Comparative analysis of Mixed-Data Sampling (MIDAS) model compared to Lag-Llama model for inflation nowcasting

TL;DR

This paper compares the traditional MIDAS econometric model with the innovative Lag-Llama neural network for inflation nowcasting, demonstrating Lag-Llama's superior performance across multiple metrics in Euro area data from 2010 to 2022.

Contribution

It provides a comparative analysis showing that the Lag-Llama neural network outperforms the MIDAS model in inflation nowcasting tasks.

Findings

Lag-Llama outperforms MIDAS across all evaluation metrics.

Pre-trained neural network models can enhance economic indicator forecasting.

The study confirms the potential of AI-based models in macroeconomic nowcasting.

Abstract

Inflation is one of the most important economic indicators closely watched by both public institutions and private agents. This study compares the performance of a traditional econometric model, Mixed Data Sampling regression, with one of the newest developments from the field of Artificial Intelligence, a foundational time series forecasting model based on a Long short-term memory neural network called Lag-Llama, in their ability to nowcast the Harmonized Index of Consumer Prices in the Euro area. Two models were compared and assessed whether the Lag-Llama can outperform the MIDAS regression, ensuring that the MIDAS regression is evaluated under the best-case scenario using a dataset spanning from 2010 to 2022. The following metrics were used to evaluate the models: Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), correlation with the target, R-squared and adjusted R-squared. The results show better performance of the pre-trained Lag-Llama across all metrics.