Explains the statistical concept of included-variable bias in regression models, challenging the traditional 'omitted-variable bias' framing.
Explores the challenge of defining and reducing toxic content in large language models, discussing categorization and safety methods.
Key takeaways from RecSys 2020 conference, focusing on ethics, bias, sequence models, and notable papers in recommender systems.
A statistician's response to New Zealand's proposed Algorithms Charter, analyzing its principles for ethical and transparent government algorithm use.
A data scientist details how a flawed train-test split method introduced bias when adding image thumbnails to a content recommendation model.
