Maya Hristakeva

Personalisation @Spotify #RecSys #MachineLearning

[Zahra Nazari @ZahraNazari1]

Super excited this work is getting out! a summary of the work:
- Recommender engines are serving as a window into the world by regulating what content we see on a daily basis. 
(1/3)

[Mounia Lalmas @mounialalmas]

A great article about music recommendations at Spotify, including the research we are doing at @SpotifyResearch in this area.
https://t.co/jiCC090OLC

[Balázs Hidasi @balazshidasi]

I compiled my notes from #recsys2021 into a blogpost: impressions, current trends in recsys research, my favorite papers and highlights from other interesting works. https://t.co/nCnesi5gFD @gravityrd @domonkostikk

[Paul Lamere @plamere]

Spotify is America’s most loved workplace. I’m not surprised. It really is a great place to work.

https://t.co/5JanHOLbsQ

[Chip Huyen @chipro]

An early draft of the machine learning interviews book is out 🥳

The book is open-sourced and free. Job search is a stressful process, and I hope that this effort can help in some way.

Contributions and feedback are appreciated!

https://t.co/N1m3kNvZfo

[Maya Hristakeva @mayahhf]

@totopampin @Spotify Welcome!

[Maya Hristakeva @mayahhf]

@ocelma @Spotify Welcome! ✨

[Natasha Jaques @natashajaques]

I couldn't resist. With contributions from @maxhkw

[Josh Baer @jbx____]

Cool to see our ML and ML Platform reps talk about how we build ML @ Spotify! Cool insights on how we leverage an engagement team, layer our ML for product and build for the user needs!
Way to go Lex, @Jiminy_Kirket, Maisha, @mayahhf and @unclesam
https://t.co/1jMzy7r8q0

[Eugene Yan @eugeneyan]

RecSys2020 (22-26 Sep) gave a peek into recent ideas on recommenders from academia & industry.

Some takeaways:
• Emphasis on ethics & bias
• Offline evaluation is tricky
• Dot product > learned similarities
• Many examples of real-world recsys

More👇 https://t.co/XAOl8WsU3o

[Chip Huyen @chipro]

When talking to people who haven’t deployed ML models, I keep hearing a lot of misperceptions about ML models in production. Here are a few of them.

(1/6)

[Mounia Lalmas @mounialalmas]

Congratulations to @ZhenwenDai @pchandarr @ghazalfazelnia @BenCarterette our first @SpotifyResearch paper "Model Selection for Production System via Automated Online Experiments" accepted at #NeurIPS2020. Great team work describing work around ML experimentation at scale.

[Denis Parra @denisparra]

proceedings of the #recsys2020 conference @ACMRecSys https://t.co/oTmiDbUs8d you can access papers for free!

[Mounia Lalmas @mounialalmas]

Sharing widely the slides of our #KDD2020 "Tutorial on Online User Engagement: Metrics and Optimization", which @hongliangjie and I gave on Sunday. Thank you for attending, your questions and feedbacks 🙏

https://t.co/g5lPtFsT1X

[Daniela Witten @daniela_witten]

The Bias-Variance Trade-Off & "DOUBLE DESCENT" 🧵

Remember the bias-variance trade-off? It says that models perform well for an "intermediate level of flexibility". You've seen the picture of the U-shape test error curve.

We try to hit the "sweet spot" of flexibility.

1/🧵

[Ching-Wei Chen @cweichen]

Only 1 more week to submit to #PodRecs: The Workshop on Podcast Recommendations @ACMRecSys! This is a relatively new field covering broad topics of #RecSys, NLP, KDD, speech/audio, fairness, evaluation and more. Don't be shy, apply! @PodRecSys #RecSys2020 https://t.co/Rxk0ckttUC

[Elias Bareinboim @eliasbareinboim]

Interested in Causal Inference & Reinforcement Learning? Consider attending my @icmlconf tutorial on the basic principles & tools of Causal Reinforcement Learning (CRL). I’ll discuss many new & pervasive learning challenges/opportunities within CRL. Link: https://t.co/jXWmCYXvEA

[Nando de Freitas @NandoDF]

This is such an important tweet for new researchers: A Turing award winner’s public admission that failure is ok. It’s through trying and failing (ie falsifying some hypotheses) that we make scientific progress. Thanks Geoff for setting a brilliant example.

[Sean J. Taylor @seanjtaylor]

A framework for designing and evaluating metrics: https://t.co/ifW7iCqdJL