Stock Price Prediction using Encoder-Decoder Model: Evaluation and Analysis
The aim of this project is to predict stock prices using an Encoder-Decoder model. The model consists of an EncoderRNN and a DecoderRNN, which are trained on historical stock data.
The trained model is then evaluated on a test dataset to assess its performance. Additionally, several evaluation metrics are computed, including the mean squared error (MSE) loss, profitability performance (PP), and cumulative returns (CDR). Furthermore, the correlation between the predicted and true closing prices relative to the opening prices is ana…