Say goodbye to guesswork and hello to data-backed decisions. The dashboard offers comprehensive insights into every stage of your app’s lifecycle, empowering you to make smarter decisions that drive results. With over 49 different reports and the ability to filter by tags, attributes, and device properties, the App Health Dashboard will be your trusted companion and  transform your mobile optimization and marketing strategies. 

Drive More App Downloads
Are you tired of playing the customer acquisition guessing game? Say goodbye to acquisition uncertainties with the App Health Dashboard! Identify and track the strategies driving the most installs and lower your Customer Acquisition Cost (CAC) and Cost Per Install (CPI). Dive into data on app installs, uninstalls, and net gain to optimize your acquisition strategy for maximum efficiency.

Deliver Value in The App 
Data-backed insights make it possible to create experiences to onboard customers and capture their preferences successfully. Compare opt-in rates, device types and audiences so you canfine-tune your onboarding experience. Discover where activation rates drop so you can create messaging programs and native no-code app experiences that showcase the actual value of your app and get customers to share their preferences and interests.

Engage Your Customers Effectively
Boosting app engagement has never been more data-driven! Analyze session frequencies, track KPIs and monitor MAUs and DAUs to ensure your app engagement is trending in the right direction. Track session duration, engagement rates and impressions to discover the most opportune times to connect with users on their preferred channels.

Build More Loyal Customers
Loyalty is the golden ticket, and the App Health Dashboard helps you cash in! Create and track custom events, such as purchases, for each loyalty tier. Identify segments that are revenue powerhouses and those needing a little extra love. Compare long-term retention rates across different audiences, ensuring your app becomes a mainstay on users’ devices.

We get it. Data is not just numbers; it’s the key to unlocking unprecedented success and making smarter, faster decisions. With the App Health Dashboard, you’re not just tracking metrics; you’re uncovering insights to help shape the future success of your app and forge lasting connections with your audience.

Ready to revolutionize your mobile marketing strategy? Dive into the future with Airship’s App Health Dashboard and optimize every stage of your app’s lifecycle!

The post A New Tool to Help Marketers Measure and Optimize Mobile App Performance appeared first on Airship.

This isn’t a new trend, when we look at retention data over the last two years the trend line remains the same. 

In 2022 year to date we’re seeing the Android retention rate drop by 38% between Days 1 and 2 and for iOS retention rates drop by 34% between Days 1 and 2.  By Day 30 retention rates drop to an average of 9%.  

Liftoff’s 2020 mobile app trends report estimates cost per install for a new app customer in North America to be $5.28 

This means that if you have 10,000 customers install your app each month at a cost per install of $5.28 and you have an average drop off of 67% in the first 30 days your cost impact of that customer loss is ~$424k per year..

What are you doing during this critical first 2 days to make a good first impression on new customers for your app?

These 2 days occur within the “Activation” phase of the Mobile App Experience (MAX) Customer Lifecycle.  There are steps you can take to optimize your costs and activate your new customers.

The Activation phase is all about first impressions and you know you only have one chance to make a positive first impression. 

It’s time to evaluate your app’s customer onboarding experiences. 

“a 5% increase in customer retention produces more than a 25% increase in profit”
Bain & Company

1 .  Ask for preferences from your customers, but only if you’re going to use them to personalize their experience

There’s a tightrope to walk when it comes to gathering preferences.  Stephanie Liu, Forrester Analyst, says that “consumers can want both privacy and personalization”.

If you ask a customer for information, make sure you’re utilizing that data to personalize their experience as quickly as possible.  This builds trust and also encourages them to come back to the app. 

2 . Explain why opting into notifications benefits the customer 

We’ve all been there.  You open an app for the first time and before you can even look at the first screen, it bombards you with requests (ATT, Opt in, creating a login, etc).  Some customers abandon the app right away, and others may dismiss the onboarding screens completely.   Prioritize gathering  information that helps them within the first 14 days.  Then go back to ask for more data later.  

