After the deregulation came into the market, electricity price forecasting became an essential task for all the players in the market in order to safeguard themselves from the volatile nature of electricity prices (EP). Since EP is one of the most volatile commodities, the statistical model fails to perform well. At the same time, deep learning models have the unique ability to handle the nonlinear volatility of EP. In this study, we have discussed the GA-GRU model, where the gated recurrent unit (GRU) is used for sequential time series forecasting of EP, while the genetic algorithm is used to tune the hyperparameters of the GRU model. To validate the effectiveness of the proposed model, we conducted a comparative analysis with the benchmark models, and the proposed study states that GA-GRU outperforms for short-term price forecasting.