Tag: recommendations

5 Ways to Boost eCommerce Sales with Product Recommendations

Businesses know that acquiring new customers is more difficult and costlier than selling new products to existing customers. This is why eCommerce businesses prefer to invest in a good loyalty program. And product recommendations is one of the best marketing tools that a retailer can have in its arsenal. After all, the right recommendation helps sell more products to existing customers.

Simply put, recommendations are suggestions made by the retailer on various things that the customer might also be interested in. But in order to do this, the company has to know its customers and what they want. This is to avoid scenarios like recommending red stilettos to a client who prefers white trainers.

The question now is how to successfully use recommendations to improve eCommerce sales. Here are five suggestions:

1. Generate Personalized Product Recommendations

Personalized recommendations are carefully calculated and chosen products that are offered with the customer’s shopping behavior and history taken into consideration.

[Image via Amazon.com]

Amazon is a prime example of personalized recommendations. First-time site visitors will initially see some generic suggestions that are either crowdsourced bestsellers or what other visitors are checking. But once a purchase has been made, they’ll see recommendations based on items they’ve bought or searched for recently. These suggestions are found in the product description of the item a customer is currently checking or on the homepage that they’re logged into.

2. Have Well-Timed Customized Email Recommendations

Email marketing is still one of the most effective marketing strategies. It’s affordable, practical, and can boost conversions. But to have a more robust customer engagement, personalized email recommendations are the way forward. After all, the more relevant the email’s content is, the higher the rate of emails opened, website visits and sales.

Amazon is again a good example of this strategy. The company’s AI sends well-timed emails that recommend products that the customer has just browsed on the site. The emails are also sent as soon as the customer leaves the site, thereby ensuring that they’re still receptive to recommendations.

3. Make Product Pages More Appealing With Relevant Suggestions

The product page is one area where you can make more recommendations. However, it’s important that you find the best way to showcase your items because at this stage, you’ll either push your client towards the checkout process or drive them away altogether. Data-backed recommendations can provide shoppers with more choices at this key stage. By putting together selections based on the customer’s interest, the odds of conversions can increase by as much as 411%.

[Image via Shopify.com]

Brands can boost conversions by suggesting complementary items. For instance, if the shopper is looking for shoes, they can cross-sell by suggesting a shoe rack. Product recommendations can also be based on the shopping patterns of other shoppers. For example, if previous shoppers also bought a necklace after buying a blouse, then the product page would recommend what “people who bought this product also bought.”

4. Don’t Stop at a Confirmed Order

A successful order confirmation doesn’t mean you have to stop making recommendations. This stage of the shopping process can still be a good arena for recommending items that the customer could buy. Think of it as a last chance to add more products to the deal.

There are two good ways to make the most of order confirmations. One would be to have recommendation popups. Aside from thanking your customers for their latest purchase, include messages that suggest “you might be interested in this product.” The second way would be to integrate recommended products in the order confirmation email. Make your offer more compelling with the promise of freebies or discounts in their next purchase.

5. Making Friendly Referrals

As already mentioned, recommendations shouldn’t stop just because a purchase has been made. Recommendations can be used as a referral tool, one that can push a brand further, generate traffic, and boost more sales.

Brands can do this by asking customers to share the news of their latest purchase with their friends via social media. Bear in mind that people are more likely to buy or use the same brand that a trusted friend has used and recommended. To make this easier for your customer, integrate a “Share This” button on the customer’s order confirmation page.

There’s no question that recommendations have positive results. It’s a marketing strategy that eCommerce businesses can easily adopt. So this year, put more emphasis on recommendations and see your sales numbers grow.

[Featured image via Pixabay]

January 29, 2018
Pinterest Experiments With Real-Time Related Pin Recommendations, Object Recognition

Pinterest is experimenting with new visual search technology. The company asks us to imagine discovering new products and ideas on Pinterest based on visually similar objects, as Pinned by people with similar tastes.

We’re told that’s the idea behind some of the latest technology the company’s Visual Discovery team is working on. Pinterest is sharing details on new experiments on its blog and in a newly released white paper by Kevin Jing, its head of Visual Discovery and founder of VisualGraph, which Pinterest acquired in early 2014.

“After the acquisition of VisualGraph last year, the team began work on a large-scale, cost-effective machine vision pipeline and stack to improve visual search results and the 1.5 trillion recommendations we serve each year,” a Pinterest spokesperson tells WebProNews. “Visual signals are used in almost everything we do, and with more than 50 billion Pins in the system, we have one of the largest, unique and richly annotated datasets available.”

