LSTM Prediction with Low Accuracy

Question

I used an LSTM model for this prediction. But the accuracy is very low. How could I fix this issue?

from keras.layers import Dropout
from keras.layers import Bidirectional
model=Sequential()
model.add(LSTM(50,activation='relu',return_sequences=True,input_shape=(look_back,1)))
model.add(LSTM(50, activation='relu', return_sequences=True))
model.add(LSTM(50, activation='relu', return_sequences=True))
model.add(LSTM(50, activation='sigmoid', return_sequences=False))
model.add(Dense(50))
model.add(Dense(50))
model.add(Dropout(0.2))
model.add(Dense(1))
model.compile(optimizer='adam',loss='mean_squared_error',metrics=['accuracy'])
model.optimizer.learning_rate = 0.0001

Test and Train Prediction Plot

Epochs

Answer 1

your structure seems correct. try my code.

from keras.models import Sequential from keras.layers import LSTM, Dense,Dropout, Bidirectional

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
#from keras.utils import plot_model
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from keras.layers.merge import Concatenate
import matplotlib.gridspec as gridspec

import random
import scikitplot as skplot
import datetime
from datetime import date
from pandas_datareader import data as pdr

def create_dataset(dataset, look_back=3):
    dataX, dataY = [], []
    for i in range(len(dataset)-look_back-1):
        a = dataset[i:(i+look_back)]
        dataX.append(a)
        dataY.append(dataset[i + look_back])
    return np.array(dataX), np.array(dataY)

COLUMNS=['your_data_column']
dataset=df[COLUMNS]
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(np.array(dataset).reshape(-1,1))

train_size = int(len(dataset) * 0.60)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size], dataset[train_size:len(dataset)]

look_back=3
trainX=[]
testX=[]
y_train=[]
n_future = 1
features=2
timeSteps=4

model = Sequential()

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

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= 50))
model.add(Dropout(0.2))
model.add(Dense(units = n_future))

model.compile(optimizer="adam", loss="mean_squared_error", metrics=["acc"])