Root Cause Analysis using Open AI’s Code Interpreter

Root Cause Analysis using Open AI’s Code Interpreter

Root cause analysis (RCA) is changed forever. For a newsletter, wanted to understand the correlation between parameters such as subject length, emojis, numbers, dollar signs with open rates and click rates
Instead of doing it in excel or asking a data analyst to crunch the numbers, I just ran this table through Open AI’s code interpreter (advanced data analysis) on ChatGPT. And it gave me a decent correlation matching some of my intuition and breaking some others.
notion image
Intuitively: - numbers, dollar signs performed better - certain keywords that were meant to perform better, did Counter intuitively - longer subject lines performed better than shorter ones - question marks didn’t work in subject lines This no doubt saved me time so I could quickly get to the root cause and fix the issue for the new Even though I tested it out on a few newsletter editions, I still think that the correlation makes sense, but will test out with more data
If you liked this post, subscribe to my newsletter: