Great points! While I was drafting this article, I was already quite curious about the main reason behind the relationship between Embarked variable and Survival. I am almost certain that one of the your explanations for this effect is the answer. Another possibility could be that Southampton might have been the port that most 3rd class passengers embarked on the ship. To be honest, it is not very difficult to answer these questions. On the other hand, my motivation to write this article was to improve the first model that introduced in the Part-I of the tutorial (https://bit.ly/2MiIPXh) where I developed a program with less than 20 lines of code to enter the Kaggle’s Titanic competition. Thus, I tried to keep things as simple as possible since an articles can get quite messy with extensive analyses and yes, the competition only focuses on the accuracy. However, I absolutely agree that analyzing the issues you have pointed out would have made the article a lot better. So, I will keep these in mind in my next article :) Thank you very much for your time!