deep learning and statistical approaches in financial modeling of foreign assets and liabilities of nepal’s banking system

This study investigates the detailed mathematical exploration followed by its com- putational performance of time series and deep learning models: arima, rnn, and tcn applied to foreign assets and liabilities of banking system of nepal con- sisting monetary authorities and various depository corporations. we analyze trends, seasonal patterns, trajectories and their descriptive statistics to capture underlying behaviors, identifying the optimal arima order that most effectively captures linear trend. empirical study shows that the rnn handles non-linear patterns which is determined by performance metrices on the training and testing split. tcn being computationally extensive model is not able to capture robust relation of the data due to lack of long-range dependencies and large time win- dowed dataset for training. based on our results, the rnn could be used as the most suitable time series forecasting model for the foreign assets and liabilities of nepal as it enhances the accuracy, minimizes error, and improves effectiveness in contributing to decision-making in banking system.