way deeper than just font selection.

4. Performance matters.

How quickly a website loads is more important today than ever before. With mobile devices making up a larger and larger percentage of website traffic, and with emerging countries becoming an important part of the audience on the Web, the need to create sites that load quickly for all users is paramount. To accomplish this, website designers must look for ways to streamline a site’s overall file size. The new Google logo is only 305 bytes, which is a significant decrease from the old logo, which weighed in at ~14,000 bytes. Google actually had to deliver a text-based, non-image version of their old logo in some instances, but the new one is so small that it can be delivered to all connections, keeping the brand identity consistent. Overall performance is critical to the success of a website – after all, no one ever complains that a site loads too fast. You may not be thinking about download size and performance when creating a logo, but you should be, because improved performance should be a thread that runs through every decision you make on your website. Better performance can mean happier visitors, improved search engine rankings and better conversions rates for your website.

5. You can’t please everyone.

As soon as the new Google logo debuted, there were people praising the design as well as those tearing it down. Even within the design community, reactions on Twitter ranged from “The beautiful balance of utility and joy” to “I love the font in the new Google logo – a revival of Paul Renner’s rarely seen 1934 masterpiece, Futura Jackas” – proof that no matter how well-reasoned or well-intentioned the principles behind your design are, you simply cannot please everyone. One of the most challenging realities of a redesign, whether it is for a logo, a website or an application, is that you are forcing change upon people who did not ask for or expect it. Even if the change is for the better, it’s human nature to favor the familiar and therefore to react strangely to a change that they did not initiate themselves. Couple this with the fact that people are more likely to contact you when they dislike something than when they like it, and a redesign can quickly generate what feels like an overwhelming amount of negative comments. For some companies, this initial wave of critical feedback can be scary and may lead to the temptation to revert back to the old design. But you cannot give into this! If you followed a good process and if the new design is well thought-out and executed, you need to give it time for people to grow accustomed to it and embrace it. You cannot please everyone, but given ample time, you will find that a quality redesign will win people over, and all of those detractors will fall silent.

6. Redesign for the right reasons.

Because introducing a new visual identity can be disorienting for your customers, and because there’s no purely scientific method to ensure your redesign will be well received, it’s important to make sure that there is good reason behind your decision to reinvent the look of your brand. With Google, the logic behind their decision was clear: “Since its inception, the Google.com homepage has been strikingly simple: The quirky, multicolored logo sits above a single, approachable input field on a clean white canvas. But as technology moves forward, the canvas itself is changing, and the inputs and needs are becoming more diverse. New classes of devices and ways to interact and communicate have emerged with wearables, voice technology, and smart devices in the world around us. Users now engage with Google using a constellation of devices, and our brand should express the same simplicity and delight they expect from our homepage, while fully embracing the opportunities offered by each new device and surface.” In short, Google needed a new identity that would represent the brand as effectively to someone who is typing keywords into a search bar on a desktop as one who is using a smartwatch as one who is using a device that may not yet even be conceived – or at least available to the general public. Likewise, while you should never redesign your company’s logo just for the sake of redesign itself, if your brand has evolved since your logo was originally conceived – whether in terms of the products you offer, the audience you serve or the channels and platforms through which they interact with your brand – it may well be worth the risk to introduce a new, modernized identity that will support the growth of your company now and for many years to come.

---