Pinterest is experimenting with real-time related pin recommendations and object recognition. The former, for new pins entering the system (which haven’t had related pins in the past), are based on visual similarities of other pins in the system. According to the company, over 90% of pins now have related pins served up as recommendations.

The object recognition can power recommendations based on specific objects in a pin’s image. The company says it’s experimenting with blending these pins into related pin recommendations below a pin. A pin’s image of an athlete wearing a backpack, for example, might lead to related pins for a similar backpack, running shoes and/or athletic wear.

The company plans to roll out a version of this later this year depending on how the experimentation goes.

“By sharing our machine vision pipeline implementation details and the experiences of launching products (detailed in the white paper), we hope visual discovery can be more widely incorporated into today’s consumer apps, for greater use by everyday people,” the spokesperson says.

Read the white paper here and find more info in this post.

Images via Pinterest

May 29, 2015
Pinterest’s New Acquisition Should Help Its Search And Ad Offerings

Pinterest just announced that is has acquired the team and technology behind recommendation and commerce startup Kosei. The company says it will use he acquisition to accelerate its discovery and monetization efforts.

“The team includes some of the best minds in machine learning, data science and recommendation engines, who’ve created a unique technology stack that drives commerce by making highly personalized and powerful product recommendations,” a spokesperson tells WebProNews. “Among Kosei’s accomplishments is building a graph that understands more than 400 million relationships between 30 million products.”

Asked about how the acquisition will affect Pinterest’s efforts in search and advertising, the spokesperson said, “Over the years we’ve been building a system for helping people discover the most relevant Pins, and the Kosei team is a great complement to our existing technology (see how we’ve been using machine learning here). The acquisition of Kosei will enable us to move faster in our efforts to provide relevant recommendations across the service, as well as in ad targeting and measurement as we roll out Promoted Pins.”

The post linked to above talks about the acquisition, and notes that machine learning tech will be used by the discovery team, which includes search. This is something to consider if you’re considering your Pinterest SEO efforts.

As far as Promoted Pins performance goes, word is that the ads are already really good at getting clicks.

We’re told that Pinterest will be working with the Kosei team in the next 90 days to best understand how to integrate their team and technology.

Michael Lopp, head of Pinterest engineering, said in a statement, “As people use Pinterest to save and discover the things they want to do in the future, we have a growing data set of more than 30 billion objects that will only get more powerful over time. With these leaders in machine learning and recommendation systems, we can move faster in discovery and monetization, and building an infrastructure to help brands better understand customer intention and deliver the best content to Pinners.”

Head of Pinterest partnerships Joanne Bradford added, “Recommendations and ads systems are rapidly changing due to the confluence of mobile and personalization. The Kosei team and technology will help us accelerate our ad efforts by offering marketers more solutions to tap into our growing and valuable data set and object graph. This year we’ll provide the best ads canvas with the most actionable insights to reach an engaged and passionate brand-centric audience.”

Kosei co-founder and CEO Lance Riedel said, “We’ve delivered an amazing product that combines a wide range of disciplines, from machine learning to outstanding engineering and a deep understanding of products and consumer interests. As Pinterest builds a recommendation engine for all objects, joining the company will only accelerate our efforts, ultimately leading to very real benefits for commerce partners and Pinners. We’ve been focusing on revolutionizing recommendations with a deep understanding of serving beautiful ads to the right people in the moments that matter, and Pinterest’s vision for building a next generation discovery platform matches our own.”

Kosei is Pinterest’s 6th acquisition, after Punchfork, Livestar, Hackermeter, Visual Graph, and Icebergs.

Image via Pinterest

January 21, 2015
Netflix Spends A Lot On Content Recommendations

Netflix Chief Product Officer Neil Hunt spoke this week at the AMC Conference on Recommender Systems. You can watch the whole thing here:

The video is over two hours long, but GigaOm’s Janko Roettgers pulled some interesting info out of it, including the fact that Netflix is spending $150 million every year on content recommendations. The company also employs as many as 300 people specifically to maintain and improve this part of its business, which it obviously considers to be very important element in keeping subscribers. Roettgers reports:

Hunt explained during his talk that Netflix has a very limited window to convince a customer to watch something. The typical user only looks at the Netflix app one or two minutes, he said, and may browse 20 to 50 titles before either choosing something to watch or giving up entirely and doing something else.

