AI Food Waste
Management: ML vs
Deep Learning
A complete walkthrough of the AI-Powered Food Waste Management dataset from Kaggle. Build 5 scikit-learn models and 2 TensorFlow neural networks to predict waste amounts (regression) and classify high vs. low waste (classification). Every line of code is explained for beginners — with copy buttons on every block.
# AI Food Waste Management — KaggleHub import kagglehub from kagglehub import KaggleDatasetAdapter df = kagglehub.load_dataset( KaggleDatasetAdapter.PANDAS, "vinay24baghira/ai-food-waste...", file_path, ) print("First 5 records:", df.head())
Six steps from raw CSV
to model verdict.
The complete pipeline for the AI Food Waste Management machine learning project. Click any step to jump straight to its code and beginner-friendly explanation.
Data Loading with KaggleHub
Stream the food waste dataset straight into a pandas DataFrame. Check shape, head, info, and describe. No manual download needed.
Exploratory Data Analysis
Histograms + KDE for waste amounts and key features. Scatter plots of features vs. waste. Correlation heatmap of all numeric features.
Preprocessing & Encoding
Handle missing values, label encode categorical features, auto-detect the waste target column, create high vs. low waste classification target, scale features without leakage.
Machine Learning Models
Train Linear/Logistic Regression, Random Forest, Gradient Boosting, SVM and KNN — to predict waste amount (regression) and classify high vs. low waste (classification).
Deep Learning Models
Two 4-layer TensorFlow networks (128→64→32→1) with ReLU, BatchNorm, Dropout, EarlyStopping and ReduceLROnPlateau — one regression, one classification.
ML vs DL Comparison
Side-by-side leaderboard: R², RMSE, MAE for regression; accuracy, precision, recall, F1 for classification. The verdict on tree ensembles vs neural networks on food waste data.
Load the dataset with KaggleHub.
Stream the food waste dataset straight into a pandas DataFrame — no manual download needed.
What is this dataset? The AI-Powered Food Waste Management dataset contains data about food items, their quantities, waste amounts, storage conditions, and costs. It’s designed for building AI models that predict and reduce food waste — a real-world sustainability problem. Each row is one food item or waste event.
What is KaggleHub? Kaggle is a website where people share datasets for machine learning. KaggleHub is a Python library that lets you load those datasets directly into your code with one line — no manual downloading.
What is a DataFrame? A pandas DataFrame is like an Excel spreadsheet inside Python. It has rows (one per food item/waste event) and columns (food type, quantity, waste amount, cost, etc.). The variable df we create here holds all the data.
Why check shape, head(), info(), describe()?
df.shape→ How many rows and columns?df.head()→ Show the first 5 rows so you can see column names and sample valuesdf.info()→ What type of data is in each column? (text vs. numbers) How many missing values?df.describe()→ Basic statistics: mean waste amount, mean cost, min, max
Important: The file_path is the CSV filename inside the dataset. Visit the Kaggle dataset page → Files tab to find the exact filename. Also, check df.head() to identify the exact column name for waste amount — it might be called waste_amount, waste_kg, quantity_wasted, or something else. The code in Step 3 auto-detects it.
# Install dependencies as needed:
# pip install kagglehub[pandas-datasets] pandas numpy matplotlib seaborn scikit-learn tensorflow
import kagglehub
from kagglehub import KaggleDatasetAdapter
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
# Set the path to the file you'd like to load
# Check the Kaggle dataset page → Files tab for the exact filename
file_path = "food_waste_data.csv"
# Load the latest version
df = kagglehub.load_dataset(
KaggleDatasetAdapter.PANDAS,
"vinay24baghira/ai-powered-food-waste-management-dataset-v1",
file_path,
)
print("Dataset shape:", df.shape)
print("First 5 records:")
print(df.head())
print(df.info())
print(df.describe())kagglehub loads the dataset, pandas handles data tables, numpy handles math, matplotlib and seaborn create charts."vinay24baghira/ai-powered-food-waste-management-dataset-v1", (3) load the file we specified. Result stored in df.object = text (categorical), int64/float64 = numbers. Also shows missing values.Exploratory Data Analysis in seaborn.
