talk-data.com talk-data.com

Filter by Source

Select conferences and events

People (32 results)

See all 32 →
Showing 5 results

Activities & events

Title & Speakers Event

Jupyter notebooks have been around for a while now and are an approachable starting point for anyone interested to explore data and programming. It's done a lot of good, but it was never really designed to be 'the' Python notebook. It's always wanted to support multiple languages and this is reflected in many of the design decisions. And that makes you wonder, what could one do if we really did do just that? What if we ignored other languages and really only cared about Python and data tools? Would the notebook be different?

The goal of this talk is to demonstrate this idea by talking about widgets, reactive Python, modern data tooling and also about the freedom to rethink your tools. There will also be demos. Lots. Of. Demos.

Python

Machine learning (ML) models in production often start with a single objective, such as maximizing conversion rate in the payment industry. However, real-world business contexts are often more nuanced where other aspects relevant to a transaction, such as transaction cost or fraud risk, come into play. These objectives can be inherently conflicting: while optimizing for authorization may drive more revenue, it could also lead to higher costs or increased risk exposure.

Addressing such trade-offs necessitates the consideration of multi-objective optimization (MOO), while key information in the payment context plays a role in determining which objective should get more weight when considering the trade-off. In this talk we will share how we (Optimize ML team at Adyen) use the contextualized scalarization approach to improve our Intelligent Payment Routing product with a focus on conversion rate and transaction cost optimization.

AI/ML

We talked about:

Vincent’s Background SciKit Learn’s History and Company Formation Maintaining and Transitioning Open Source Projects Teaching and Learning Through Open Source Role of Developer Relations and Content Creation Teaching Through Calm Code and The Importance of Content Creation Current Projects and Future Plans for Calm Code Data Processing Tricks and The Importance of Innovation Learning the Fundamentals and Changing the Way You See a Problem Dev Rel and Core Dev in One Why :probabl. Needs a Dev Rel Exploration of Skrub and Advanced Data Processing Personal Insights on SciKit Learn and Industry Trends Vincent’s Upcoming Projects

Links:

probabl. YouTube channel: https://www.youtube.com/@UCIat2Cdg661wF5DQDWTQAmg Calmcode website: https://calmcode.io/ probabl. website: https://probabl.ai/

Free Data Engineering course: https://github.com/DataTalksClub/data-engineering-zoomcamp

Join DataTalks.Club: https://datatalks.club/slack.html Our events: https://datatalks.club/events.html

AI/ML Data Engineering GitHub HTML Scikit-learn
DataTalks.Club

Creating and maintaining open-source libraries - Vincent Warmerdam

About the event

Outline:

  • ​​Working in open source
  • ​Maintaining scikit-learn and other open-source projects

​​ About the speaker:

Vincent works as a Research Advocate at Rasa where he collaborates with the research team to explain and understand conversational systems better. One of his activities is maintaining a youtube playlist that explains NLP algorithms over at “the algorithm whiteboard”. Before, he was a consultant working on production algorithms for a large range of companies.

​Vincent is a firm believer in open source and certainly doesn’t mind to evangelise from time to time. He has a blog about the slightly less obvious aspects in the world of data science over at https://koaning.io. He’s also working on a project that tries to help people get started over at https://calmcode.io.

​​DataTalks.Club is the place to talk about data. Join our slack community!

Working in Open Source - Probabl.ai and sklearn

We talked about 

open source getting started with open source convincing your employer to contribute to open source public speaking the checklist for open source projects the role of research advocate

And many more things!

Links from Vincent:

https://www.youtube.com/watch?v=68ABAU_V8qI&t=975s&ab_channel=PyData https://www.youtube.com/watch?v=kYMfE9u-lMo&t=958s&ab_channel=PyData https://koaning.io/projects.html https://calmcode.io/ https://makenames.io/ https://koaning.github.io/clumper/api/clumper.html

Join DataTalks.Club: https://datatalks.club​

GitHub HTML
DataTalks.Club
Showing 5 results