Another interesting tidbit is that Netflix is about to start testing recommendations that take global data into account where it would typically use regional data.

Recommendations aren’t the only thing Netflix is trying to improve when it comes to getting people to find titles that appeal to them. The company has also recently introduced some search improvements.

About a month ago, the company unveiled a new “instant search” feature on its desktop site, which shows cover art for titles as you type. Along with that and an upgrade to its mobile search this week, you can also now search for “Netflix” to quickly access any of the company’s “original” titles.

Image via Netflix

October 10, 2014
Netflix Launches New Social Recommendations

Netflix just announced the launch of a new social recommendation feature, which enables users to recommend titles to people privately. When you finish watching something, it will ask you if you know anyone else who’d like the show, and will prompt you to find your friends using Facebook.

Netflix notes that it will not post anything to Facebook or share what you watch to your friends’ News Feeds.

“After selecting friends from a row of their pictures, and adding an optional message, click Send,” Netflix director of product innovation Cameron Johnson says in a blog post. “Your friends will receive the recommendation the next time they log into Netflix. They can thank you for the recommendation, and if they watch it or add it to their list, we’ll let you know.”

“For friends who have not yet connected Netflix and Facebook, we’ll send your recommendation as a private message to Facebook Messenger,” he adds.

The feature is available on the Netflix website, on iOS, PS3, and Xbox, as well as a variety of set-top boxes and smart TVs. Android is noticeably absent from the list, but the company says it will be adding additional platforms in the coming months.

Netflix has explained the complications of launching features on Android in the past, citing the operating system’s fragmentation as the main difficulty.

Netflix first launched Facebook integration last year.

Images via Netflix

September 2, 2014
Foursquare’s New, Still Check In-Less App Is Here

Foursquare went and pissed a bunch of people off when they decided to “unbundle” and separate the core functions of their main app into two apps. They relegated check-ins to a new app, called Swarm, and promised that Foursquare would relaunch in the summer as an app entirely devoted to local search and recommendations. Some with an if it ain’t broke don’t fix it mindset were skeptical.

Despite the criticism – which they most certainly saw coming – Foursquare is moving ahead as planned. Foursquare’s new app – new logo and all – is now available for download. Foursquare had already cut check-ins out of the main app, but the new app showcases Foursquare’s vision – the reason why they chose to split everything up.

Launching the new Foursquare app prompts a wizard of sorts wherein Foursquare asks you to give it some information on your tastes. If you’ve been using Foursquare for any amount of time, it already knows a little bit about you – but this sort of “taste” mapping is at the heart of the app’s new recommendation focus. Based on what you like (revealed by activity and what you tell it specifically), Foursquare will recommend places you might like nearby.

“Every search is tailored to your tastes, your past ratings, and picks from friends and experts you trust,” says Foursquare.

Tips are also at the heart of the new Foursquare. As promised, Foursquare has developed a new “expertise” ladder for tips. The more you tip about certain areas, types of locations, or varieties of cuisine – and the more people respond to your tips by saving them – the faster your “expertise” levels up. That expertise level will be displayed to all, so that people can feel a bit more comfortable in trusting your tips.

“Friends” are now “followers” (friends are for Swarm, ya dinguses). People who follow each other will have their tips placed more prominently in the app.

“There’s no reason why we should all get the same recommendations when looking for a place to eat, drink or shop. Getting a one-size-fits-all list of places may have been innovative in 2006, but it feels downright antiquated now,” says Foursquare. “The new Foursquare frees you from having to read long, random reviews, wondering if those people share your tastes. With Foursquare, find things based on your tastes, the places you like, and the friends and experts you trust most.”

So, what’s Swarm’s place in the world of new Foursquare? Not hugely prominent, but definitely present. Your check-ins on Swarm will help power Foursquare’s recommendations – but as noted before, check-ins on Foursquare are dead. Not only can you not check in on it, your Swarm check-ins will never appear anywhere on the new Foursquare app.

“The world is a beautiful place full of all sorts of amazing experiences, and our phones should help guide us to them. We’re releasing it today, and can’t wait for everyone to experience it,” says Foursquare.

How’s the app look? Nice. It looks nice. Would it look or feel any more cluttered with check-ins and an activity feed. Probably not.

