Daily Dose of DS offers a daily dose of inspiration, education, and motivation for data scientists and aspiring data professionals. Through bite-sized articles, tutorials, and curated resources, readers embark on a journey to master the art and science of data analysis, machine learning, and artificial intelligence. By staying updated with the latest trends, techniques, and tools in data science, readers can hone their skills and stay ahead in this rapidly evolving field.

Daily Dose of Data Science | Avi Chawla | Substack

Quantile regression extends traditional regression by predicting multiple percentiles of the outcome distribution rather than just the mean. Instead of a single point estimate, it provides quantile-level predictions (e.g., 25th, 50th, 75th percentiles) by training separate models with asymmetric loss functions. The technique uses quantile loss (pinball loss) with a weight parameter that assigns different penalties to over- and under-predictions, pulling the regression line toward desired percentiles. Implementation involves optimizing model weights using scipy's minimize function for different quantile values, and the approach works particularly well with tree-based models like LightGBM.

Introduction to Quantile regression

Lightning AI + Voltage Park: One Platform, Zero Infrastructure Headaches

P.S. For those wanting to develop “Industry ML” expertise: