COMPARATIVE ANALYSIS OF PREDICTIVE POWER OF TRADITIONAL ECONOMETRICS AND A.I BASED MODELS OF EXCHANGE RATE IN NIGERIA

Abstract

This paper presents a comparative analysis of the predictive power of traditional econometric models and AL- based models in forecasting exchange in Nigerian. The exchange is one of the macroeconomics variable which are interest rate, inflation. The traditional models including Auto regression integrated moving average (ARIMA) Where the AL MODELS including artificial neutral network (ANN), GRU, LSTM model to model and predict the real exchange data. The purpose of the study is to show the effectiveness and compare the best predictive for forecasting the exchange in Nigerian. The paper evaluates the performance of each model in term accuracy, robustness and computational efficiency. The data under was collected from ranging from 1997 to 2023 and the data base was collected by Nigeria statistic s bulletin. This study split the data set into training and testing and applied all stated models. The study selects a model that meets the key performance indicators (KPI) criteria .this model was selected as the best candidate model to predict the behavior of the exchange rate data.