“95% of unaddressed new users churn within 90 days”
Airship Benchmark Report: How Push Notifications Impact Mobile App Retention Rates

If you’re looking for help with an audit of your onboarding experience, reach out to your Airship Account Manager to learn about a  use case audit.  We also have Strategic Services available to help guide you in developing onboarding experiences for your app.

The post First Impressions: Optimizing the Activation Phase appeared first on Airship.

A customer data strategy includes all of the relevant events that need to be tracked, the set of identities that are accessible, and the various data objects that should be captured in order to achieve business goals. With a data strategy in place, you can better understand what data is available and more effectively use data to deliver great mobile app experiences.

The path to creating your data strategy is bespoke to your business. Teams often start with a single use case around customer data and don’t establish a comprehensive data strategy as they scale their digital presence. But this increases risk exposure when internal and external conditions change.

Inside most companies:

• Websites and apps change, with landing pages and app screens being added, optimized, or removed
• New campaigns are run, often requiring new data flows to measure success. New tools are required to optimize performance, thus requiring new integrations
• Event tracking changes as developers across different platforms work in silos over time
• Customers toggle between known and anonymous states, and across different devices, which requires dynamic identity resolution capabilities
• Users update their consent preferences to opt out of personalized experiences, and their information will need to be extracted from certain flows and tools
• Models are built and experiments are run which force several of these steps to be repeated

And in the market:

• New privacy regulations such as GDPR and CCPA fundamentally change the way you can collect, manage, and activate data
• Apple and Google create new platform rules that change how you can access cookies and device identifiers
• API requirements change as vendors continually update their offerings and specs

Teams end up making a faustian bargain in their pursuit of growth. The challenge becomes adapting to the changes — more use cases require that more tools added, the number of data objects grows exponentially, and the subsequent maintenance due to API changes increases, not to mention the introduction of new privacy requirements. It all becomes quite overwhelming.

This is Data Chaos. This is a universal phenomenon.

How to solve data chaos

General Stanley McChrystal defines risk as “threats times your vulnerability to those threats.” The reality here is that teams can’t always control external factors that threaten their data strategy, such as new regulation, policy and platform changes etc., but they can strengthen their vulnerability to those threats.

To effectively scale, teams need to first think about solving for their vulnerabilities. The focus should first be on improving adaptability to properly address the dynamic needs of the organization.

Implementing a trusted Customer Data Infrastructure that can protect data quality and improve data governance is the precursor to successful activation and personalization. Without this, teams will experience the common phenomenon of “garbage in, garbage out.” And with lots of channels and partners connected, that’s a whole bunch of garbage.

What about the alternatives?

Application-focused CDPs and Marketing Suites focus on providing rich audience insights and segmentation capabilities. These are only valuable tactics when there is a strong, adaptable data quality and governance foundation. The best dashboards and segmentation capabilities will not make an impact if the data is bad or the pipelines break at critical moments.

The Modern Data Stack and Reverse ETL providers offer an interesting activation solution for data engineering teams building a data architecture around the cloud data warehouse. The reduction in both the cost of storage and compute has made this appealing on the surface. And while this approach may solve some of the technical challenges around customer data activation, they too ignore the operational challenges related to perpetual market changes, as well as the huge opex burden created by the need to manage that change. Basic questions such as “how is data quality managed?” and “how is privacy incorporated?” are often brushed aside entirely.

By decoupling data from where it’s actioned and forcing clients to operate within rigid systems, these offerings do little to help teams battle the entropy in their systems.

The solution

Customer Data Infrastructure should provide the adaptability required to manage new data connections, privacy changes, and market shifts. Operating in a state of data order, teams can access high-quality, real-time data and use it to power personalized app experiences scale.

If brands want to solve the activation challenge, they need to begin by solving the data chaos challenge, including both the technical and the operational aspects. Customer Data Infrastructure should work alongside your Cloud Data Warehouse, and should support customer engagement tools such as Airship.  your activation tools including even an Application CDP.

With high-quality customer data being forwarded to Airship, you’re able to execute your data strategy at scale and power experiences that drive post-purchase up-sells, reduce checkout abandonment, and much more.