Before any model touches the data, we visualize distributions, plot features vs. waste amounts, and check correlations.
What is EDA? Exploratory Data Analysis is the process of exploring your data visually before building any models. It’s like inspecting your pantry before planning meals — you want to know what you’re working with.
What is a histogram? A histogram counts how many food items fall into each waste range. For example, how many items wasted 0–5 kg, how many 5–10 kg, etc. The KDE curve (smooth line on top) estimates the overall shape.
What is a scatter plot? A scatter plot places each food item as a dot, with one feature on the x-axis and waste amount on the y-axis. Plotting Quantity vs. Waste Amount reveals whether larger quantities lead to more waste — the core question of this dataset.
What is correlation? Correlation measures how strongly two variables move together, from -1 to +1. If quantity and waste correlate positively (above 0.5), it means larger quantities tend to produce more waste. The heatmap shows all pairwise correlations at once.
Why does EDA matter? The scatter plots reveal whether the relationship between food features and waste is linear (a clear trend) or noisy. This tells you whether to expect high or low R² from your models. Also, the waste distribution histogram shows if most items have low waste with a few high-waste outliers (right-skewed).
2.1 · Missing values, target detection & distributions
# Check for missing values
print("Missing values:\n", df.isnull().sum())
print("\nDuplicates:", df.duplicated().sum())
categorical_cols = df.select_dtypes(include=['object']).columns
numeric_cols = df.select_dtypes(include=[np.number]).columns
print(f"\nCategorical columns: {list(categorical_cols)}")
print(f"Numeric columns: {list(numeric_cols)}")
# Auto-detect the waste/target column
target_col = None
for candidate in ['waste_amount', 'waste_kg', 'waste_quantity',
'waste', 'food_waste', 'quantity_wasted',
'waste_quantity_kg', 'waste_generated', 'amount_wasted']:
if candidate in df.columns.str.lower().tolist():
target_col = df.columns[df.columns.str.lower() == candidate][0]
break
if target_col is None:
target_col = numeric_cols[-1]
print(f"Warning: Using '{target_col}' as target.")
print(f"Waste target column: '{target_col}'")
# Distributions of key numeric features
key_cols = list(numeric_cols[:4])
if len(key_cols) > 0:
fig, axes = plt.subplots(1, len(key_cols), figsize=(5*len(key_cols), 5))
colors = ['#4C72B0', '#55A868', '#C44E52', '#8172B2']
for ax, col, color in zip(axes, key_cols, colors):
sns.histplot(df[col], kde=True, color=color, ax=ax)
ax.axvline(df[col].mean(), color='black', linestyle='--', label=f"Mean: {df[col].mean():.1f}")
ax.set_title(f'Distribution of {col}')
ax.legend()
plt.tight_layout()
plt.show()waste_amount, waste_kg, quantity_wasted, etc.). If none match, it falls back to the last numeric column. Always verify the detected column name in the output.2.2 · Scatter plots & correlation heatmap
# Scatter: first numeric feature vs target
if len(numeric_cols) >= 2:
feat = numeric_cols[0]
plt.figure(figsize=(10, 6))
sns.scatterplot(data=df, x=feat, y=target_col, s=60, color='#4C72B0')
plt.title(f'{feat} vs {target_col}')
plt.show()
# Correlation heatmap
plt.figure(figsize=(10, 8))
sns.heatmap(df[numeric_cols].corr(), annot=True, cmap='coolwarm', fmt='.2f',
square=True, linewidths=0.5)
plt.title('Correlation Between Numeric Features')
plt.show()The scatter plot of quantity vs. waste amount is the key visualization. If you see an upward trend, it confirms that larger quantities tend to produce more waste. The correlation heatmap shows all pairwise relationships — look for strong correlations (above 0.5 or below -0.5) between features and the waste target.
