Homepage
Open in app
Sign in
Get started
ACCESSIBILITY
DATA
MACHINE LEARNING
MOBILE
IN OTHER LANGUAGES
JOIN IT MELI
PREVIOUS STORIES
CAREERS
Machine Learning
"10 flight checks for a ML project" series by Nico Presta
10 flight checks for any (big) ML project
10 flight checks for any (big) ML project
So you are about to start a new machine learning project. Here is a “flight checklist” for your plane to take off and land safely!
Nicolas Rodriguez Presta
May 12, 2021
#1 — No Machine Learning. KPIs first
#1 — No Machine Learning. KPIs first
The importance and complexity of designing good KPIs in a Machine Learning project.
Nicolas Rodriguez Presta
May 19, 2021
#2 — Skills diversity: Building the right machine learning team
#2 — Skills diversity: Building the right machine learning team
A view of the differents skills needed for develop a successful ML project
Nicolas Rodriguez Presta
May 27, 2021
#3 — This is why you are not iterating your ML project fast enough
#3 — This is why you are not iterating your ML project fast enough
Stop delaying that deploy, take risks to base decisions on production metrics
Nicolas Rodriguez Presta
Jun 10, 2021
#4 — Be accountable for the Tech Debt
#4 — Be accountable for the Tech Debt
Let’s find out how much technical debt do your machine learning projects have with this game.
Nicolas Rodriguez Presta
Jul 30, 2021
#5 — Any Machine Learning Project, is a Software Project First
#5 — Any Machine Learning Project, is a Software Project First
This explanation may seem unnecessary; not in my experience, though.
Nicolas Rodriguez Presta
Aug 19, 2021
#6 — The key for data science projects: Stand Close to the User
#6 — The key for data science projects: Stand Close to the User
Time investment is correct, but only if time is invested in the generation of short or long term value for the user.
Nicolas Rodriguez Presta
Sep 17, 2021
#7 — Are your Problems Similar to those of the Rest of the Industry?
#7 — Are your Problems Similar to those of the Rest of the Industry?
The question is: Can the components of your ML current solution be commoditized?
Nicolas Rodriguez Presta
Oct 14, 2021
#8 — Continuous Benchmark in ML projects
#8 — Continuous Benchmark in ML projects
The importance of enabling the competition to improve the final product.
Nicolas Rodriguez Presta
Oct 22, 2021
#9 — Train serving skew & data dependency problems
#9 — Train serving skew & data dependency problems
How to mitigate risks from data problems in productive machine learning models
Nicolas Rodriguez Presta
Nov 18, 2021
About Mercado Libre Tech
Latest Stories
Archive
About Medium
Terms
Privacy
Teams