A Practical Guide to Causal Inference in ML
Moving beyond correlation to understand what actually drives your metrics.
#causal-inference#tutorial
Writing
Thoughts on ML, AI, and building things that work.
Why Interpretable ML Wins in Business
How SHAP and LIME help you get buy-in from stakeholders (without pretending correlation is causation).
#interpretable-ml#shap#lime#causal-inference#ml-in-business
Lessons from Deploying LLMs in Production
What I learned shipping LLM applications to real users.
#llms#mlops
Pre-Snap Tells and Offensive Predictability in the NFL
Using ML classification on NFL tracking data to measure how formation predictability correlates with on-field performance.
#sports-analytics#machine-learning#classification
Predicting DNA Properties with Bioinformatics and Interpretable ML
Using k-mer features to predict DNAse I hypersensitivity with interpretable models in R.
#bioinformatics#interpretable-ml#genomics
Predicting Drug Toxicity with Cheminformatics and ML
QSAR modeling on the Ames Mutagenicity dataset using interpretable ML in R.
#cheminformatics#bioinformatics#interpretable-ml
From Pairwise to Batch Sequence Alignment in R
Building a practical bioinformatics pipeline from single alignments to parallelized batch processing to a Shiny app.
#bioinformatics#r#sequence-alignment
Want more? Subscribe to the newsletter.
Subscribe →