Data Science for Climate Science – ML Weather Forecasting, Downscaling and Emissions Monitoring
📋 KEY INSIGHTSClimate and weather data science is one of the highest-impact ML application domains: improved numerical weather prediction saves lives through better storm...
Deep Learning for Recommendation Systems – Two-Tower, DLRM and Sequential Recommenders
📋 KEY INSIGHTSDeep learning recommendation systems (DLRS) have largely superseded matrix factorisation in production because they can simultaneously model sparse ID features (user ID,...
Bayesian Deep Learning – MC Dropout, Deep Ensembles, SWAG and Calibrated Uncertainty
📋 KEY INSIGHTSBayesian deep learning (BDL) produces calibrated predictive uncertainty estimates from neural networks — quantifying not just the predicted class or value but...
Causal Discovery – PC Algorithm, LiNGAM, NOTEARS and Learning DAGs from Observational Data
📋 KEY INSIGHTSCausal discovery algorithms automatically learn the causal graph (DAG or CPDAG) from observational data — without running experiments — by exploiting conditional...
Data Science in Supply Chain – Demand Forecasting, Inventory Optimisation and Logistics ML
📋 KEY INSIGHTSSupply chain data science encompasses three interconnected forecasting and optimisation problems: demand forecasting (how much of each product will be needed, when,...
