All Times ET
Keywords: Unemployment Rate, Multivariate Time Series, Recurrent Neural Networks, Vector Autoregressive, Macroeconomic Indicators, Federal Reserve
Unemployment rate is an important macroeconomic indicator that is monitored by US federal government for the purpose of ensuring the proper functioning of the overall economy. Since unemployment rate is the measure of joblessness in the economy, it is important to build better forecast models for unemployment. These models are also used by the government to implement policy changes to increase employment opportunities and reduce financial hardship on the unemployed during recession. This paper uses multivariate time series methods such as Recurrent Neural Networks, Feed Forward Artificial Neural Networks and Vector Autoregressive Models to assess the improvement in forecasting of unemployment rates against their univariate time series equivalent as well as a benchmark model used by the Federal Reserve. The multivariate methods will consider historic macroeconomic variables such as GDP, Inflation, Fed Funds Rate, Commercial Loan Activities and Money Supply (Liquidity) in the economy. We further compare models across forecasts over the quarters of a year using mean absolute error and standard deviation.