How data is driving Innovation in Media

The advance of data driven technology and artificial intelligence is radically transforming the Media and broadcast industry.

Devoncroft presented some initial data on investment trends in broadcast technology, where AI and machine learning occupy the seventh place in the list of the most important trends.

In this article, we’re going to examine some challenges and solutions showing how data science and artificial intelligence are innovating the Media sector.

 

Data Driven Consumer Analysis

woman in a theatre

Consumer analysis can be made in different way: aggregating social media data, tracking sites with cookies, tracking transactions on e-commerce sites.

A new path in analyzing customers is through emotion detection algorithms, that are becoming better and better, and some companies are using them to measure customer reactions on new products.A developing field is emotion detection cameras, that with the help of Machine Learning analyses images detecting emotions.

Case study – Disney

Disney Research has developed a neural network that has been trained to watch an audience of theatergoers as they watch a film. It can track reactions like smiling and laughter on hundreds of faces in a dark theater, allowing Disney to quantify whether or not a film is working as intended on a granular scale. Disney’s researchers tested the system across 150 showings of several films like The Jungle Bookand Star Wars: The Force Awakensin movie theaters. Emotion cameras also create a more accurate picture of audience response.

AI-powered tech creates real-time and reliable data, allowing Disney greater insight into what provokes (the desired) emotion.

 

Recommender systems

Portrait of a funny raccoon with electric guitar, showing a rock gesture

A recommender (or recommendation) system is an information filtering system that seeks to predict the rating or preference a user would give to an item. Over the past years, recommendation engines have become quietly ubiquitous. Companies like Amazon or Netflix leverage recommender systems to help users discover new relevant products or videos creating a better user experience while driving incremental revenue. Music recommender systems have experienced a boom in recent years, thanks to the success of online streaming services.

Case Study – Pandora

Pandora creators have developed a particular Recommender system, based on a strong classification of pieces of music. Every time a new song comes out, someone on Pandora’s staff — a specially trained musician or musicologist — goes through a list of more that 450 possible attributes and assigns the song a numerical rating for each one. This is what they call “Music Genome Project”.

Given the vector of one or more songs, a list of other similar songs is constructed using what the company calls its “matching algorithm”.

 

Tv Rating Prediction

Vintage Television on wood table on gray background

Rating projections are challenging: they require a steady inflow of rich, granular, reliable data, and the ability to adapt and incorporate new data to account for the latest changes in viewing behavior. Viewers are increasingly consuming media on different devices and through different channels. Their viewing is also increasingly likely to be time-shifted to work conveniently around their own schedule. These changes are making predictions more difficult. More difficult, but also more crucial to the evolving TV ecosystem.

Case Study – Nielsen

Nielsen found a strategy to innovate and improve the practice of ratings projections.

When looking into the granular results for each network,  some indications show that the Machine Learning model created by Nielsen and the network’s projections might be combined to complement each other. A model consisting of 90% ML projection and 10% network’s projection outperformed each model individually in the two quarters tested.

The human element will always play a key role in the interpretation, so we might as well include that human element in the modeling process. The media landscape is changing fast, and those who are able to merge algorithms and intuition will be best positioned to anticipate the coming trends and capitalize on the opportunities.

 

How we work is changing! In a digital world we connect together to find global solutions for transformation. Through Mathesia you can drive change and collaborate to develop new opportunities and deliver innovative solutions to make a better world.

There are brilliant minds that can help you innovate and evolve by providing technical solutions. With Mathesia you have an online platform to develop your organisation through data driven innovation. Access the Mathesia network of world-leading experts in Data Science & Mathematics to design partnerships with specialists in data driven solutions, who can help you build value for your customers and stakeholders.