619: Tools for Deploying Data Models into Production

<p>Jon Krohn speaks with Erik Bernhardsson, the man who invented Spotify’s original music recommendation system. They address the different ways to interview a data science candidate, how to deploy a data model into the cloud, and the approach he took that made Spotify go from a digital music startup to an AI-driven streaming giant.</p><p>This episode is brought to you by Datalore (<a href='https://datalore.online/SDS'>datalore.online/SDS</a>), the collaborative data science platform, by Zencastr (<a href='http://zen.ai/sds'>zen.ai/sds</a>), the easiest way to make high-quality podcasts, and by Bunch (<a href='https://superdatascience.com/bunch'>superdatascience.com/bunch</a>), the AI driven leadership coach. Interested in sponsoring a SuperDataScience Podcast episode? Visit <a href='https://www.jonkrohn.com/podcast'>JonKrohn.com/podcast</a> for sponsorship information.<br/><br/></p><p>In this episode you will learn:<br/>• The data problem that Erik’s company Modal Labs solves [04:32]<br/>• Erik’s prolific blogging career [09:15]<br/>• Opportunities for making data teams more efficient and productive [14:42]<br/>• Erik’s views on interviewing data scientists and software developers [20:18]<br/>• Erik’s tips and tricks for data science interviewees [31:35]<br/>• How Erik built Spotify’s original music recommendation system [38:58]<br/>• Applying vectors to other tools, and opportunities for working with vectors [47:45]<br/>• Using Annoy to search across vectors [50:57]<br/>• Building Python module Luigi for Spotify [55:20]<br/>• The tools that Erik loves to work with [1:06:23]<br/><br/></p><p>Additional materials: <a href='https://www.superdatascience.com/619'>www.superdatascience.com/619<br/></a><br/></p>