Image via Foursquare app, iTunes

August 6, 2014
Check-in Out: Foursquare Officially Kills Check-ins

Just a few hours after touting Swarm’s success in becoming users’ go-to place for check-ins, Foursquare has announced that starting tomorrow, all check-ins will be moving to that app. For the first time since its launch in 2009, you won’t be able to check in using Foursquare.

Back in May, Foursquare decided that to survive and flourish, they were going to have to split apart. The company announced the launch of a new app called Swarm, one that would be tailored to handle the checking in aspect of the service – while transitioning the main Foursquare app into one entirely focused on local search.

But up until now (tomorrow), check-ins have still worked on Foursquare, and any check-in made on Swarm automatically shows up on the main Foursquare app. Foursquare has always made it clear that Swarm would be the place for check-ins, and now they’re making good on that promise – like it or not.

“Starting tomorrow, we’re moving all check-ins to our new app, Swarm. Don’t worry; all your past check-ins, all your friends, all your photos, they’re all automatically in Swarm. For everyone still using Foursquare to check in, you’ll need to download Swarm to keep checking in,” says the company.

If you look above, the left-hand view is a Foursquare venue page for someone who doesn’t use Swarm. As you can see, there’s no check-in button. On the right, however, there’s a Swarm-powered check-in button. If you have downloaded and signed up for Swarm, that’s the venue page you’ll see on the Foursquare app. So yes, you can technically check-in from the main Foursquare app, but not on it.

As for the new Foursquare we’ve been promised – well, it’s coming soon. Foursquare says a couple of weeks, to be not-that-precise. What we do get today is a brand new logo. At least is doesn’t look like balls.

Foursquare echoes the same kind of constantly-touted benefits of personalized recommendations (It doesn’t get you, and, as a result, everyone gets the same one-size-fits-all results. Why should two very different people get the same recommendations when they visit Paris?). Few people would argue that notion. The question is – can Foursquare deliver on bettering local search?

“This is the beginning of the ‘personalized local search’ future we’ve been talking about since we started Foursquare. It’s been built with the help of our amazing 50,000,000-strong community, with all your tips, check-ins, photos, and the smarts we layered on top of that. Those of you have been with us since the beginning, your check-ins and history will continue to help shape your recommendations. For those of you giving us a try for the first time – you still get all the benefits of a better way to explore any neighborhood, no check-ins required,” says Foursquare.

More like no check-ins allowed. If you’re on the fence about Swarm, I will tell you that there is a pretty killer unicorn rainbow sticker over there.

Images via Foursquare Blog

July 23, 2014
Etsy Aims To Help Sellers By Giving Buyers Custom Recommendations

Etsy announced this week that it is making some changes to make the shopping experience better for customers, which will in turn positively affect sellers.

Etsy’s Heather Burkman says one such change is through custom recommendations. She talks about a recent email test Etsy ran.

“Half of the buyers received an email with the same set of items, and the other half received custom sets of items based on their individual shopping preferences,” she explains. “The group with customized recommendations were twice as likely to come back and purchase than the group that received the same set. Not only do custom recommendations better connect the right buyers with the right shops, but they also bring exposure to a greater variety of sellers.”

“We’ll be testing more custom shopping recommendations on Etsy, to give buyers more ways to discover items,” she adds. “Overall, we see value in both curated and custom shopping experiences, as they serve different needs of shoppers.”

These days Etsy is offering users around 20 million items. In 2013, it sold over $1.35 billion worth of goods.

Image via Etsy

February 21, 2014
Google Reportedly Trying Another Content Recommendation Product

Google is reportedly getting ready to launch a new content recommendation tool for publishers that would point their website visitors to more of their articles.

Search Engine Journal shares a snippet from an email it and other Google partners have been receiving:

Our engineers are working on a content recommendation beta that will present users relevant internal articles on your site after they read a page. This is a great way to drive loyal users and more pageviews.

It’s unclear exactly what this will look like, and what the recommendations will be based on, but SEJ’s Matt Southern notes it is based on a different algorithm than one Google was using for mobile sites last year.

You may also recall another time Google offered a content recommendation tool via its +1 button:

At some point, that appears to have gone away.

Image via Google

February 11, 2014
Foursquare Now Pushes Recommendations to All Users with 7.0 Update

With the new 7.0 update, Foursquare is pushing recommendations to all iOS and Android users – even when they don’t have the app open. Now, when you arrive at a location (be that a specific city or state, or a specific venue), Foursquare will let you know what to eat, buy, see, and more.