Encode, engineer, scale — without leakage.
Handle missing values, encode categorical features, create a high vs. low waste target, and scale features.
Why do we need preprocessing? Machine learning models only understand numbers. If the dataset has text columns (like food type or storage method), we need to convert them to numbers. Also, some rows might have missing values that need to be handled.
Handling missing values: We use dropna() to remove rows with missing data. If the dataset has many missing values, you might want to fill them with the mean or median instead.
Label encoding for categorical features: We use LabelEncoder to convert text columns (like food type, storage type) to numbers. Example: Cold=0, Room=1, Frozen=2.
What is a target variable? For regression, the target is the waste amount column (kg or quantity). For classification, we create a high_waste target: 1 if waste ≥ median, 0 if below. This splits food items into “high waste” and “low waste” categories.
What is train/test split? We divide data into 80% for training and 20% for testing. random_state=42 makes the split reproducible.
What is scaling? Standardization rescales every feature so mean=0, std=1. This matters because quantity might range from 1–500 while temperature ranges from -5–30 — without scaling, features with larger ranges would dominate.
What is data leakage? When information from the test set accidentally influences training. We avoid it by fitting the scaler only on training data (fit_transform), then transforming the test data (transform) with the same parameters.
from sklearn.preprocessing import LabelEncoder, StandardScaler
from sklearn.model_selection import train_test_split
data = df.copy()
data = data.dropna()
# 3.1 Encode categorical features
le = LabelEncoder()
for col in categorical_cols:
data[col] = le.fit_transform(data[col].astype(str))
# 3.2 Create classification target
target_median = data[target_col].median()
data['high_waste'] = (data[target_col] >= target_median).astype(int)
# 3.3 Define features (X) and targets (y)
X_reg = data.drop(columns=[target_col, 'high_waste'])
y_reg = data[target_col]
X_clf = data.drop(columns=[target_col, 'high_waste'])
y_clf = data['high_waste']
# 3.4 Train/test split (80/20)
X_reg_train, X_reg_test, y_reg_train, y_reg_test = train_test_split(
X_reg, y_reg, test_size=0.2, random_state=42)
X_clf_train, X_clf_test, y_clf_train, y_clf_test = train_test_split(
X_clf, y_clf, test_size=0.2, random_state=42)
# 3.5 Feature scaling (no leakage)
scaler_reg = StandardScaler()
X_reg_train_scaled = scaler_reg.fit_transform(X_reg_train)
X_reg_test_scaled = scaler_reg.transform(X_reg_test)
scaler_clf = StandardScaler()
X_clf_train_scaled = scaler_clf.fit_transform(X_clf_train)
X_clf_test_scaled = scaler_clf.transform(X_clf_test)
print(f"Target median: {target_median}")
print(f"Train shape: {X_reg_train.shape}, Test shape: {X_reg_test.shape}")
print(f"Class distribution:\n{y_clf.value_counts(normalize=True)}")file_path from Step 1 and the target_col from Step 2 must be correct. Visit the Kaggle dataset page to verify the CSV filename, and check df.head() output to confirm the exact column name for waste amount.random_state=42 = reproducible.fit_transform on train (learns mean/std), transform on test (applies same parameters). No data leakage.Five scikit-learn models,
two tasks.
For each task — predict waste amount (regression) and classify high vs. low waste (classification) — we train five models.
What is supervised learning? Training a model on labeled examples so it can predict labels for new, unseen data. Two types:
- Regression: predict a continuous number — e.g., “this food item will have 15 kg of waste”
- Classification: predict a category — e.g., “this item is high waste (1) or low waste (0)”
The five models, explained simply:
- Linear Regression: draws the best-fitting straight line through the data. Simple, fast baseline.
- Logistic Regression: for classification — estimates the probability of being a high-waste item.
- Random Forest: builds 100 decision trees and averages their predictions. “Wisdom of the crowd.”
- Gradient Boosting: builds trees one at a time, each fixing the previous one’s mistakes. Often the strongest on tabular data.
