Modeling US Dollar and Nigerian Naira Exchange Rates During COVID-19 Pandemic Period: Identification of a High-performance Model for New Applications

This study modeled the US Dollar and Nigerian Naira exchange rates during COVID-19 pandemic period using a classical statistical method – Autoregressive Integrated Moving Average (ARIMA) two machine learning methods Artificial Neural Network (ANN) Random Forest (RF). The data were divided into sets namely: training set test set. was used to obtain parameters of model, performance estimated model validated on that served as new data. Though ARIMA random forest performed slightly better than neural network in set, their poor. with 5 nodes input layer, hidden layer 1 node output (ANN (5,5,1)) (test set) is chosen best forecast for future USD NGN rate. information from high-performance (5, 5, 1)) modeling rate will assist econometric trading currencies offer both speculative precautionary assistance individuals, households, firms nations who use locally international trade.