I’m doing a team project related to food recommendation, my task is to predict calories based on input of protein and sodium.

The data looks like this:
enter image description here

I tried various machine learning model at first but the accuracy is so low (XGboost r square is 25%), when I removed outliers (R square is 37%). I then tried using neural network regression and got the results below:

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.callbacks import EarlyStopping
import matplotlib.pyplot as plt

# Step 2: Split the data into features and target
X = df_clean[['protein', 'sodium']]
y = df_clean['calories']

# Step 3: Split the data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Step 4: Normalize the data
scaler = MinMaxScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Step 5: Define the neural network model with additional layers and dropout
model = Sequential()
model.add(Dense(128, input_dim=2, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1))  # Output layer for regression

# Step 6: Compile the model
model.compile(optimizer='adam', loss='mse', metrics=['mae'])

# Step 7: Define early stopping callback
early_stopping = EarlyStopping(monitor='val_loss', patience=10, restore_best_weights=True)

# Step 8: Train the model
epochs = 20
batch_size = 32
history = model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_data=(X_test, y_test), verbose=1, callbacks=[early_stopping])

# Step 9: Evaluate the model on the test set
test_loss, test_mae = model.evaluate(X_test, y_test, verbose=0)
print(f'Test loss: {test_loss:.4f}, Test MAE: {test_mae:.4f}')

# Step 10: Make predictions on the test set
y_pred = model.predict(X_test)

# Step 11: Visualize the results
plt.figure(figsize=(8, 6))
plt.scatter(y_test, y_pred)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=3)
plt.xlabel('Actual Calories')
plt.ylabel('Predicted Calories')
plt.title('Neural Network Regression')
plt.show()

# Step 12: Plot training & validation loss values
plt.figure(figsize=(10, 6))
plt.plot(history.history['loss'], label='Training Loss')
plt.plot(history.history['val_loss'], label='Validation Loss')
plt.title('Model Loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(loc='upper right')
plt.show()

enter image description here
enter image description here

Could anyone suggest the approach for this problem, I’m new to this field so any help is really appreciated.