From Raw Data to Edge: Building a Predictive Pipeline
How we turn scattered, messy data into a deployed prediction service — collection, features, training and inference.
Research
Case studies and methodology notes on quantitative sports analytics — how we collect data, validate models and build predictive pipelines.
How We Validate a Predictive Model
Backtesting, accuracy, calibration and drawdown — why a model is only as good as the evidence behind it.
Analyzing a Live Match: A Case Study in Data-Driven Decision Making
A first-hand account of a qualifying match in Samokov — how live observation compares to a predictive model's read before tip-off.