Forecasting Inflation in Norway Using Machine Learning

Abstract

This thesis investigates the efficacy of machine learning (ML) models, such as Random Forest and Long-short-term memory (LSTM), in forecasting post-Covid inflation trends in Norway. The research demonstrates that LSTM models outperform traditional benchmark models and an autoregressive integrated moving average (ARIMA) model within a 12-month forecast horizon, focusing on the sudden surge in inflation following the pandemic. The findings are constrained to the specific economic conditions of the post-Covid period in Norway, with no testing performed under other economic circumstances. This thesis contributes to the understanding of ML’s potential in economic forecasting and suggests pathways for future research to overcome its limitations and explore new methodologies in the field of economic analysis.