The following post tries to mimic the following idea by google AI LINK and also takes a lot of tips from the final project of the Deep Learning course from the Advanced Machine Learning course on Coursera.

If you haven’t seen the first part please go there to have a better understanding of what is the problem and what kind of preprocessing was done on the data before the model stage: Part 1.

In this two part blog post I go over my solution for the Avito challenge competition on Kaggle. It was a pretty interesting competition since it forced me to use many techniques across different fields in Machine Learning like Natural Language Processing and Computer vision. The solution is divided into two parts:

• Part 1 focuses on explaining the problem and some of the feature engineering used
• Part 2 looks at the different models tried and also the stacking methodology

I like going over a complete course as it helps cement content in the brain. That’s also one of the strongest benefit of mentoring and teaching. It forces you to review material and education is a lot about repetition. In this first review I will look at the following online course I’ve done recently :
AI Nanodegree

Hello, welcome to my blog. This post is simply here to see if it is working correctly (or at all!).