Improving Robustness of LSTM Model for Stock Price Prediction
I am currently working on a Long Short-Term Memory (LSTM) model for predicting stock prices. My model takes into account the fact that there are non-trading minutes with no data. I have also incorporated sentiment analysis into my model.
Total params: 0 , on doing model.summary() keras
model = Sequential() model.add(Embedding(283, 100, input_length=56)) model.add(LSTM(150)) model.add(LSTM(150)) model.add(Dense(283, activation=’softmax’)) model.compile(loss=’categorical_crossentropy’, optimizer=’adam’,metrics=[‘accuracy’]) model.summary() Tensorflow Version: 2.16.1, Keras Version: 3.3.3 , Device – M3 pro macbook I tried to build a LSTM model for text generation using a dummy dataset (had 282 unique words, checked with tokenizer), expected non zero params but the output is 0 […]