•  
      •  
    #product #data #project #managers

    Nine lessons I learned working with ML products

    I want to share with you 9 stories about ML development which illustrate how confusing and counterintuitive ML can sometimes be. Some of them fun, some... have learning value. I hope they will help you avoid some of the mistakes and achive significant results faster.

    Key Takeaways:
    1. Always start with a heuristics.
    2. Reliable fallback is a good foundation for innovation.
    3. Model = Code + Data.
    4. Online/offline parity.
    5. Why models always fail quitely.
    6. Do customers care about the precision and recall?
    7. Experimenting 100x faster, are you kidding me?
    8. Where models go to die.
    9. If you want to eat well invest in modelling approaches, if you want to sleep well invest in features.
    • Difficulty Intermediate
    • Speech type Standard 40min
    Andrew Mende
    Sr. Product Manager Machine Learning at booking.com
    Netherlands
    Product manager with a passion for big data and machine learning.

    Other Speakers

    The program was full of amazing talks about people, code, trends, and people again. All talks underwent a careful selection process by our program committee. We didn't accept marketing talks and sell slots to sponsors. Only meaningful content, only hardcore.

    Partners