It seems the ability of this tool to extract features from regular enterprise databases will save lots of manual effort<p>Github repo url <a href="https://github.com/Featuretools/featuretools" rel="nofollow">https://github.com/Featuretools/featuretools</a><p>Python notebook for NYC Taxi 1.5 million trips training dataset <a href="https://github.com/Featuretools/NYC-Taxi-Demo/blob/master/NYC%20Taxi%203%20-%20Simple%20Featuretools.ipynb" rel="nofollow">https://github.com/Featuretools/NYC-Taxi-Demo/blob/master/NY...</a><p>How this automated feature extraction compares:<p><pre><code> Received a score of 0.45288 on the Kaggle competition.
Placed 685 out of 1257.
Beat 45% of competitors on the Kaggle competition.
Scored 4% better than the baseline solution
Had a modeling RMSLE of 0.40196</code></pre>