Route 53 + API Gateway + Lambda could improve yours too.

Photo by @ryland_dean on Unsplash

As your company grows, your team uses more tools. You have a CRM, a Sales Management System, a Customers Service platform, a Product Analytics tool, a Subscription Analytics platform, a few in-house tools, and probably more.

How many times a day do you navigate to the CRM to find a customer, just to switch to your Customer Service platform or any of your Data Analysis tools, and look at the same person across multiple tools?

If you have to navigate from one tool to another, you certainly have a loss of productivity.

How to improve navigation between your tools?

In fact, the solution is simple: you just…

How to tune XGBoost hyperparameters and supercharge the performance of your model?

Photo by @spacex on Unsplash

Why is XGBoost so popular?

Initially started as a research project in 2014, XGBoost has quickly become one of the most popular Machine Learning algorithms of the past few years.

Many consider it as one of the best algorithms and, due to its great performance for regression and classification problems, would recommend it as a first choice in many situations. XGBoost has become famous for winning tons of Kaggle competitions, is now used in many industry-application, and is even implemented within machine-learning platforms, such as BigQuery ML.

If you’re reading this article on XGBoost hyperparameters optimization, you’re probably familiar with the algorithm. …

How to use Bigquery ML to deploy your models in no time, and focus on what really matters.

Photo by Patrick Federi on Unsplash

A few months ago at Agorapulse, we kickstarted two new Machine Learning based projects. Since we’d been using BigQuery for almost 2 years, we had to give BQML a shot. Here is what we learned, and what you could learn from it!

The biggest challenges might not be what you think

As a Machine Learning engineer, you usually think about How to create the best performing model, What algorithm to use, or How to optimize the model to go from a 94% accuracy to 96%.

But if your company is at the beginning of its Machine Learning journey, it’s probably not the most important part of the process. At…


Here we are, Zack Snyder’s Justice League was just released on March 18, 2021. The same day that France (at least, a part of it) entered the 3rd lock-down.

Well, that’s perfect timing to use the spare time and make a Data-based movie analysis!

The notebook is accessible here on Kaggle.


Zack Snyder’s Justice League is a new, deeper and longer, version of the 2017's Justice League movie.

The two versions are fundamentally the same movie: a big bad guy (Steppenwolf) wants to find the 3 MotherBoxes to conquer earth. …

Today technology and “everything as a service” makes it easier and faster than ever to build products. In this article, I wanna share the “leverage what already exists” philosophy, by telling you the story of a 7 days side software project — that even made some recurring revenues for the past few months.

Back in April 2018, I launched a product Leadly, the first application that I intended to sell. Leadly was a landing page app working inside Facebook, which allowed you to generate leads, get emails and send notifications to your leads directly through Facebook notifications… pretty cool stuff.

David Martins

Lead Data Engineer & Data Scientist | Passionate about Tech · History · Futurism · Philosophy

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store