riqbal-k

riqbal-k

riqbal-k

riqbal-k

riqbal-k

riqbal-k

riqbal-k

#calculate mean squre error
mse <- history$metrics$val_loss[length(history$metrics$val_loss)]
mse <- round(mse, 7)
mse

riqbal-k

# Calculate the mean and standard deviation of the original dataset
mean_return <- mean(return_log)
sd_return <- sd(return_log)
# Rescale the predicted and original values
y_train_pred_rescaled <- y_train_pred_returns * sd_return + mean_return
y_test_pred_rescaled <- y_test_pred_returns * sd_return + mean_return
y_train_rescaled<-y_train * sd_return + mean_return
y_test_rescaled<-y_test * sd_return + mean_return
# Shift the predicted values to start from where the training data predictions end
shift <- length(y_train_pred_rescaled)

riqbal-k

# Calculate the predicted returns using the LSTM model
y_train_pred_returns <- model %>% predict(x_train)
y_test_pred_returns <- model %>% predict(x_test)
# Set up the layout of the plots
par(mfrow = c(1,2))
options(repr.plot.width=15, repr.plot.height=8)
# Plot the training and predicted values
plot(y_train, type = "l", col = "green",main="Apple daily Log Returns", xlab = "Day", ylab = "Returns",lwd =3)
lines(y_train_pred_returns, col = "red")
legend(x = "topleft", legend = c("Train", "Train Predictions"), col = c("green", "red"), lwd = 3)

riqbal-k

split_data <- function(stock, lookback) {
  data_raw <- as.matrix(stock) # convert to matrix
  data <- array(dim = c(0, lookback, ncol(data_raw)))
  
  # create all possible sequences of length lookback
  for (index in 1:(nrow(data_raw) - lookback)) {
    data <- rbind(data, data_raw[index:(index + lookback - 1), ])
  }
  
  test_set_size <- round(0.2 * nrow(data))