The Film Data Scientist returns to dig into what it means for a movie to be "dumb", and how movies are changing in this regard.

I read all 68 pages of the patent behind Ben Affleck’s stealth AI start-up that Netflix just bought in order to understand exactly how the system works (and so you don't have to).

I studied the dialogue in 64,332 movies released between 1940 and 2022. Each movie’s writing was scored using four metrics, ...

I analysed over 200,000 errors across 11,842 films released between 1930 and 2025, to understand where and how audiences say movies gets facts, physics, and history wrong.

I’ve written about the data behind Hallmark movies a few times before. So it was great fun to sit down with Pulitzer prize-winning data journalist (and good friend) Walt Hickey of NumLock to talk all ...

Last week, I shared my analysis of how filmmakers are subtly changing how they frame human faces over time. Today I wanted to take it one stage further and see if we can use those faces to measure how ...

Films evolve in many small ways that are easy to miss if you are not looking for them. One area I had not studied before is shot composition. It is such a basic building block of visual storytelling ...

Last Friday I ran another event with Jason Blum and the Blumhouse team, this time in New York. We were looking at how the horror is changing, and how we have to evolve the way we think about horror.

I have been asked for years whether “Go Woke, Go Broke” is true for movies. So it was a real honour to be able to give the keynote today at the Zurich Summit and answer the question. Over the last few ...