Efficiency, the ultimate measure of success during the Industrial Age, has given way to adaptability, now the most important driver of success in the Information Age. This is what mParticle was purpose-built to do–solve for data quality, governance, and connectivity to make sure teams can not only adapt to data chaos but become stronger as a result.

The post What is Data Chaos? And How to Solve it to Improve Your Mobile Data Strategy appeared first on Airship.

The infographic below shares highlights of this latest data study. Of particular interest: average direct open rates from notifications are now higher in Europe than anywhere else in the world. 

Download the report with data specific to Europe here — and get in touch anytime if you’d like to discuss the report with one of our experts.

The post [Infographic] How the Pandemic Is Influencing Mobile User Engagement in Europe appeared first on Airship.

Those stats come from a recent Gartner report, “Chief Marketing Officers: Lead and Champion a Test-and-Learn Culture to Reach Your Marketing Goals.” And we not only agree with these findings, but we’ve also seen in our own customer base that those who are running regular experiments are growing about four times faster than those who are running one-off or occasional experiments. 

Bottom line: experimentation accelerates growth. 

But what will really make testing the powerful secret weapon it should be for your brand is when it’s baked into your culture. So how can you bake experimentation into everything you do — and reap the growth rewards it brings? 

Here it is in three steps:

The chart above outlines the different stages of building a culture of experimentation so you can have a sense of where you want to go. Unless you’re already at Level 3 (if it makes you feel better, most organizations aren’t), you’ve got a lot of opportunity in front of you. 

Step 1: 

The first step is to get an experimentation solution that makes testing simple and easy integrated into your martech stack. We’ve got you covered there. (Not to toot our own horn, but Apptimize is the most-installed mobile SDK in the world for A/B testing, with over 300 Million MAUs and counting.) Whether you’re testing new features (and keeping messaging to different test groups perfectly synched) or UX flows, our solution is easy to install, easy to use and easy to manage. 

Step 2: 

Start getting buy-in from the stakeholders that will need to participate in making the shift to a culture of experimentation. That means setting up meetings or coffee breaks with folks to:

• Share the stats from the beginning of this post about the benefits of a test-and-learn culture. 
• Talk about how much time, money and effort it will save when you can get to the best and most effective solution more quickly by iterating and testing.
• Run some tests and share your wins — and the bottom-line results they can drive. 
• Quantify a few high-priority goals or opportunities for your organization that testing can help with. For example: “What if we could reduce abandoned carts in the app by 2% by optimizing our check-out process through testing?”

Step 3: 

Once you’ve got some key stakeholders bought in, and have shared some of the results testing can help you achieve, consider centralizing test results so more and more people in your organization can see and appreciate the significant rewards of testing — and get ideas of their own. 

That’s it! You’re on your way. Before you know it, you’ll be at Level 3 on the maturity scale, with A/B testing integrated into your development cycles, and running tests that build on each other and become more and more powerful over time. 

The ultimate goal, of course, is to make users experience with your brand better, faster and more delightful to increase your effectiveness in every stage of the customer journey from acquisition to retention.

Whether you’re still shooting from the hip or ironing out the kinks in your process, we’ve helped companies at every stage move towards the true growth culture.

LEt’s get You Started

Contact us for a personalized demo and let us show you how we can help you move toward 4x growth today. 

The post How a Culture of Experimentation Can Lead to 4X Growth appeared first on Airship.

A culture of experimentation has many benefits — one of them is helping you meet your revenue goals. A/B testing is a great way to practically experiment with your data to determine what works – and what doesn’t. Whether it is finding the winning message copy, the most engaging images or best action-inciting rewards, you’ll be able to make smart, impactful decisions that will increase the ROI from your engagement channels. 

Here are three ways you can use A/B testing to boost customer engagement goals. 

Capture Omnichannel Sales 

As the customer journey grows increasingly omnichannel, brands need to optimize and personalize their digital experiences to capture sales. 

For example, If a customer is browsing products, you can split test the product images or descriptions both online and on mobile to see which leads to more conversions. 

