Nowcasting means forecasting in fine detail, by any method, over very short horizons, from the present into the immediate future. Originally used in meteorology, the term was later adopted in economics to describe an early assessment of the economy’s current (“now”) state. It is like a weather forecast for the economy – but instead of projecting rainfall or temperature, economists use nowcasts to make a judgment about whether the economy is growing or shrinking, and whether the balance of risk is toward heating up (increasing inflation) or cooling down (lost output and rising unemployment).
Our research looks at the practical side of short-term macroeconomic forecasting and the science behind it. We propose a Python package that combines machine learning and econometrics – canonical time-series models and modern algorithms – to read the economy as it moves, reacts, and reshapes itself. Every nowcast is estimated from the ground up, not just with new data, but with updated variables, model structures, and parameters, allowing it to respond to evolving macroeconomic dynamics, structural breaks, and policy interventions in real time. Explainable AI (XAI) principles, applied along the way, ensure that the results are fully auditable. Users know which variables matter most and how each new piece of information changes the outlook.
In that sense, the package is more than a forecasting solution. It is a tool for understanding how information flows through the economy. Grounded in strong theoretical foundations and designed for evidence-based empirical analysis, it provides a way to work with real-time data without locking users into a specific way of modeling or thinking about it.
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号