Forecasting Unemployment Rates using a Combined ARIMA and LSTM Approach

Airen, Kushagra (2024) Forecasting Unemployment Rates using a Combined ARIMA and LSTM Approach. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (3MB) | Preview

Abstract

Predicting unemployment involves using historical data and macroeconomic factors to estimate the value of the number of unemployed people as a percentage of the labor force. This study proposes a hybrid approach of combining the strengths of a statistical model like ARIMA and a deep learning model like LSTM to accurately predict the unemployment rate especially in economic crisis like COVID-19 pandemic. A combination of financial indicators of United States datasets, spanning from1979 to2023 are used to train the model to predict unemployment rate. Along with ARIMA- LSTM hybrid model, standalone models of ARIMA and LSTM were also implemented and evaluated using the performance metrics, in which the standalone LSTMmodel has outperformed the hybrid model with the MAE of 0.43. The objective of this research also aligns with the United Nations Sustainable Development Goal 8 since by predicting unemployment this study will aid in inclusive and sustainable economic growth and ensure productive employment and decent work for all.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jilani, Musfira UNSPECIFIED
Uncontrolled Keywords:	ARIMA-LSTM; hyperparameter tuning; LSTM; unemployment; economic crisis
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > Economics H Social Sciences > HD Industries. Land use. Labor > Issues of Labour and Work H Social Sciences > HD Industries. Land use. Labor > Issues of Labour and Work > Unemployment
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	06 Aug 2025 14:44
Last Modified:	06 Aug 2025 14:44
URI:	https://norma.ncirl.ie/id/eprint/8449

Actions (login required)

View Item