Solving the Titanic Kaggle Competition in Azure ML

In this tutorial we will show you how to complete the titanic Kaggle competition using Microsoft Azure Machine Learning Studio.This video assumes you have an Azure account and you understand how to use Azure.

Kaggle Titanic Experiment:

Learn more about Data Science Dojo here:

Watch the latest video tutorials here:

See what our past attendees are saying here:

Like Us:
Follow Us:
Connect with Us:

Also find us on:

#azuretutorial #azure #kaggle


3 replies on “Solving the Titanic Kaggle Competition in Azure ML”

Why do you train on 100% of your data. Even after cross validation you basically ignore your original model and train a complete new one. So with 100% of data you cannot ensure that your model gets worse than before can you? Thx

Hi, I’m following your process for the “random acts of pizza” dataset from Kaggle.
In the model building I get around 75% accuracy which is matched with 10 fold cross validation with a variance of 1% either way. However after building the model on all train data and applying to the test set I get just a 52% accuracy score when submitted to Kaggle. If I am sure that I am following the steps correctly does this just in the card that my model is overfitting the train data?

Leave a Reply

Your email address will not be published. Required fields are marked *