These real-time recommendations aren’t new – in fact, Foursquare has been testing them out for months. But this is the first time they’re bringing the feature to all users.

“The idea behind Foursquare has always been that, someday, hundreds of millions of people will carry software in their pocket that lets them know when friends are nearby, when places they’ll love are around the corner, and whether nearby merchants can help them save money. This is the future we’re spending our days building,” said Foursquare when they first began to push these types of notifications to users.

And with version 7.0, Foursquare has made good on this vision. Though the new app doesn’t make use of all the possible push notification scenarios that one could imagine, it makes use of the most popular and well-received type – the “once you arrive at a location” suggestion. It’s passive recommending, something that Foursquare has been talking about and experimenting with for years.

With 7.0, Foursquare has also offered up a significant design change, as well as tweaks to help you better explore what’s around.

“Foursquare has been completely redesigned for iOS 7 and there’s a lot to see. It’s smarter, faster, and has a whole new look,” says a post on the Foursquare blog. “We shuffle the deck every time you open the app so you don’t miss a thing. Just swipe to explore great tips, find money-saving specials near you, and check out the feed to see what your friends are up to tonight.”

A couple of months ago, Foursquare touted that they now have well-over 40 million total users. Earlier this year, the company expanded their ad offerings by showing sponsored tips after check-ins and opening up self-service advertising to any and small businesses.

You can download the new app on both iOS and Android today.

Image via Foursquare Blog

December 6, 2013
Pinterest Adds ‘Related Pins’ To Your Home Feed

Pinterest announced today that it is going to start putting recommendations dubbed “related Pins” in your home feed.

While this means you will be getting content from boards that you aren’t necessarily following, it also means that you will have a new way to discover content that you might actually enjoy. The keyword is “might”.

“Related Pins are picked specially for you based on the unique things you’re into, such as other Pins you’ve saved or liked,” explains Pinterest software engineer Dmitry Checkik. “So if you’ve been collecting recipes for your big holiday feast, we might show you a related Pin for fool-proof pie crust, or the perfect double-stuffed sweet potato”

Pinterest says it will only show you a few of these at first, and will use the feedback you give them to improve on what it shows you in the future. If you click the “i” you can rate the pin with a thumbs up or thumbs down.

In the comments of the blog post announcing the feature, users are already saying they dislike it, and are asking if they can opt out. While that’s only an early few, it’s not a great sign, especially since they are starting to include ads in the mix as well.

October 29, 2013
Foursquare Brings Real-Time Recommendations to iOS

Foursquare has just announced that their new style of real-time recommendations are now being pushed to some iOS users through an app update released today.

“When you arrive someplace, we can tell you something great there (like the best thing to order, or a money-saving special). With this release, we’re turning real-time recommendations on for a small batch of people who use Foursquare on their iPhone (and expanding to more every day),” said the company on their blog.

Foursquare’s new recommendations ping users when they get near (or check-in to) certain locations, and suggest things like popular menu items and current deals. Of course, this works with a variety of types of locations, but these new recommendations are going to be especially useful for restaurants.

The feature is only going to be available for some iOS users right now, but Foursquare will expand it eventually. Android got this feature about a month ago.

“The idea behind Foursquare has always been that, someday, hundreds of millions of people will carry software in their pocket that lets them know when friends are nearby, when places they’ll love are around the corner, and whether nearby merchants can help them save money. This is the future we’re spending our days building,” said Foursquare.

And that’s the key – passive recommendations. Foursquare wants to let you know what’s good at that restaurant you’re at or what one user had to say about that concert venue before you even have to ask.

With the new Foursquare for iOS, the company has gone back to a previous format which allows users to quickly sort recent friend check-ins by “nearby” or “worldwide.” They’ve also streamlined your feed to only show your friends’ most recent check-ins. To see all of their other check-ins you have to go to their profile.

You can grab the latest version on iOS now.

Image via Foursquare Blog

October 9, 2013
Twitter Rolls Out New Recommendations

Twitter announced that it is rolling out a new kind of recommendation to some users, which aims to deliver personalized suggestions based on when multiple people in the user’s network follow the same user or favorite/retweet the same tweet.

