Image generated using Midjourney: https://www.midjourney.com/

Using ChatGPT to predict the Oscars

How to use ChatGPT to build a model to predict who will win Best Picture at the 2023 Academy Awards

I used ChatGPT to build a model to predict the winner of the Best Picture category at the 2023 Academy Awards. Over the past couple of weeks, I have worked on this project with ChatGPT. I will share the code we generated, the decision-making process behind it, and the final results.

The purpose of this article is threefold:

1. Assess the strengths and weaknesses of working with ChatGPT on a data science project.
2. Provide a tutorial for others to follow who are interested in exploring and modeling Oscar nominees.
3. Generate some insights and takeaways from the data and model itself.

Notes: If you are using this for purpose 2, see the notebook on my GitHub for the complete code. Also, some of these chunks of code can take a long time to run.

First, here are my thoughts on the benefits and areas for improvement for ChatGPT, based on my experience on this project.

Strengths:

• ChatGPT is an amazing tool that speeds up analysis and problem-solving. I would not have been able to do this work as quickly without ChatGPT.