What are the features of forecasting with holidays and rare events?
Machine Learning / AI
How to use product categories to form relevant recommendations?
What are causal graphs (DAG) and d-separation?
What is Snapdragon AI Engine?
How do you evaluate the quality of a fine-tuned LLM on a user domain?
How to check the relevance of a model on test data before deployment to production?
How to approach dataset preprocessing?
How to implement an item-based approach in recommendation systems?
What is the difference between Series and DataFrame in pandas?
What is pruning in LLM and what approaches are there (magnitude, structured, SparseGPT)?
What is spatial cross-validation and why is it needed?
What is RLAIF and how does it differ from RLHF?
How to divide clients into two groups for A/B testing?
What classic approaches exist for filling gaps in interaction matrices in recommendation systems?
How to ensure the quality of a model using trigger purchases and customer avatars?
Which techniques are cheaper than human eval (LLM-as-a-judge, model-graded)?
What is the difference between the map and apply methods in pandas?
What is product quantization (PQ) and what are its quality losses?
How to get recommendations from the interaction matrix?
What is a concordance index?