15 Mistakes to Avoid in Data Science

Authors

Lucas Joppa

Environmental expert on sustainability in the tech industry

Louis Tremblay

Senior System Engineer

Sam Cvetkovski

Data Analytics Leader and Consultant

Lacey Westphal

Data Scientist, Manager of Academic Data Analysis

Sara Anstey

Data Analytics Consultant

Madecraft

Full-Service Learning Content Company

Course details

As a data scientist, your goal is to always be growing your skills. But, if you realize it or not, there are errors you may be making that are keeping you from moving to the next level. In this course, learn the top 15 data science mistakes: misunderstanding business problems, using the wrong tools, starting without a plan, and much more. Four leading data scientists share the hard-won lessons they've learned about alienating colleagues with technical jargon, moving too fast, and using sample sizes that are just too small. Find out why you should make your best effort to prevent bias—and avoid overpromising solutions to stakeholders. Plus, learn why writing custom code can lead to a big waste of time and why the most promising data science insights fall flat without a compelling story.

Topics include:
Communication tips
Keeping up to date on tools and techniques
Documenting your work
Avoiding bias
Working with stakeholders

Concepts

0. Introduction

01 - Avoid common mistakes to excel in data science

1. Mistakes to Avoid

02 - Communicating with overly technical language
03 - Skipping the fundamentals
04 - Moving too quickly
05 - Having a data set that is too small
06 - Failing to adopt new tools
07 - Not considering the level of variation
08 - Lack of documentation
09 - Relying solely on formal education
10 - Taking too long to share results
11 - Including your bias
12 - Overpromising solutions to stakeholders
13 - Building tools from scratch
14 - Assuming the knowledge level of stakeholders
15 - Not telling a story with the data
16 - Not confirming with stakeholders

Conclusion

17 - Get started on the right path