As Twitter recently noted, it is experimenting a lot with different features these days, testing them with small sub-sets of users before launching them to wider groups. The company has been experimenting with the technology for this particular feature by using an experimental account – @MagicRegs.

Twitter software engineer Venu Satuluri explains in a blog post:

As its bio notes, @MagicRecs “sends instant, personalized recommendations for users and content via direct message”. Over time, we’ve been tweaking the algorithms –– based on engagement and your feedback –– in order to send only the most relevant updates.

And that brings us to today –– after getting great feedback, we’re bringing this functionality to more users. Twitter for Android and Twitter for iPhone users will receive recommendations via a push notification. As with any notification, you can change your settings at any time; you can turn these notifications off or on with the “Recommendations” toggle in your notifications settings.

Twitter says it will continue to use the @MagicRecs account for experimentation, so expect further tweaks to the feature as time goes on.

Image: Twitter

September 25, 2013
When And Where You Watch Something On Netflix May Soon Play A Role In What You Watch

If you use Netflix regularly to stream movies and shows, then there’s a really good chance that its recommendations play a pretty big part in your viewing habits. This will likely be even more the case from now on, now that the user profiles are rolling out. Now, you won’t have the distractions of what Netflix thinks other people in your house want to watch. It’s going to be more personal than ever.

Wired spoke with a couple of Netflix engineers, producing a rather interesting look into the kinds of things Netflix takes into consideration when determining what to show users as recommendations. It turns out, as you might have guessed, that they use a lot of different data points related to your usage habits. I say usage, because it’s not just about viewing. In some cases, it’s literally about how you interact with the Netflix interface (in addition, of course, to your viewing habits).

“We know what you played, searched for, or rated, as well as the time, date, and device,” explains engineering director Xavier Amatriain. “We even track user interactions such as browsing or scrolling behavior. All that data is fed into several algorithms, each optimized for a different purpose. In a broad sense, most of our algorithms are based on the assumption that similar viewing patterns represent similar user tastes. We can use the behavior of similar users to infer your preferences.”

He also says Netflix is working on incorporating viewing time data into the recommendation algorithms.

“We have been working for some time on introducing context into recommendations,” Amatriain tells Wired. “We have data that suggests there is different viewing behavior depending on the day of the week, the time of day, the device, and sometimes even the location. But implementing contextual recommendations has practical challenges that we are currently working on. We hope to be using it in the near future.”

Another interesting bit of the interview has Carlos Gomez-Uribe, VP of product innovation and personalization algorithms at Netflix saying that “predicted ratings aren’t actually super-useful.” This, of course, was what the famed “Netflix Prize” was based on.

Funny how things change.

August 7, 2013
Meet Max, Netflix’s New Recommendation Companion

Netflix has been using its algorithms to suggests movies and TV shows that you may like for some time now. Sometimes those suggestions are good, and other times they are hilariously bad. It all has to do with what you watch, how long you watch it, and whether or not you rate it. I guess what I’m saying is that it’s kind of your fault too, you know.

Merely suggesting titles is a static experience, however, and Netflix apparently wants to make the process more dynamic. To that end, they’ve just unveiled Max, an interactive recommendation companion. Yes, it’s a Netflix wizard. I guess it’s kind of like Clippy.

For PS3 users, Max will now be there when you open up your Netflix app. For everyone else, Netflix says that it depends on how Max “performs.” They say that if all is good, then Max will begin to pop up on more and more devices – probably the iPad next. It’s also only available to users in the U.S. for now.

If you choose to activate Max, there are a few ways in which he’ll try to find you something to watch. One method involves having you rate a few titles within a given genre. Another has you pick between two very different movie stars, and Max will pick a film starring one of them. Another lets you pick between two incredibly specific subgenres (think “tortured geniuses”).

Then there’s “Max’s Mystery Call.” This is when Max gets ballsy and decides that he already knows something that you’ll love. All you gotta do is just go with him.

At any time after Max has selected a movie or TV show for you to watch, you can either have him choose again or simply say no thanks.

If you don’t stream Netflix on a PS3, you can check out what will likely be coming to you in the near future below:

June 28, 2013
Google+ Aims To Lower Your Site’s Mobile Bounce Rate

Google announced the launch of content recommendations for mobile sites via the Google+ Platform. By adding a line of code, webmasters can encourage users to look at more of their articles when they’re browsing mobile sites, by delivering recommended (by Google) content based on a variety of factors.

