We’ve spent the past few weeks discussing predictive analytics in much detail. We started with an overview of predictive analytics, then took a tour of various companies doing outstanding work in predictive analytics today, and finally reviewed the awesome dashboards of Recorded Future and Sift Science. In this final post, we look at some common, yet relatively unnoticed applications of predictive analytics in our daily life.
Table of Contents
1. Google Suggest
Google has made searching online easy and part of our lives. One killer feature of Google search is Suggest. It leverages predictive analytics to give out search query recommendations in real-time. This feature was the work of Kevin Gibbs, who started out trying to build a URL predictor that auto-completes the URL as a user types it in. This idea was then ported over to Google search itself, driving a lot of adoption, and saving users a lot of time while searching. Gibbs comments that ‘It took hundreds of machines to store everything that it might return to you.’
2. Amazon Product Recommendations
We’ve all gotten lost in product research on Amazon.com, jumping from one product to another, comparing one list with another, in a seemingly endless maze of products. This addictive shopping experience is due to the smart work of Amazon in the background where they’ve perfected the art of cross-selling. Amazon’s recommendations are made in many contexts such as the item page, checkout page, search results page, an extremely customized home page, and even via email promotions. These recommendations are based on aggregate data for tons of transactions, and user behavior. If you’re interested in the nuts and bolts of how this works, here’s a patent filed by Amazon for their product recommendation feature.
3. Facebook’s News Feed
In the early days of Facebook, the newsfeed used to have all updates from your friends in chronological order. In recent times, have you noticed that Facebook increasingly prioritizes updates from your close friends and family more than others? This is its predictive analytics alrogithms at play, guessing which stories you’d be most interested in based on who you speak with most frequently, and your profile information. If you’re interested in knowing all the factors that influence your News Feed, do check out this detailed post from Marketing Land.
4. Video Games like Battlefield
Gaming companies like EA and Zynga generate a lot of structured and unstructured data from their games. EA games generate a whopping 50TB of data per day. This data is in the form of gameplay data, micro-transactions, time stamps, in-game advertising, multi-player information, and much more. These companies see the huge opportunity to customize gameplay, find new ways of monetizing games, and even enriching the gaming experience by making it social. In the interesting talk below, EA’s Rajat Taneja talks about the change in mindset that they had to make to make the shift from traditional data warehousing to adopting the big data mindset.
5. FICO Credit Score
This is perhaps the most well-known application of predictive analytics. FICO score is used to assess the creditworthiness of a person, and the level of risk a finance company incurs when lending to that person. It uses factors such as on-time payments, credit capacity used, and duration of credit history to assign each person a score. This process of assessing risk when lending used to take banks weeks before, but now can be done in just a few hours, thanks to the FICO score. Unfortunately, as with all predictive models, accuracy is a concern, and even an established model like the FICO score can go badly wrong as in the sub-prime mortgage crisis of 2008.
6. Email Spam Filtering
Spam filtering is another widely used application of predictive analytics. When Gmail launched back in 2004 it was lauded for its exceptionally better spam filtering than the then popular Yahoo Mail. Spam is a major concern for email users. When dealing with spam, email service providers need to not only filter out spam email, but ensure the spam filters don’t catch false positives. According to Mashable, in the year 2012, 78% of all email sent are spam. You can imagine the difference those efficient spam filters make in the way we consume email every day.
7. USPS Zip Code Recognition
We don’t often use snail mail these days, but the digit recognition system used by the US post office is an example of predictive analytics. The postal service needs to recognize the numbers in a zip code, and sort its mail by zip code. It uses algorithms that have been trained to recognize hand-written digits. It has a large set of pictures that are labeled by hand as being in 0 to 9, and uses them to accurately identify zip code numbers on mail.
8. Behavioral Advertising
Advertising platforms are ever in the search of a better way to target ads to their user base. Be it Google with AdWords, Facebook with their ads within the News Feed, or advertising startups like UberAds. In this video, Scott Howe of Acxiom Corp, a media company, talks about how behavioral advertising is in its infancy, and is set to mature a lot in future.
9. Election Campaigns
While many of the above examples show predictive analytics geared towards predicting a single score, or making an ‘either/or’ decision, when it comes to an election campaign, political parties need to predict something as complex as what impact a particular messaging would have on a particular demographic group. Election campaign planners have long recognized the role of social media in deciding the outcome of an election. The next step is to leverage data in making more accurate predictions on the impact of their messaging. In the video below, Eric Seigel, an expert in predictive analytics, talks about how the Obama campaign used uplift modeling to predict which kind of message would sway a voter in the right direction
With that we come to the end of this 6 part series on predictive analytics. I hope you’ve enjoyed reading each of the posts, and are now more aware of the unique possibilities predictive analytics opens up to us as we enter a new world of data.
If you missed any of the previous parts in this series, here they are: