forecast-evaluation

Introduction to time series preprocessing and forecasting in Python using AR, MA, ARMA, ARIMA, SARIMA and Prophet model with forecast evaluation.

scores: Metrics for the verification, evaluation and optimisation of forecasts, predictions or models.

Utilities for Scoring and Assessing Predictions

AI-assisted XAUUSD daily research workflow with Research Skill, Agent Harness, LangGraph, Tool Calling, and free public data sources.

Comparing sequential forecasters via confidence sequences & e-processes

A verification pipeline for evaluating models and forecasts.

Easily evaluate your forecasts with (multivariate) Diebold-Mariano and (multivariate) Giacomini-White tests of equal predictive ability and MCS.

Multi Horizon Superior Predictive Ability (SPA) test proposed by Quaedvlieg (2021)

This code mainly computes the forecast of headline inflation using different aproaches. Likewise presents the forecast evaluation for each model along different points in a span period.

Pre-registered, read-only research instrument measuring whether model forecasts beat prediction-market prices (Polymarket, Kalshi) after resolution. Append-only ledger, hash-committed nightly. No execution code. MIT.

Temporal adaptation of the gamma index for time series forecast evaluation under joint amplitude and timing tolerances, with applications to renewable energy forecasting.

Replication package for "Comparing predictive ability in presence of instability over a very short time" by Iacone F., Rossini L., & Viselli A. (The Econometrics Journal, 2025). Includes files to replicate the Monte Carlo experiments and US SPF application.

Standalone AR forecasting workflow for the Sentiment–Volatility Ratio capstone project, using UMCSI and VIX data with expanding-window evaluation.

End-to-End Python replication of Iadisernia & Camassa’s LLM macroeconomic forecasting methodology (ICAIF 2025). Implements: 2,368 synthetic economist profiles, 120,000+ GPT-4o forecasts across 50 European Central Bank (ECB) SPF rounds, a rigorous ablation study with Monte Carlo & binomial hypothesis testing.

USDA Food Price Outlook forecast evaluation using CPI data, analyzing forecast accuracy, category-level errors, and long-term food inflation relative to overall CPI trends.

Reference implementation of the Relative Utility Value metric for forecast value assessment

Loss-function sensitivity in GARCH volatility forecast evaluation: evidence from Goldman Sachs and SLV.

self archived publications

Global COVID-19 data analysis & US case forecasting using ARIMA, SARIMAX, Prophet and Machine Learning (Ridge Regression) — 90% accuracy on 2020 JHU CSSE dataset.

Supplementary materials for the following publication: Davydenko, A., & Goodwin, P. (2021). Assessing point forecast bias across multiple time series: Measures and visual tools. International Journal of Statistics and Probability, 10(5), 46-69. https://doi.org/10.5539/ijsp.v10n5p46