“When you help someone find a great article on your site, you’re not only making them happier, you’re inspiring deeper engagement and loyalty,” says Google+ product manager Mario Anima. “That’s why today, we’re bringing together elements of Google+ and Google Search to suggest the right content from your mobile website, at just the right time.”

Anima explains, “For example: Forbes visitors can now more easily discover other Forbes articles based on Search Authorship, signals and other articles with lots of Google+ activity (including +1’s and shares). In all cases, recommended content is based on the specific page the visitor is viewing, to boost the relevance of recommendations. And they only appear when people tap for more, so as not to interrupt their browsing experience.”

Recommendations will show up regardless of whether users are signed into Google+. When they’re signed in, they’ll just be more personalized, based on content that was shared or +1’d by people in their circles – not unlike Google’s personalized search results.

Documentation for implementation can be found here.

May 13, 2013
Cancer Sample Handling Changes Called For By Doctors

In a column appearing this week in the Journal of the American Medical Association (JAMA), doctors have called on the medical community to change the way it handles cancer tissue samples. At issue is the rise of new gene sequencing technology, which traditional sample handling practices impede by damaging DNA.

“Deciding how best to obtain (tumor) samples and how best to process them for whole genome or exome sequencing is a pivotal yet unresolved issue with several layers of complexity,” said the column’s authors, who are from the Scripps Translational Science Institute (STSI), a non-profit biomedical research organization. “As the new clinical applicability of genomics emerges at a fairly rapid rate, the field of pathology will arrive at a tipping point for a fundamental change in how cancer specimens are handled.”

The current methods for sample processing involve placing biopsy samples into a formaldehyde mixture called formalin, then placing them into paraffin. Using gene sequencing on samples prepared this way, say the doctors, is difficult because the chemicals involved damage the sample’s DNA.

“We need to completely rethink the way we have collected and stored cancer tissue samples for decades,” said Dr. Eric Topol, one of the column’s authors and director of STSI. “It’s becoming increasingly clear that obtaining an accurate map of a tumor’s DNA can be the key to determining the specific mutations that are driving a person’s cancer, how best to treat it and how likely it is to recur.”

The alternative the doctors recommend involves freezing a portion of samples, which preserves the tissue’s genetic coding. That procedure, however, would require larger biopsy samples and incur higher storage costs. The doctors point out, though, that patients would likely agree to more invasive biopsy procedures if it means better diagnosis and treatment.

“This type of change will require discussion about new operative standards, which will need the cooperation of surgeons, pathologists, ethicists and, of course, appropriate patient consents,” said Dr. Stanley Robboy, president of the College of American Pathologists. “It’s these types of implications we will need to consider and incorporate as a progressive healthcare agenda is moved forward.”

January 4, 2013
Foursquare Further Integrates Facebook in Order to Fight Facebook

Foursquare has just made a counterattack against Facebook in the battle for location recommendation supremacy – by further incorporating Facebook into its service.

Starting today, you will now see new Facebook-oriented information on Foursquare locations, and Foursquare is going to use the power of your Facebook friends in their recommendations as well. As long as you’ve connected your Facebook account with Foursquare, you will now see indicators like “X Facebook friends left tips here” and “X Facebook friends liked this place.”

You’ll also see specific tips from specific users, like “Your friend Sam X left a tip here.”

The important thing about this new Facebook data is that you will see these tips from Facebook friends, even if you’re not Foursquare friends with them.

“By expanding your recommendations to include your Facebook friends who are on Foursquare, you’ll get even better personalized insights when you’re deciding where to go, while still only sharing check-ins with your close friends – the ones you’re friends with on Foursquare,” they say.

Foursquare reminds users that no privacy settings have changed. They’re simply using the information they already have, but finally displaying it prominently within their app and on desktop.

“Your check-in privacy remains the same. As always, we’ll never post to Facebook without your permission, and your Facebook friends will never see your check-ins unless you friend them on Foursquare.”

The timing of this is particularly interesting, considering Facebook just unveiled a huge revamp of its “Nearby” feature. Now, Facebook users can get personalized location suggestions based on their friends’ activity. Of course, this move was seen as a direct play at the local recommendation market of which Foursquare enjoys a substantial piece. This move by Foursquare, as well as the recent updates to their iOS app, amounts to a counterattack – or at least a deflection.

