LSTM Layer accuracy is 0

Question

hello everyone

i have network that gets 9 days and predict 10s day price using lstm

my x shape is (240,9,1) and y shape is (240,1,1)

the problem is accuracy is 0

can anyone help

here is my code

 

model = Sequential()

model.add(LSTM(units=50, input_shape=(train_x.shape[0], 1), return_sequences=True))

model.add(Dropout(0.2))

model.add(LSTM(units=50, return_sequences=True))

model.add(Dropout(0.2))

model.add(LSTM(units=50, return_sequences=True))

model.add(Dropout(0.2))

model.add(LSTM(units=25))

model.add(Dropout(0.2))

model.add(Dense(units=1))

model.compile(optimizer='adam', loss=tf.keras.losses.MeanSquaredError(), metrics=['accuracy'])

print(model.summary())

model.fit(train_x, train_y, epochs=100, batch_size=64)

 

and also extra questions

what is batch_size and units of lstm and droupout

thanks for help