Feature Importance Analysis with SHAP I Learned at Spotify (with the Help of the Avengers

<p>Two years ago, I conducted a fascinating research project at Spotify as part of my Master&rsquo;s Thesis. I learned several useful ML techniques, which I believe any Data Scientist should have in their toolkit. And today, I&rsquo;m here to walk you through one of them.</p> <p>During that time, I spent 6 months trying to build a prediction model and then deciphering its inner workings.&nbsp;<em>My goal was to understand what made users satisfied with their music experience.</em></p> <p>It wasn&rsquo;t so much about predicting whether a user was happy (or not), but rather understanding the&nbsp;<em>underlying</em>&nbsp;factors that contributed to their happiness (or lack thereof).</p> <p>Sounds exciting, right? It was! I loved every bit of it because I learned so much about how ML can be applied in the context of music and user behavior.</p> <p><em>(If you&rsquo;re interested in the applications of ML in the music industry, then I highly recommend checking out this interesting&nbsp;</em><a href="https://research.atspotify.com/2018/07/understanding-and-evaluating-user-satisfaction-with-music-discovery/" rel="noopener ugc nofollow" target="_blank"><em>research</em></a><em>&nbsp;led by Spotify&rsquo;s top experts. It&rsquo;s a must-read!)</em></p> <h1>Machine Learning &amp; Behavioral Psychology in Tech</h1> <p><img alt="" src="https://miro.medium.com/v2/resize:fit:700/0*7vLTGTsdjM71gxvT.png" style="height:700px; width:700px" /></p> <p>Image by Author (Midjourney)</p> <p>In tech, research projects like mine are very common because a lot of the work revolves around delivering the best personalized experience for users/customers.</p> <p><a href="https://towardsdatascience.com/feature-importance-analysis-with-shap-i-learned-at-spotify-aacd769831b4">Visit Now</a></p>