December 20, 2012
Facebook Turns Nearby Feature into an Actual Location Recommendation Tool

Facebook has just announced a huge revamp of their Nearby feature inside the mobile app that turns it from a not-too-remarkable tracker of friends’ check-ins to an actual attempt at a personalized local recommendation engine.

Now when you open up Nearby, you’ll see a search bar, a history list, and a bunch of new location categories – restaurants, nightlife, arts, hotels, shopping, etc. Each category has its own subcategories, like Mexican food inside restaurants or movie theaters inside the arts category.

Facebook is not just listings locations arbitrarily, or based on their global popularity. With Nearby, Facebook is using true social recommendations to find the best places for you based on your friends’ interactions. Let’s say your good friend Jimmy just gave an Indian restaurant a few miles away from you a great rating when he checked-in last night. Well, there’s a good chance that Facebook’s NEarby algorithm would put that location front and center for you.

“When someone looks for a place, the results that appear in their Nearby list are based on things like their friends’ recommendations, ratings, check-ins, and likes,” says Facebook.

Once you choose a location, you’ll be presented with Facebook’s redesigned location pages which include friends who’ve been there, hours, a map, star ratings, and reviews.

After you’ve experienced the location, Facebook wants you to share that experience with your friends through rating and reviewing. In theory, the more people that participate in this way, the better the recommendations will become.

Facebook encourages businesses to update their pages to include any and all information, including their category so they can be easily found through Facebook’s new Nearby product. Also, now more than ever, businesses need to make sure users are liking, checking into, rating, and sharing their Facebook page so that Facebook knows to recommend them when people are looking for things to do on the go.

So, Facebook has finally gotten into the local search game in a real and meaningful way. Facebook says that 150 million people visit Pages on a daily basis – so they have a rather impressive amount of like, check-in, and rating data to pull from. This, in theory, could make Facebook Nearby incredibly useful. They say that this is an early build, and “there’s a lot more to do.” But Facebook’s foray into truly personalized location recommendations should make the folks over at Foursquare and Yelp pay attention. Facebook says that the Nearby update should be available later today on iOS and Android.

December 17, 2012
Ovarian Cancer Screening Not Recommended by USPSTF

The U.S. Preventive Services Task Force (USPSTF) today issued its final recommendation for women considering being screened for ovarian cancer. The task force does not recommend that women undergo ovarian cancer screening as a prevantive measure. The recommendation applies to women of average risk who show no symptoms of ovarian cancer and do not have genetic mutations that increase their risk of getting the disease.

“There is no existing method of screening for ovarian cancer that is effective in reducing deaths,” said Dr. Virginia Moyer, task force chair. “In fact, a high percentage of women who undergo screening experience false-positive test results and consequently may be subjected to unnecessary harms, such as major surgery.”

The USPSTF pointed out that today’s recommendation is in-line with recommendations by the American Cancer Society and the American Congress of Obstetricians and Gynecologists, neither of which recommend screening for ovarian cancer. The task force’s full recommendation is available on its website or in the online version of the Annals of Internal Medicine.

“Currently, routine screening for ovarian cancer has no proven benefit and may actually lead to important harms,” said Moyer. “In light of this, there is a critical need to develop better screening tests for ovarian cancer.”

The USPSTF is an independent panel of physicians and experts in preventive medecine that uses evidence-based medicine to recommend preventive care and procedures to primary care physicians. It’s recommendations are highly regarded by the medical community. The task force last month recommended that HIV tests become more routine for preventive care.

September 11, 2012
Google Affiliate Network Gets New Recommendation Engine

Google announced that it has released a new recommendation engine for the Google Affiliate Network.

Publishers can go to the Advertisers > Recommended advertisers sub-tab to find a list of available programs ranked based on relevancy and predicted performance. Recommendations show why they were made and estimates of earnings potential. Advertiser recommendations are displayed based on whether they are in a similar category to the publisher category and the revenue potential (based on estimated payout fees).

“In addition to the average advertiser EPC, each recommendation has an estimated advertiser EPC. Estimated EPC is a brand new metric designed to help publishers understand how much they could potentially earn with that advertiser,” says Google in a blog post.

Additionally, under the Links > Recommended links sub-tab, Google displays recommended text and banner links, based on what Google’s algorithms think will perform best for publishers.

Of course, Advertisers can see publisher recommendations too. They can do so under the Publishers > Recommended publishers sub-tab.

August 9, 2012