Let’s say a customer has added items to their online cart and you want to nudge them to buy now. In that case, you might consider A/B testing the mobile checkout page with a free shipping offer — or experiment with a more streamlined process to ease the checkout process.

Through A/B testing, you’ll be able to drive sales through key channels and double down on the most effective incentives or offerings.

Crank Up Customer Engagement

Since high stakes are riding on a customer’s first impression, you can turn to A/B testing to nail that first interaction. 

For example, following an app download, you may want to run experiments on the first-run experience. Should you show the user a straight-forward registration page or provide a tutorial? Should you allow users to login with their social accounts or by email? If you ask the user to select some categories in the beginning to personalize their browsing experience, would this result in higher click-through rates? These are all questions that can be answered through A/B testing.

As you witness your conversions climb, you can use more A/B tests to optimize even further. For example, you can show different first-run experiences to users coming in from your Google Adwords campaigns and those referred from a partner site.

Fine Tune Your Loyalty Program

Keeping your loyal customer base happy means more profits. A/B testing can help you make the experience of earning and redeeming points as streamlined and delightful as possible.

Test where and how to display their points online or on the mobile app to encourage engagement. If you show the number of points they’re short of to reach a reward milestone, would that boost sales among members close to that milestone? How about testing different types of rewards to see which encourage more loyalty sign-ups? For loyalty members using their mobile app to collect points, what’s the best experience for higher levels of engagement?

Want to know how Apptimize, an Airship company, can help? Contact us to learn more.

The post Three Ways A/B Testing Can Help You Meet Your Goals appeared first on Airship.

To help marketers get a clearer idea on what AI can do for them today, Airship’s Lead Data Scientist, Lisa Orr, and Strategic Account Manager, Phil West, hosted a webinar on how to use data and our machine learning solutions, Predictive Churn and Predictive Send Time Optimization. We shared best practices and strategies from top brands who are using predictive data to reduce customer churn, improve engagement by 10% or more and drive increased customer lifetime value.

Here are the highlights from the webinar “How Top Brands Use Machine Learning Data to Reduce Churn & Boost Engagement (And How You Can Too)” — to get all of our insights, watch the full replay anytime.

1) The Differences Between AI, Machine Learning and Predictive Analytics

AI, Machine Learning and Predictive Learning are often put together and sometimes mistaken for each other, but they are three different tools that can help marketers make decisions based on data. To help differentiate between the three, we used the example of how a Roomba works.

AI is a branch of computer science dealing with the simulation of intelligent behavior in computers; the capability of a machine to imitate intelligent human behavior. A Roomba can appear intelligent, as if it’s making its own decisions wandering around, cleaning the dirt on your floor, but it’s actually following a set of rules (like turning after hitting a wall).

Machine Learning is a branch of artificial intelligence in which a computer generates rules based on raw data that has been fed into it, or put simply: a machine that learns from data. For a Roomba, beyond a simple set of rules (like turning after hitting a wall), the vacuum robot could be mapping the space, figuring out where it’s been so it doesn’t revisit the same places again.

Predictive Analytics is a variety of statistical techniques that analyze current and historical facts to make predictions about the future or otherwise unknown events and allow assessment of risk or potential associated with a particular set of conditions. This is a catchall phrase that ultimately means there is some smart data processing going on under the hood (like with the Roomba) providing marketers with a tool for making data-driven decisions fast.  

2) Segment Audiences Based on Churn Risk to Boost Results

Airship built a powerful machine learning model that uses app data to predict churn, and simplifies the concept into three groups: High, Medium, and Low. Here’s our advice on how to approach each risk group:

High Risk: You’ve spent the money to acquire and engage, but now they’re at risk: how do you bring them back? Don’t be afraid to engage with them on a different channel. Everyone likes a deal, so sending a deal or offer to high-risk users to bring them back works well with email, but it also delivers results with the app. One Airship customer set up an automation pipeline for their high-risk group and that worked so well, it became a top-three revenue driver.

Medium Risk: Keep these users educated and engaged. Using educational or inspirational messages can remind them why they downloaded the app in the first place. You can also highlight features that low-churn users are using, to drive that same behavior with them. This is a strategy that also works with High-Risk users.

