Mobile app business models are often built around advertising and cross-promotions. Yet with so many moving parts—frontend/backend, advertising platforms, partners, and more—there are many opportunities for something to break. Like a butterfly wing creating a distant storm, if one element is working less than optimally, it can cause problems elsewhere.
Many companies use dashboards and alerts to track what is happening with the apps they developed. For example, important KPIs to track could include number of user installations, revenue, ad conversion, and cross-promotion success rate. Each of these KPIs has its own typical pattern. (For example, installations may drop during evening hours and rise again during daytime hours or drop overall throughout the weekend.) The typical pattern may also have a trend associated with it, as ideally app usage is growing over time.
And yet, each KPI can be broken down much further into more granular metrics. For a single KPI—installations for instance—we can further analyze it for each geographic region, for each type of device (e.g., iOS or Android), for each device version (Android Jelly Bean, Lollypop, Nougat, etc.), and more. The more granularity the better since it allows you to find the root cause more quickly if something goes wrong or quickly leverage something that is working well. However, if you consider every possible KPI multiplied by every possible permutation, you quickly arrive at a massive number of metrics to track. Is it better to track “installs” or “installs on Android in California”? Add to that the fact that you probably want to measure these at a minimum every minute, and you soon find yourself overwhelmed with dashboards and alerts.
This is where anomaly detection comes into play. Using machine learning, you can learn the normal behavior of each metric or even combinations of metrics (e.g., revenue per install) and identify in real time if a metric behaves abnormally. Ira Cohen outlines ways to use anomaly detection to monitor all areas of an app, from the code to the user behavior to partner integrations and more, to fully optimize your mobile app.
Ira Cohen is a cofounder of Anodot and its chief data scientist, where he is responsible for developing and inventing its real-time multivariate anomaly detection algorithms that work with millions of time series signals. He holds a PhD in machine learning from the University of Illinois at Urbana-Champaign and has over 12 years of industry experience.
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org
Apache Hadoop, Hadoop, Apache Spark, Spark, and Apache are either registered trademarks or trademarks of the Apache Software Foundation in the United States and/or other countries, and are used with permission. The Apache Software Foundation has no affiliation with and does not endorse, or review the materials provided at this event, which is managed by O'Reilly Media and/or Cloudera.