GraphLab Notebook | Who Survived the Titanic?

User 2 | 11/3/2014, 8:40:06 PM

        <div class="EmbeddedContent"><img src="http://graphlab.com/images/GLlogo_FU_STACKED_300.png" class="LeftAlign" /><strong>GraphLab Notebook | Who Survived the Titanic?</strong>
           <p>The competition requires to predict which kind of people were likely to survive the sinking of Titanic. We will face this challenge building regression models, Gradient Boosted Trees and Support Vector Machine models, using the regression, tree ensembles and classification toolkits which GraphLab comes with.</p>
           <p><a href="http://graphlab.com/learn/gallery/notebooks/who_survived_the_titanic.html">Read the full story here</a></p>
           <div class="ClearFix"></div>
        </div>

Comments

User 871 | 11/3/2014, 8:40:06 PM

This is very well written study of data and methodology for finding best classification algorithm. Only problem is that in many places % accuracy and error are quoted different from what actual computation shows in thsi same notebook. I wonder what is the cause of this discrepancy?