Low Risk: These are your really active folks and your best users, so how do you reward them or drive additional value? Since they are super active with the app, they are a great group to test different messages. You can try an additional push and see if they opt-out or delete the app with that extra message, but more often than not, the additional push actually helps the users engage with the app, not push them away.

3) Segment Your Audience to Send Test Notifications

No one wants to spam their customer, but you also want to make sure that you’re sending the right amount of notifications to get the best engagement. Segmenting your audience by risk can also separate the right audience to test those additional pushes.

A good test is to target low-risk, and possibly medium-risk, with an additional push, and see how the messages engage with that audience. What we see is that the additional push increases engagement, rather than push customers away into opting-out. One of our clients targeted a low-risk audience for an additional message every week and it became their best performing engagement.

It’s also important to think about consistency, rather than simply frequency. Another customer noticed a dramatic fall in their app opens and they weren’t sure why, until they realized they forgot to send their one weekly push. It can be easy to take notifications for granted!

4) The Best Time to Send a Notification May Surprise You

When is the best time to send a notification? It depends not only on the brand, but also by user. Sending a message during a time an individual is most likely to engage has a positive impact on direct open rates, and that window of time may be outside daytime hours. For one brand, Airship’s Send Time Optimization data showed that the highest engagement hours were actually the late night hours, with high activity happening even between 1 a.m. and 4 a.m.

Another example is a high-end retailer whose data showed a huge spike at night with opens, between 10 p.m. and midnight. Thinking about what kind of customers were using the app at that time (perhaps opening the app at the end of a long work day) they decided to try out inspirational messages, with the option of sending it out to everyone or targetting just those using the app that that time.

What works for some, may not work for all. Lisa worked with a data analyst that had a global audience to take into consideration. Before Send Time Optimization, he had to do a lot of research and make a lot of guesses, thinking about the different geographical regions and activity patterns of his customers. The Optimization button took away all that decision making, instead using data to send messages at the best times for the specific groups of customers. It worked so well, he sent a thank you note to the Airship team!

Is your brand using machine learning to reduce churn and boost engagement? For more insight and use cases, watch the webinar here and make sure to subscribe to our blog newsletter to get the best of Airship straight to your inbox.

Are you making smart data moves? Airship can help you develop strategies around Predictive Data that maximize your audience potential and engagement. Connect with us today and let’s talk!

The post How to Use Machine Learning Data to Reduce Churn & Boost Engagement – Webinar Recap appeared first on Airship.

The emergence of Open Banking and the opening up of APIs to third-party providers is paving the way for innovation and collaboration to challenge traditional processes — according to research from CACI, mobile banking transactions will more than double over the next four years. While the rise of Open Banking represents a huge opportunity to banks and Payment Service Providers (PSPs), it also poses challenges. It’s easier than ever to change banking providers, and opening APIs to third parties means areas which have traditionally been dominated by banks are now far more competitive. Accountancy firm PwC has predicted Open Banking sector could be worth £2.8bn by the end of the year, and £7.2bn by 2022.

Customers now have enhanced digital services thanks to Open Banking, giving them choice and flexibility in the ways they manage their money. We’ve already far greater seen the growth of digital channels encourage dramatic shifts in other industries, like retail, in which the high-street is struggling to fend off the convenience of online shopping. These expectations have permeated into the banking sector. In fact, according to Forrester research, “Thirty-four percent of European online adults now use a smartphone app and/or their bank’s mobile website for banking activities at least monthly.” (The State Of Digital Banking, 2018, Forrester Research, Inc., February 7, 2018) – a number expected to rise as bank branches continue to close across the UK.

Further to that, 64% of adults are expected to adopt Open Banking in the next four years, creating another channel for banking and financial services to connect with their audience, while providing the opportunity for the sector to integrate new third-party services, allowing banks to innovate even faster. This offers a competitive edge and enables financial institutions to launch apps and other innovative services in order to create ‘wow’ moments for customers, improving the overall open banking experience.

