Comparative Performance of LSTM and GRU in Forecasting NVIDIA Stock Prices: Insights from the Digital Financial Market

Main Article Content

👤 Richard Berlien
🏢 Universitas Murni Teguh, Indonesia

The rapid evolution of artificial intelligence and digital technologies has transformed financial forecasting, enabling more accurate and data-driven decision-making in digital markets. This study investigates the comparative performance of two deep learning architectures, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), in predicting NVIDIA stock prices as a case study of digital financial market behavior. Historical daily stock data from 2018 to 2026 were analyzed using key financial indicators, including opening, closing, high, low, and trading volume. Both models were developed using a time-series forecasting framework with data normalization, a 60-day sliding window, and evaluation through Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The results show that both LSTM and GRU models effectively captured temporal dependencies and nonlinear price movements, with the GRU model achieving superior accuracy (RMSE 3.5801, MAE 2.4518) and faster convergence compared to LSTM (RMSE 4.5841, MAE 3.1153). The GRU model also demonstrated higher adaptability to short-term fluctuations, while LSTM exhibited stronger long-term trend stability. These findings confirm that deep learning architectures can significantly enhance stock price prediction accuracy and offer valuable insights for digital market analysis. The study contributes to the growing application of AI in finance by highlighting the potential of GRU-based forecasting models for real-time prediction and decision support in dynamic digital trading environments.

Berlien, R. (2026). Comparative Performance of LSTM and GRU in Forecasting NVIDIA Stock Prices: Insights from the Digital Financial Market. Fintech Innovation Journal, 2(4), 280–193. https://doi.org/10.63913/ftij.v2i4.40

Article Details

Section
Articles

Similar Articles

<< < 1 2 3 4 

You may also start an advanced similarity search for this article.