The 96th Academy Awards are officially in the books and the ceremonies went without a hitch for the second year in a row. There were several memorable moments like Billie Eilish and brother Finneas performing the Oscar winning Original Song and the butt-naked award presentation for Best Costume. But in the end it was Ryan Gosling that stole the show with his singing performance that left the audience in awe. So critics think the Oscars are back from their post-pandemic malaise.
With seven Oscars out of thirteen nominations, the big winner was Oppenheimer as predicted. Director Christopher Nolan finally broke his bad luck and was handed his first Oscar in his seventh nominations. Emma Stone won her second Oscar in her young and still thriving career edging out co-favorite Lily Gladstone. That was one of four wins for the movie Poor Things, which was second best only to Oppenheimer.
Prediction Results and Analysis
In this year’s edition, we got six of the eight major categories right. Our models nailed the six categories we have been predicting every year since the inception of our fun and educational project in 2018. On the other hand, the historically challenging screenplay categories played spoiler again as our #2 picks ended up with the Oscar in both Original and Adapted Screenplay. In the craft/technical categories, we had a decent hit rate of seven out of eleven this year. The consolation was that three of the four Oscars we missed in that group also went to our #2 picks. In conclusion, we predicted 13 out of 19 award winners for a 68% overall hit rate.
Poor Things was the movie that performed better than our models gave it credit for as it walked away with four statues vs. the two that we gave it in our predictions. Despite some misses in less prominent categories, our models did impressively since getting 13 out of 19 predictions right with anywhere between 5 to 10 nominees for each category is equivalent to finding the one correct combination out of 2,441,406,250 possible combinations. The tables below summarize the prediction outcomes per category.
As we shared in our predictions post, this year we augmented our dataset with historical betting odds data for the six major categories: Best Picture, Director, Actress, Actor, Supporting Actress, and Supporting Actor. Our Fusions made use of the odds data considerably for Supporting Actress, Director, Actor, and Supporting Actor — not as much for Best Picture or Supporting Actress. Given the fact that we got all those right gives us confidence to keep tracking odds data in the future wherever possible.
Of course, we always welcome our users to come up with creative ideas of their own including adding new data points to further enrich our public dataset. This is consistent with BigML’s long-term commitment to making Machine Learning accessible to everyone thanks to transparent white-box modeling and workflows built on top of our proven algorithms.
History to Date Predictions Performance
We’ve also updated the cumulative table below that compiles all our predictions between the 2018 and 2024 Oscars and the corresponding hit rates for the major categories. In addition to the Top Picks that we annually shared in our past blogs, this table lists how the accuracy metric improves if we also consider the movies that received the highest two (Top 2) or three (Top 3) scores. The Top Picks alone had an average 70% hit rate, whereas the coverage reaches 94% with the Top 3 taken into account.
As the pioneers of ML-as-a-Service here at BigML, we invite many more of you to put your Machine Learning skills to the test quickly with this very approachable skills practice use case and do so without the overhead of having to download and install many open-source packages worrying about compatibility issues or hard-to-decipher error messages. It takes just 1 minute to create a FREE account and about as much time to clone the movies dataset to your account. As always, let us know how your results turn out at feedback@bigml.com!