The Potential of Connected Money

Leading global banks including Lloyds, RBS, HSBC and NatWest have already made inroads into Open Banking. For example, HSBC released an app in May, Connected Money, which allows customers to see a single view of all their UK current and savings accounts, mortgages, loans, and cards held across 21 banks – including Santander, Lloyds, and Barclays – all in one app. The result of a $2 billion investment in technology, the app provides consumers with a better understanding of their money and also creates scope to attract customers from other providers. The potential of Connected Money is further amplified as the app uses Open Banking APIs for a feature that actively makes suggestions about where consumers can cut day-to-day costs, saving users money and enhancing their customer experience.

Connected Money not only enables HSBC to provide an enhanced and more convenient user experience, but it also better positions the bank to take on emerging fintechs and challenger banks, including Monzo, which saw its user base grow by 300% to 450,000 in just nine months last year due to its appeal amongst tech-savvy millennials and its focus on customer experience.

Adding Value with Personalised Marketing

When using a retailer’s app, users may be window shopping. But when it comes to finances, users are often more task-focused and tend to be looking for specific information, meaning they’re highly engaged.

By adding value through timely and relevant messages, financial institutions can use their apps as another method of communication for customers. For example, using location-targeting, financial institutions can determine their user does a lot of travelling and that they might be interested to see a bank or provider’s exchange rates or travel insurance offers. Timely and personalised in-app notifications and messaging around relevant content can delight the customer by adding real-time value and result in additional services being used, making an impact on the bottom line. Likewise, fraudulent activity can be identified using both physical and digital data points, and customers can be immediately notified through all opted-in channels (SMS, email, push notification, in-app message).

Why Data Is Your Friend

By 2020, mobile interactions will outnumber interactions by all other channels 10 to 1. In fact, according to a recent survey, marketing executives’ number one challenge today is understanding these behaviours and reaching people in the right moment. Financial institutions should be making the most of real-time data to orchestrate marketing messages that relevantly and helpfully serve customers in their exact moments of need, and on every level.

There are typically big milestones in a banking customer’s journey – starting a family, buying a first home, taking out a loan to start a business – and banks are becoming more aware of customers’ situations and introducing innovations to help them prepare. For instance, Cleo, which is described as an “AI friend” monitors customers’ spending habits and alerts them when a particular purchase is likely to take them over their monthly budgets. The AI-driven chatbot interacts with customers, without unnecessary jargon, giving them helpful advice on managing their money.

Open Banking represents a great opportunity for banks and fintech companies to enhance their app or service, by providing customers with improved functionality to assist their financial management. Further to that, on a more personal level, it can help customers to set targets and achieve life goals; giving the financial services industry the chance to exceed consumer’s expectations.

We love data too. Our data and analytics solutions mean you can use the customer data you have to deliver better messaging and services, which drive deeper engagement and a better customer experience. Come chat with us. 

The post App Engagement in the Open Banking Era appeared first on Airship.

Artificial Intelligence. Machine Learning. Predictive Data. These are all hot button words, but do you know what the differences are — and how you could be using them to improve your bottom line?

If you don’t, no worries. Join us for our webinar, “How Top Brands Use Machine Learning Data to Reduce Churn and Boost Engagement (And How You Can Too)” where our experts, Lisa Orr and Phil West, will explain the differences between AI, Machine Learning, Predictive Analytics and also show step-by-step how to use data and Urban Airship’s machine learning solutions.

Join the Webinar and You Will Learn How to:

• Protect your acquisition spend by identifying and re-engaging users who have the highest risk of churn

• Build a smarter messaging strategy by combining churn risk data with other customer data (like loyalty status or purchase history)

• Improve engagement rates by sending at the times individuals are most active

We’ll also share best practices and strategies from top brands who are using predictive data to reduce customer churn, improve engagement by 10% or more, and drive increased customer lifetime value.

Get Knowledge You Can Actually Use

Predictive analytics, paired with mobile marketing automation, increases our ability to have the right conversation at the right time with the right person in the right way. However, as you may have noticed, there’s a lot of hype around using AI in marketing. Never fear, this webinar is not about that. This webinar is about understanding what AI and data can do for your brand today.