- SVM: finds the best boundary between classes. Good for small datasets, sensitive to scaling.
- KNN: for a new food item, finds the 5 most similar items and averages their waste amounts. Simple but scaling-sensitive.
Regression metrics:
- RMSE: “off by X kg on average” (in waste amount units).
- R²: variance explained. 1.0 is perfect, 0 = no better than guessing the mean.
Classification metrics:
- Accuracy: fraction of all predictions that were correct.
- Precision: of all predicted “high waste” items, how many actually were?
- Recall: of all actual “high waste” items, how many did we catch?
- F1: harmonic mean of precision and recall.
4.1 · Regression — Predict Waste Amount
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor
from sklearn.svm import SVR
from sklearn.neighbors import KNeighborsRegressor
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
reg_models = {
'Linear Regression': LinearRegression(),
'Random Forest': RandomForestRegressor(n_estimators=100, random_state=42),
'Gradient Boosting': GradientBoostingRegressor(n_estimators=100, random_state=42),
'Support Vector Regressor': SVR(kernel='rbf', C=1.0),
'K-Nearest Neighbors': KNeighborsRegressor(n_neighbors=5),
}
reg_results = []
for name, model in reg_models.items():
model.fit(X_reg_train_scaled, y_reg_train)
y_pred = model.predict(X_reg_test_scaled)
mse = mean_squared_error(y_reg_test, y_pred)
rmse = np.sqrt(mse)
mae = mean_absolute_error(y_reg_test, y_pred)
r2 = r2_score(y_reg_test, y_pred)
reg_results.append({'Model':name,'MSE':round(mse,2),'RMSE':round(rmse,2),'MAE':round(mae,2),'R²':round(r2,4)})
reg_results_df = pd.DataFrame(reg_results).sort_values('R²', ascending=False)
print(reg_results_df.to_string(index=False))4.2 · Classification — Predict High vs. Low Waste
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix
clf_models = {
'Logistic Regression': LogisticRegression(random_state=42, max_iter=1000),
'Random Forest': RandomForestClassifier(n_estimators=100, random_state=42),
'Gradient Boosting': GradientBoostingClassifier(n_estimators=100, random_state=42),
'Support Vector Classifier': SVC(kernel='rbf', random_state=42, probability=True),
'K-Nearest Neighbors': KNeighborsClassifier(n_neighbors=5),
}
clf_results = []
for name, model in clf_models.items():
model.fit(X_clf_train_scaled, y_clf_train)
y_pred = model.predict(X_clf_test_scaled)
clf_results.append({'Model':name,'Accuracy':round(accuracy_score(y_clf_test,y_pred),4),'Precision':round(precision_score(y_clf_test,y_pred),4),'Recall':round(recall_score(y_clf_test,y_pred),4),'F1 Score':round(f1_score(y_clf_test,y_pred),4)})
clf_results_df = pd.DataFrame(clf_results).sort_values('Accuracy', ascending=False)
print(clf_results_df.to_string(index=False))
best_clf = clf_models[clf_results_df.iloc[0]['Model']]
y_pred_best = best_clf.predict(X_clf_test_scaled)
cm = confusion_matrix(y_clf_test, y_pred_best)
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=['Low','High'], yticklabels=['Low','High'])
plt.show()Two TensorFlow neural networks
with modern regularization.
Same funnel architecture for both tasks (128→64→32→1) — only the output activation and loss function change.
What is a neural network? A stack of layers, each containing “neurons” (math units). Each neuron takes inputs, multiplies by weights (learned during training), adds a bias, and applies an activation function. “Deep” = many layers.
The architecture, explained:
Dense(128): 128 neurons, each connected to every neuron in the previous layer. First layer takes our features.Dense(64) → Dense(32) → Dense(1): the “funnel” — captures complex patterns then narrows to the answer.ReLU: if input is negative, output 0; if positive, output as-is. Lets the network learn non-linear patterns.
