Monday 29 February 2016

Can we predict Oscar winners using data analytics?

In the run up to the Oscars, millions of people across the globe were intrigued about who would win what awards for which films. One of the questions people in the tech world have been asking is whether we will be able to predict future Oscar winners, based upon data analysis. Two tech firms called Cognizant and Clarabridge, are convinced that they will be able to accomplish this. Both companies looked at 150 variables, from film genre to box office takings, from review ratings to the percentage of female viewers under 18. They then applied their algorithm to data going back fifteen years to work out which of these variables were the most important. Both firms also measured the sentiment films elicited on websites such as IMDB and Rotten Tomatoes. Just to give some sense of the amount of data, the tech firms looked at 150,000 text reviews and more than 38 million star ratings from IMDB alone. 

Data crunchers are able to measure sentiment more precisely these days thanks to Big Data analytics and pattern spotting algorithms. Cognizant and Clarabridge expressed a 64% certainty that 'The Revenant' would win an award. In view of the awards given to Leonardo DiCaprio and Alejandro González Iñárritu, it would seem their prediction was bang on the mark! This certainly raises some interesting questions about Big Data analytics. Could data analytics predict Oscar winners of the future with 100% accuracy? It's certainly a possibility. But would we really want to know this in advance? Wouldn't this spoil the atmosphere of the Oscar awards ceremony? Only time will tell. One thing for sure is that Big Data is becoming ever more sophisticated at predicting competition outcomes. Whether that is a good thing or a bad thing is an open question right now.  

No comments:

Post a Comment