Sign Up Today!

Don’t miss out – reserve your spot today!

Have questions? We got answers.

The post How to Use Machine Learning Data to Reduce Churn and Boost Engagement appeared first on Airship.

Figuring out when to send notifications is a tricky problem. Personalizing the experience to each user is challenging — let alone sending individually-timed messages across an entire audience base.

We solved both problems with our Predictive Send Time Optimization Solution. The model decides the best time based on individual engagement patterns — and provides an easy way to send to each user’s best time in a single step.

The (Mostly Manual) Ways Brands Have Been Trying To Predict Best Time To Send

While building this model we polled customers about their general engagement strategies to determine how they decide the best time to message their users.

Some marketers send notifications the moment they are finished composing them, regardless of user timezone.

Others use their intuition to identify the best time to send a campaign: a marketer of a dating app scheduled messages at 6pm local time as it represents the window when people get home from work and start thinking about their potential dates for the night.

On the more data-driven side, we learned that a telecom company selected best time for each individual based on a few rules: send at the hour in which they last saw an open from a user, unless that time was outside day hours; then send to an early morning hour the following day.

Our conversations revealed that marketers want to be more data-driven with their send time decisions, but are still relying mostly on intuition and convenience.

Machine Learning To The Rescue

We created a model that:

• Selects optimal engagement time personalized to each individual user

• Is localized to each user’s timezone

• Is extensible to dormant users, and

• Is both actionable when building campaigns and explorable in our data products

Our models are based on a user’s recent engagement history.

To start, app opens are localized to the user’s timezone and aggregated to the hour over the last 60 days of app activity. Best hour is determined by striking a balance between the user’s engagement patterns and a generalized model of engagement patterns across an app’s total audience.

The model includes a preference for daytime hours to avoid assigning late night best times to users who may infrequently engage with apps late at night. (However, if a user truly spends most of their time engaging at night then their personalized best time will fall into night time hours.)

Our model also creates a generalized “best hour to send” recommendation, which brands can use as a rule for sending messages to dormant or low-activity users. The general best hour aggregates opens across app users and selects the best hour based on the most frequent opening time for each app and app operating system.

Testing & Results

To test the model we compared predicted best times to true open times for open events that occured after model generation. We compared the best time model to both a baseline model (e.g. everyone’s best hour is set to 12pm) and to the general best hour (e.g. everyone’s best hour is set to the general model best hour).

We found that personalized best time more accurately predicts the hour a user opens than either the general model or the baseline model. It performed better than both the generalized best time (52% higher match rate on average) and the baseline model (100% higher match rate on average).

“We found that personalized best time…performed better than both the generalized best time (52% higher match rate on average) and the baseline model.”

Making It Easy To Put the Model To Work for You

We want to make deriving insights and taking action with the Predictive Send Time Optimization model simple for the marketer and their analytics teams:  

• As with our Predictive Churn model, we ship weekly predictions as user tags to facilitate integration between predictive model output and our data solutions.

• We make it easy to schedule messages with Predictive Send Time Optimization

• We offer simple ways to visualize the user-level predictions

• Analytics teams can ingest predictive tags into their own systems with real-time data streaming.

• Through our customer analytics solution Insight we provide a deeper dive into the model, surfacing the cross-audience best hour as it relates to each day of the week and for each app operating system.

Since launch we’ve seen major retailers, a major research firm and an international media company adopt optimized notifications into their daily workflow. We’ve seen higher direct open rates with optimized sends and have heard positive feedback on how the tool is saving teams time and effort. One of our customers is even using Predictive Send Time Optimization to meter traffic into their app.

We are excited to hear about the success of the model in the wild and look forward to building more predictive tools that fit our customers’ needs.

Ready to get started with Predictive Send Time Optimization? Let us show you how it can work for you in a personalized demo! Contact us today!

The post How We Built Our Machine Learning Model for Predictive Send Time Optimization appeared first on Airship.