BROADCASTS.com

b'If you\\u2019ve taken a machine learning class, or read up on A/B tests, you likely have a decent grounding in the theoretical pillars of data science. But if you\\u2019re in a position to have actually built lots of models or run lots of experiments, there\\u2019s almost certainly a bunch of extra \\u201cstreet smarts\\u201d insights you\\u2019ve had that go beyond the \\u201cbooks smarts\\u201d of more academic studies. The data scientists at Booking.com, who run build models and experiments constantly, have written a paper that bridges the gap and talks about what non-obvious things they\\u2019ve learned from that practice. In this episode we read and digest that paper, talking through the gotchas that they don\\u2019t always teach in a classroom but that make data science tricky and interesting in the real world.\\n\\nRelevant links:\\nhttps://www.kdd.org/kdd2019/accepted-papers/view/150-successful-machine-learning-models-6-lessons-learned-at-booking.com'