Amid the ongoing pandemic, such as the Covid-19 outbreak, there exists a critical need to comprehend and forecast the dynamic trends of daily confirmed cases to effectively prevent and mitigate the impact of its consequences. This study aims to investigate the essential factors acting as predictors for forecasting daily new confirmed cases specifically within the Indonesian setting. Utilizing advanced Deep Learning (DL) methodologies, including Deep Feedforward Neural Networks (DFNN), Long Short-Term Memory (LSTM), one-dimensional convolutional neural networks (CONV1D), and Gated Recurrent Units (GRU), this research endeavors to predict daily confirmed Covid-19 cases in Indonesia. To achieve this, a comprehensive set of 80 variables (predictors), encompassing the effective reproduction number (Rt), was utilized as input parameters. Before model construction, rigorous variable selection procedures and statistical analyses were conducted to enhance data understanding. The effectiveness of the predictive model was assessed using various metrics, such as Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Scaled Error (MASE), which evaluates MAE relative to a baseline model. Results indicate that DL models incorporating two key predictors—daily confirmed case count and Rt—exhibited superior predictive performance, capable of forecasting daily confirmed cases up to 13 days in advance. The inclusion of additional variables was found to diminish the predictive accuracy of DL algorithms.