New post on how scientific language changes and why we need to be careful when using past and future data in machine learning even in natural language processing.
Check it out here:
The post: lnkd.in/p/eeK_q26y
The code: github.com/NikNord174/a...
Check it out here:
The post: lnkd.in/p/eeK_q26y
The code: github.com/NikNord174/a...
#datascience #machinelearning #nlp #mlevaluation #datadrift | Nikolai Orlov
Scientific language is changing. And it’s breaking my model.🤖
Last week, I showed how mixing past and future data can make a solar-generation forecast look better than it really is. This project reve...
lnkd.in
August 19, 2026 at 11:19 AM
New post on how scientific language changes and why we need to be careful when using past and future data in machine learning even in natural language processing.
Check it out here:
The post: lnkd.in/p/eeK_q26y
The code: github.com/NikNord174/a...
Check it out here:
The post: lnkd.in/p/eeK_q26y
The code: github.com/NikNord174/a...
✨ New in Big Data & Society ✨
“Making machine learning good enough – studying the political endeavour of finding ‘right’ metrics and thresholds” by @annaschjoett.bsky.social and Tobias Blanke.
🔓: journals.sagepub.com/doi/10.1177/...
#machinelearning #goodenough #MLevaluation
“Making machine learning good enough – studying the political endeavour of finding ‘right’ metrics and thresholds” by @annaschjoett.bsky.social and Tobias Blanke.
🔓: journals.sagepub.com/doi/10.1177/...
#machinelearning #goodenough #MLevaluation
April 24, 2026 at 9:13 AM
✨ New in Big Data & Society ✨
“Making machine learning good enough – studying the political endeavour of finding ‘right’ metrics and thresholds” by @annaschjoett.bsky.social and Tobias Blanke.
🔓: journals.sagepub.com/doi/10.1177/...
#machinelearning #goodenough #MLevaluation
“Making machine learning good enough – studying the political endeavour of finding ‘right’ metrics and thresholds” by @annaschjoett.bsky.social and Tobias Blanke.
🔓: journals.sagepub.com/doi/10.1177/...
#machinelearning #goodenough #MLevaluation
Offline metrics vs. real-world impact for recommender systems? 🤔 Part 3 dives into bridging the gap with A/B testing, business value, & fairness! It's more than just accuracy. Learn how to truly evaluate. 👇 fanyangmeng.blog/recommender-... #RecommenderSystems #MLEvaluation
Recommender System Evaluation (Part 3): Real-World Deployment - When Rubber Meets the Road
Go beyond offline accuracy to truly evaluate your recommender system. This guide covers A/B testing, conversion funnels, fairness, and the business metrics that drive real-world success and retention.
fanyangmeng.blog
June 16, 2025 at 6:00 AM
Offline metrics vs. real-world impact for recommender systems? 🤔 Part 3 dives into bridging the gap with A/B testing, business value, & fairness! It's more than just accuracy. Learn how to truly evaluate. 👇 fanyangmeng.blog/recommender-... #RecommenderSystems #MLEvaluation