An Easier Way to Run Spark Jobs on AWS EMR

spark-logo-trademark At JW Player, we use Spark to explore new data features and run reports that help drive product decisions and improve algorithms. But doing data analysis at the terabyte level is time consuming, especially when having to manually set up AWS Elastic Mapreduce (EMR) clusters. Our code often depends on custom libraries or Spark settings that require bootstrapping. Moreover, iterating on changes is cumbersome and adds extra steps to our workflow.

JW Platform’s Data-Driven Recommendations & Feeds

Franklin Dement, Product Manager for JW Platform’s Data-Driven Recommendations, explains new features as well as best practices for implementation.

Why use Data-Driven Recommendations?

Launched in November 2015 to a select group of publishers, JW Platform Data-Driven Recommendations:
  • Increase content plays and monetization opportunities where ads are present.
  • Use existing content connections and viewer activity to simplify your publishing workflow and increase revenue.
  • Provide your viewers with automatically-curated video suggestions that increase audience engagement and are continually updating based on interaction data and content traits.

JW Player In-Player Overlay — Available in Nov 2015 Release


Grow Your Audience With Our New JW Player Real-Time Analytics

In the new JW Player Analytics Dashboard, we’ve changed the way we analyze data in an effort to empower you with the information you need to grow.

FEATURE SPOTLIGHT:  Your New ‘Right Now’ view

In the fast-paced (and short-attention-span!) publishing world, we know that you are always searching for a quick and easy way to check what’s going on “right now” with your content campaigns. How many times have you realized a video was trending after the moment passed and your audience moved on? Static dashboard tools with stale data can’t solve for this use-case. REALtime new

Hive with Tez on EMR

Screen Shot 2015-12-11 at 3.51.19 PM Over half a billion videos are watched on JW Player video player every day resulting in about 7 billion events a day which generates approximately 1.5 to 2 terabytes of compressed data every day. We, in the data team here at JW Player, have built various batch and real time pipelines to crunch this data in order to provide analytics to our customers. For more details about our infrastructure, you can look at JW at Scale and Fast String Matching. In this post, I am going to discuss how we got Hive with Tez running in our batch processing pipelines.

Fast String Matching for Analytics Quality at JW Player

At JW Player our analytics pipeline currently receives 4M pings per minute at peak times, providing the basis for insights to the publishers on our dashboards. Recently we have moved some of our offline classification processes to the beginning of our real-time and batch pipelines, which required us to optimize our string matching implementations. We employed finite state automata, rolling hash functions, and bloom filters to achieve 6x and 3x speedup in NSFW classification and ad classification respectively. In this article, we will discuss these classification problems, then the algorithms, implementations, as well as evaluation of our solutions.Classification_omni

JW at Scale: Or How I Learned to Stop Worrying and Love Skew

JW Player introduced analytics as a major feature with JW6 in 2012. This allowed us to offer publishers insights into who was watching their content, including device, geo and video data. Adoption of JW6 exploded over the next 3 years, challenging us to keep up with the rapidly increasing data coming in each day. This article looks to explore a particular challenge we’ve faced in scaling our periodic batch pipeline for publisher analytics: key skew in Hadoop.

Analyze this! – How to use JW Player’s API with Google Analytics

JW Player and Google Analytics

In this age of information, analytics are king. Content providers like to know how their products are being used and when people are using specific features. It comes as no surprise that many providers want to know how their videos are being watched so they can improve the viewing experience. Surely, knowing your audience and their viewing habits are a sure fire way to keep everybody happy.

Introducing Our Newest Online Video Player Update – JW Player 6

Today, we are proud to announce the public release of JW Player 6! JW6 is JW Player’s biggest update yet, containing tons of new or enhanced functionality. This blog post highlights the most important ones, including a redesigned interface, move to HTML5 first and support for Apple's HTTP Live Streaming in Flash.

Mobile platforms for video: understanding where and when

Here at LongTail, we have a unique opportunity to observe and understand how video is being watched over the Internet. Our popular video player (JW Player) and video hosting platform (Bits on the Run) provide us with insight on video and device viewing habits. With the increasing popularity of tablets, we decided to have a closer look at just how this new class of devices account for video consumption across the Internet.

Understanding Video Analytics

Online video is slowing becoming ubiquitous - used more and more by publishers to promote their products and services to their customers. So how do you measure just how ubiquitous it has become? Our Answer: Video Analytics.

It is becoming increasingly important to analyze video performance. For example, retailers want to know if their video marketing efforts increase sales. Publishers want to know which type of videos (and accompanying advertisements) have the greatest return on investment. Foundations want to know if their video bulletins are successfully increasing awareness of their mission. Analytics are both intriguing and insightful across many industries.