IBM Launches Watson App for iOS

IBM recently launched a new application for its smart Watson platform, called IBM Watson Trend, to help customers find out which products are in trend. The app predicts the hottest shopping trends for the upcoming holiday season and outlines the reason behind these top trends.

Currently, the app is only on the iOS store and on desktop computers. Using APIs from IBM’s Watson developer platform, the app analyzes keywords and sentiments, including abilities such as concept tagging and taxonomy classification to sift through the enormous amount of data accumulated in its servers. IBM promised to make the app more advanced by adding geographical and linguistic data to the analysis. We are not sure why it is not launched on the Android platform yet.

The app provides insight behind the top holiday trends and products to uncover patterns and determine why people are choosing certain brands and products associated with them. The Watson app employs machine learning and natural language processing to go through more than 10,000 sources of unorganized information across a variety of social media channels, blogs, media websites, forums, comments, reviews and ratings. Sentiment analysis is an important aspect as it uses language to determine whether the mention of the product is beneficial or degrading to the trend score, as compared to traditional keyword frequency analysis.

"We envision families kicking back on the couch after Thanksgiving and using it to target their holiday shopping," said Jason Norwood, one of the inventors of the application, "The idea behind this app came from an internal innovation session. We started dreaming about a scenario where individuals like us get some purchase advice from social media. What if we could harness all of those conversations, literally tens of millions of them, and use the power of Watson to understand those conversations, the meaning and tone, and serve those insights to shoppers at the holiday season?"

There are three distinct trend groups – content, context and sentiment. Each group is assigned a Trend Score on the scale of 0 to 100 based on the size and rate of growth of a particular piece of information. Users can find out the top 100 trending products and the reason for their popularity across three categories as of now: consumer electronics, toys, and health & fitness.

IBM introduced the Watson developer platform to researchers in August of 2014. Later announcing Watson HQ in Manhattan, Watson was finally added to the company’s cloud service, Bluemix. The original Watson system had 1 natural language based API, however, today it over 30 different APIs across 50 different technologies ranging from speech, vision and data analysis.

IBM hopes that consumers will turn to their mobile phones instead of desktops in order to determine holiday trends, meanwhile demonstrating to companies how the Watson platform can be used in a variety of different industries. They predict mobile traffic to increase by 57%, while sales to increase by more than 36%.