The spread of COVID-19 in the world had a devastating impact on the world economy, trade relations, and globalization. As the pandemic advances and new potential pandemics are on the horizon, a precise analysis of recent fluctuations of trade becomes necessary for international decisions and controlling the world in a similar crisis. The COVID-19 pandemic made a new pattern of trade in the world and affected how businesses work and trade with each other. It means that every potential pandemic or any unprecedented event in the world can change the market rules. This research develops a novel model to have a proper estimation of the stock market values with respect to the COVID-19 dataset using long short-term memory networks (LSTM).
The nature of the features in each pandemic is completely different, thus, prediction results for a pandemic by a specific model cannot be applied to other pandemics. Hence, recognizing and extracting the features which affect the pandemic is the highest priority. In this study, we develop a framework, providing a better understanding of the features and feature selection. Although the global impacts incurred by COVID-19 are complicated, here we are trying to show how additional features like COVID-19 rather than the history of tickers, which is used conventionally for prediction, cab help forecasting in a real-world scenario. This study is based on a preliminary analysis of such features for enhancing forecasting models' performance against fluctuations in the market.
Our forecasts are based on the market value data and COVID-19 pandemic daily time-series data (i.e. the number of new cases). In this study, we selected Gold price as a base for our forecasting task which can be replaced by any other markets. We have applied Convolutional Neural Networks (CNN) LSTM, Vector Output Sequence LSTM, Bidirectional LSTM, and Encoder-Decoder LSTM on our dataset, and our results achieved an MSE of 6.0e-4, 8.0e-4, and 2.0e-3 on the validation set respectfully for one day, two days, and 30 days predictions in advance which are outperforming other proposed method in the literature.