Predicting Impact of COVID-19 on Crude Oil Price Image with Directed Acyclic Graph Deep Convolution Neural Network

Deep learning methods have achieved amazing results in sequential input, prediction and image classification. In this study, we propose transformation of time series crude oil price by incorporating 2-D Directed Acyclic Graph to Convolutional Neural Network (DAG) based on processing properties. Crude is converted into images, utilizing 10 distinctive technical indicators. Geometric Brownian Motion was utilized produces data for a 10-day span. Thus, 10x10 sized images are constructed. Each then labelled as Buy or Sell depending the returns series. The show that integrating DAG with CNN improves accuracy 14.18%. perform best an 99.16%, sensitivity 100% specificity 99.19%. COVID-19 has negatively affected Nigeria which indicates downward trend price. study recommends poly-cultural economy national development nation.