Regularization — preventing overfitting:
BatchNormalization: normalizes layer outputs during training. Stabilizes learning.Dropout(0.3): randomly disables 30% of neurons each step. Forces the network to learn redundant representations.
Training configuration:
Adam: adjusts learning rate automatically. The default choice for most projects.MSE loss(regression): penalizes large errors more than small ones.Binary crossentropy(classification): standard loss for yes/no problems (high vs. low waste).Epoch: one full pass through training data. We train for up to 200.Batch size (32): process 32 food items at a time before updating weights.Validation split (0.2): 20% of training data held out to monitor overfitting.
Callbacks — automatic training controls:
EarlyStopping: if val loss doesn’t improve for 20 epochs, stop.restore_best_weights=Truerolls back to the best epoch.ReduceLROnPlateau: when val loss plateaus, halve the learning rate.
Regression vs classification — the only difference:
- Regression: final layer = LINEAR activation (outputs any number — the predicted waste amount).
- Classification: final layer = SIGMOID activation (outputs 0–1 = probability of “high waste”). Threshold at 0.5.
5.1 · DL Regression — Predict Waste Amount
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, BatchNormalization
from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau
tf.random.set_seed(42)
np.random.seed(42)
def build_regression_model(input_dim):
model = Sequential([
Dense(128, activation='relu', input_shape=(input_dim,)),
BatchNormalization(), Dropout(0.3),
Dense(64, activation='relu'), BatchNormalization(), Dropout(0.2),
Dense(32, activation='relu'), Dropout(0.1),
Dense(1, activation='linear')
])
model.compile(optimizer='adam', loss='mse', metrics=['mae'])
return model
dl_reg_model = build_regression_model(X_reg_train_scaled.shape[1])
early_stop = EarlyStopping(monitor='val_loss', patience=20, restore_best_weights=True, verbose=1)
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=10, min_lr=1e-6, verbose=1)
history_reg = dl_reg_model.fit(X_reg_train_scaled, y_reg_train, validation_split=0.2, epochs=200, batch_size=32, callbacks=[early_stop, reduce_lr], verbose=1)
dl_reg_pred = dl_reg_model.predict(X_reg_test_scaled).flatten()
dl_reg_rmse = np.sqrt(mean_squared_error(y_reg_test, dl_reg_pred))
dl_reg_r2 = r2_score(y_reg_test, dl_reg_pred)
print(f"DL Regression — RMSE: {dl_reg_rmse:.2f}, R²: {dl_reg_r2:.4f}")5.2 · DL Classification — Predict High vs. Low Waste
tf.random.set_seed(42)
np.random.seed(42)
def build_classification_model(input_dim):
model = Sequential([
Dense(128, activation='relu', input_shape=(input_dim,)),
BatchNormalization(), Dropout(0.3),
Dense(64, activation='relu'), BatchNormalization(), Dropout(0.2),
Dense(32, activation='relu'), Dropout(0.1),
# KEY DIFFERENCE: sigmoid + binary_crossentropy
Dense(1, activation='sigmoid')
])
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
return model
dl_clf_model = build_classification_model(X_clf_train_scaled.shape[1])
early_stop_clf = EarlyStopping(monitor='val_loss', patience=20, restore_best_weights=True, verbose=1)
reduce_lr_clf = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=10, min_lr=1e-6, verbose=1)
history_clf = dl_clf_model.fit(X_clf_train_scaled, y_clf_train, validation_split=0.2, epochs=200, batch_size=32, callbacks=[early_stop_clf, reduce_lr_clf], verbose=1)
dl_clf_prob = dl_clf_model.predict(X_clf_test_scaled).flatten()
dl_clf_pred = (dl_clf_prob >= 0.5).astype(int)
dl_clf_acc = accuracy_score(y_clf_test, dl_clf_pred)
dl_clf_f1 = f1_score(y_clf_test, dl_clf_pred)
print(f"DL Classification — Accuracy: {dl_clf_acc:.4f}, F1: {dl_clf_f1:.4f}")The final leaderboard.
