LinkedIn Looking to Further Reduce E-Mail Notifications, Improve Relevance


LinkedIn Looking to Further Reduce E-Mail Notifications, Improve Relevance | Social Media TodayA few months back, LinkedIn noted that after repeated user complaints they’d undertaken a review of their e-mail notifications process, and significantly reduced the amount of e-mails they were sending as a result. Personally, I can vouch for this – like most users, I was getting daily updates about every single group I was in, whether they’d been updated with new content or not. Since the change, however, I’m seeing a lot less – LinkedIn says they’ve now reduced e-mail sends by over 50%, while complaints about e-mail notifications have dropped a massive 65% overall, a great result.

But LinkedIn’s not done – today, via their official blog, LinkedIn has detailed how they’re using a new, data-fuelled model to help refine and improve the quality and quantity of e-mail notifications they send users. The new system, called Air Traffic Controller (ATC), uses learning algorithms which take into account member interactions on the platform “to better determine the right frequency of communication you get from LinkedIn, at the right time, and through the right channels”.

It works like this…

Coming in for Landing

LinkedIn explains the ATC algorithm by first noting how the system determines relevance and individual preferences, based on on-platform actions.

From the official announcement:

“Our first priority is to determine the right balance of mobile notifications and emails. ATC will help us understand the best time for you to hear from us and which channel you prefer; be it email, push notification or SMS, as well as determining the right amount of messages we send you. We’re doing this by paying close attention to your communication-setting preferences and by building intelligence around how you interact with LinkedIn. For example, in the past, we sent an email for every connection invite you received. Now, if you receive a handful of connection invites in a short period of time, our platform will automatically roll that up into a single email.”

That example’s pretty basic, but you get the idea – ATC will factor in how you indicate your preferences to the system, based both on what you input in your settings and how you interact on the network. And while the first point makes logical sense, the second – ‘building intelligence around how you interact with LinkedIn’ – is a bit more vague and isn’t examined in much detail in the initial documentation.

The three areas of focus for ATC are:

  • Volume – LinkedIn’s reduced e-mail volume by more than half and is looking to refine this even further. The example provided on this front is that less e-mails will be sent to those who log-in to the site more regularly, as they’ve most likely seen all the relevant updates on the platform.
  • Frequency – LinkedIn’s putting daily and monthly limits on notifications.
  • Quality – LinkedIn will use ATC to determine each individual’s preferences to deliver more targeted content – this measure will be dictated by each user’s activity on LinkedIn.

Through this new system, LinkedIn’s hoping to better personalize each users’ individual experience and subsequent e-mail outreach profile. While little detail is given as to how each action on LinkedIn will influence ATC’s understanding in this respect, you’d assume that the system would be refined over time, enabling it to zone in on how each user needs and wants to be provided with updates relevant to them.

New Approach

As noted in the introduction, LinkedIn’s e-mail notifications have long been problematic, and have caused many headaches over the years, so it’s great to see LinkedIn taking this feedback on board and working to develop more responsive, intelligent systems. It’s also interesting to see LinkedIn taking a more algorithmic and data driven approach to this problem, something they’ve not done a lot of in times past.

The update also aligns with LinkedIn’s recent changes to their on-platform messaging functionality, which has received mixed responses from regular users.

Main image via LinkedIn

Social Media Today RSS


Three Easy Tips for Hyper-Personal Push Notifications


Nothing will turn off a mobile user quicker than a bad experience, and with 30% of users opening apps only once, there is a lot of room for improvement. And as more and more brands and marketers are diving into how to make sure their mobile game is on point—and keep from users jumping ship—they are looking into new solutions that can elevate the experience and keep that romance alive.

In fact, according to a Next-Gen Retail report, more than 60% of users have a better opinion of your brand if their mobile experience is on point. Aside from general app design, a big component of mobile user experience is communicating with your users through in-app messages and push notifications.

In-app messages are a great way to reach users that are actively tapping through your app, but they don’t extend to inactive users. This is where push notifications come in.

Push notifications are a critical tool for reaching users who are not currently using your app. Their unwritten rules of conduct can be tricky to navigate, but when crafted carefully they have the power to bring back, and even convert, passive users.

The best push notifications are personalized and triggered by a customer’s actions. If a notification is targeted and gives your customers useful information, they are much more likely to engage and have a positive experience.

For marketers considering push notifications in their mobile marketing strategy, these tips for triggering hyper-personalized notifications will help build brand loyalty, as opposed to pushing users away.

1. Make use of location with iBeacon and geofence technology

Mobile apps are becoming an integral part of daily activity—from shopping and eating to navigating and exploring. iBeacon and geofence technologies make it possible for businesses to proactively engage with users who are on the go, with uses beyond sending coupons to users near or in a store.

For example, airline apps can use geofencing and push notifications to notify users of a gate change at the airport when users enter its premises. Sports equipment stores can identify users who have entered a stadium and send them a deal on baseball gear or football gear, depending on the season. The options are vast and nearly limitless…

Friendly reminder: Don’t overuse iBeacons and geofences. When customers receive too many location-based notifications, they might delete your app and avoid your brick-and-mortar location. To measure actual uninstalls, run an A/B test with and without that push notification; this technique is proving effective.

2. Learn your users’ time preferences

In addition to its content, the timing of a push notification can have quite a bit of impact on its reception by the user. Rationally or not, users get annoyed with push notifications that come at inopportune times, such as during an important meeting or in the middle of the night.

Because users’ mobile devices are usually nearby, haptics associated with push notifications can be an irritating distraction. Unfortunately, your brand will be blamed for the disruption, even when human error causes your user to leave his or her phone on full volume during an important meeting.

To avoid mishaps, figure out what timing works for which users. If you send a push notification to all users at 8 AM PST, that’s fairly reasonable for people in California but pretty early for users in Hawaii. Sending push notifications by time zone is usually a safer bet than sending them all at once. That way, no matter where users are in the world, they would receive the notification at 8 AM their time.

The ideal time for the majority of your users can be figured out using some trial and error, combined with A/B testing.

With sophisticated tools, you can even set your push notifications to be sent at the “optimal time” for each user—based on each user’s individual history. The tools predict the likeliest time your user will interact with your app next, and they will send the notification close to that time. (Recent experiments at Leanplum with our clients have found that such optimal-time push notifications delivered 15% higher average revenue per user!)

3. Embrace segmented analytics

Look at various segments of users to see how and when they are using your mobile app. Make sure your push notifications reflect those varying habits.

For instance, March in Los Angeles is beach weather, and promotions for swimsuits are likely to be welcomed with open arms. If you try sending swimsuit promotions to Bostonians or New Yorkers in the middle of a blizzard… they will likely think you’re laughing at them and you’ll receive a less than warm reception for your message (especially if it wakes them up in the middle of the night!).

Your users also may have device-specific behaviors: They may use iPads in the evening and iPhones during the day. If you notice that pattern, it makes sense to send push notifications to iPads at a different time than on iPhones.

Carefully look at usage habits across different demographics and make sure every push campaign is carefully targeted, whether by content or timing.

Engaging and influencing your customers requires trial, error, and iteration, so A/B-test the timing and content of push notifications as well as the impact of sending a push notification versus not sending one at all. After the A/B tests are over, look at the campaign’s impact on all variables to make sure you don’t have any unwanted side-effects.

Push notification marketing has the power to influence behavior, but it needs to be used with care. Knowing your users and personalizing communication are the keys to success.

MarketingProfs All In One