August 2, 2013
Netflix’s use of data helps determine what its customers want to watch and how they want it presented. The company’s newest original show, “Orange Is the New Black,” is partially the result of analyzing viewer data. Netflix is using all types of collected viewer data in order to create content and to possibly shape the user experience. Viewer data is collected from multiple sources: Netflix, third party metadata and social media.
Netflix did not have to invest millions in an ad campaign for “Orange Is the New Black.” Instead, it relied on its viewers’ habits and preferences to add it to the recommendation system in order to bring it to its users’ attention.
“As more television is delivered digitally, the industry itself almost has to become more like the Web, where visitor behavior is analyzed ad nauseum and data helps inform even seemingly trivial changes in page layout or user experience,” suggests GigaOM. “Content is king, but every little thing matters when it’s coming at your users from every direction.”
The following information is tracked by Netflix, according to the company’s former senior data scientist Mohammad Sabah, as described at the Hadoop Summit in 2012:
- More than 25 million users
- About 30 million plays per day (and it tracks every time you rewind, fast forward and pause a movie)
- More than 2 billion hours of streaming video watched during the last three months of 2011 alone
- About 4 million ratings per day
- About 3 million searches per day
- Geo-location data
- Device information
- Time of day and week (it now can verify that users watch more TV shows during the week and more movies during the weekend)
- Metadata from third parties, such as Nielsen
- Social media data from Facebook and Twitter
Netflix analyzes the streaming video. The company captures JPEGs and notes the exact times when credits begin and is taking into account other factors, explains Sabah. Netflix could consider volume, colors, and scenery that may reflect what users like.
There is a concern about the reliance of using data too much as it may produce content that is too formulaic or that user data analysis may not matter. It may be possible to find a successful show by creating pilots and seeing what makes a hit.
There may be many other factors that affect a viewer. Will the overall user experience attract or turn away viewers, or will headline titles, layouts or banner ads have an effect?
Across all TV, whether Netflix, cable or broadcast, content producers will have to consider many factors in their shows. What common elements attract versus those that turn off viewers, should certain content be included or avoided, or are there elements that viewers replay or fast forward?
Are Millennials More Drawn to Netflix Than Other Services?, ETCentric, 8/2/13
TiVo Research and Analytics: Netflix Not Cannibalizing Traditional TV Viewing, Press Release, 7/29/13
Netflix Doesn’t Curb TiVo Fans’ Appetite for TV, But Likely Does for Everyone Else, Variety, 7/29/13