Concatenate the ML results with the DL metrics and sort.
How to read the results table:
- For regression: higher R² is better. Lower RMSE is better (in waste units — RMSE of 5 means “off by ~5 kg on average”).
- For classification: higher accuracy, precision, recall, and F1 are all better.
The pattern you’ll see: On this food waste dataset, Gradient Boosting and Random Forest typically match or beat the neural network. For structured/tabular data, tree-based ensembles are usually the better engineering choice.
Key lesson: The real value of this project isn’t just prediction — it’s identifying which factors drive food waste. Feature importance from Random Forest can reveal that storage temperature, food type, or quantity are the biggest drivers, enabling targeted waste reduction strategies.
# Regression comparison
combined_reg = pd.concat([reg_results_df, pd.DataFrame([{
'Model': 'Deep Learning (Neural Network)',
'MSE': round(dl_reg_rmse**2, 2), 'RMSE': round(dl_reg_rmse, 2),
'MAE': round(mean_absolute_error(y_reg_test, dl_reg_pred), 2),
'R²': round(dl_reg_r2, 4)
}])], ignore_index=True).sort_values('R²', ascending=False)
print(combined_reg.to_string(index=False))
# Classification comparison
combined_clf = pd.concat([clf_results_df, pd.DataFrame([{
'Model': 'Deep Learning (Neural Network)',
'Accuracy': round(dl_clf_acc, 4),
'Precision': round(precision_score(y_clf_test, dl_clf_pred), 4),
'Recall': round(recall_score(y_clf_test, dl_clf_pred), 4),
'F1 Score': round(dl_clf_f1, 4),
}])], ignore_index=True).sort_values('Accuracy', ascending=False)
print(combined_clf.to_string(index=False))What the project
actually tells us.
Six findings from running the full pipeline on the AI Food Waste Management dataset.
// quantity ↔ waste positive · storage conditions matterQuantity positively correlates with waste
Food items with larger quantities tend to produce more waste — the scatter plot typically shows an upward trend.
Storage conditions affect waste levels
Cold storage may correlate with lower waste, while room temperature storage may correlate with higher waste. The heatmap reveals these patterns.
Waste distribution is typically right-skewed
Most food items have low waste, with a few high-waste outliers pulling the mean above the median. This is common in real-world waste data.
Tree ensembles match or beat DL on waste data
Gradient Boosting and Random Forest typically outperform the neural network on this structured dataset. Deep learning isn’t always the answer — for tabular data, tree-based ensembles win.
Feature importance reveals actionable insights
Random Forest’s feature importance can rank food type, quantity, storage method, and temperature by their impact on waste — enabling targeted waste reduction strategies.
The real value is sustainability, not prediction
The goal isn’t to predict waste perfectly — it’s to understand what drives waste and take action. A model that explains 40-60% of the variance is genuinely useful for reducing food waste and saving money.
Frequently Asked Questions
What is the AI-Powered Food Waste Management dataset? +
The AI-Powered Food Waste Management dataset on Kaggle contains data about food items, quantities, waste amounts, storage conditions, and costs — designed for building AI models that predict and reduce food waste.
Can machine learning predict food waste? +
Yes. By training a model on food type, quantity, storage conditions, and other features, ML learns the relationship between these factors and waste amounts, enabling prediction for new food items.
Is deep learning better than ML for food waste data? +
Not necessarily. On this structured dataset, traditional ML models like Gradient Boosting typically match or outperform a 4-layer neural network. Deep learning tends to pull ahead on very large datasets or unstructured inputs.
Why is the R² not higher? +
Because food waste is influenced by many factors not in the dataset — human behavior, supply chain issues, weather, equipment failures. A model that explains 30-60% of the variance is genuinely useful for waste reduction.
Run the project
yourself.
Grab the AI-Powered Food Waste Management dataset from Kaggle, install the stack with one pip command, and run every cell end-to-end. Or click “Copy Full Project Code” at the top of this page.