Cherish Negative Results, They Are a Good Thing | ML Tips #3

I remember when I first started doing research, I always felt bad and stressed whenever I generated a negative results. My thought process was that I must have messed up something along the way and that I wasn't good enough.

Cherish Negative Results, They Are a Good Thing | ML Tips #3
Photo by Libby Penner / Unsplash

I remember when I first started doing research, I always felt bad and stressed whenever I generated a negative results. My thought process was that I must have messed up something along the way and that I wasn't good enough.

The truth was that I often did, but it didn't matter. Doing a data science project is an iterative process of setting up some analysis, checking the results and figure out where it went wrong.

Rechecking your analysis piece by piece and improving it until the result you are generating is correct can take many iteration. Yet, even when you did everything right the result might just be negative and it's totally fine, You take the information, refine your analysis and go for another round πŸ˜ƒ!

Some neat way to reduce the stress of negative results and to be more confident includes the following:

  • Working in teams with a merge request / code-review cadence.
  • Isolate your code and test each bits for correctness.
  • Document your code along each of your iteration thoroughly.
  • Use a report-driven-development methodology where your write the report iteratively as you code your analysis!

Subscribe to Yacine's Machine Learning Help Desk

Don’t miss out on the latest issues. Sign up now to get access to the library of members-only issues.
jamie@example.com
Subscribe