1. Abstract

Price prediction is one of the most common applications of machine learning in real-world scenarios. This project focuses on predicting the price of a pizza based on various parameters such as the number of toppings, diameter of the pizza, presence of ingredients like tomatoes or extra cheese, and other related attributes.

The dataset used in this project contains multiple features that influence the pricing of pizzas. By analyzing these attributes, machine learning models can identify patterns and relationships between pizza characteristics and their prices.

In this project, different Machine Learning algorithms such as Linear Regression, XGBoost, CatBoost, and other regression models are used to build predictive models. Additionally, Automated Machine Learning (AutoML) techniques are applied using the EvalML library, which automatically compares multiple machine learning models and identifies the best performing pipeline.

The project includes several stages such as data analysis, data preprocessing, feature engineering, model building, and model evaluation. The main goal is to develop a system that can accurately estimate pizza prices based on the given parameters.

This project helps in understanding the workflow of machine learning projects and demonstrates how AutoML can simplify the process of selecting the best model for prediction tasks.

2. Objectives

The main objectives of this project are:

1. To understand the concept of price prediction using machine learning techniques.
2. To analyze the dataset and identify relationships between pizza features and price.
3. To perform data preprocessing and feature engineering to prepare the dataset for machine learning models.
4. To build predictive models using machine learning regression algorithms.
5. To evaluate the performance of different machine learning models.
6. To implement Automated Machine Learning using EvalML to simplify model selection.
7. To compare traditional machine learning models with AutoML generated models.
8. To develop a system capable of predicting pizza prices based on different input parameters.

3. Existing System

In traditional systems, pizza prices are generally determined manually by restaurant owners based on ingredient costs, size, and preparation expenses.

However, these traditional methods have several limitations:

1. Price estimation is done manually without data analysis.
2. It is difficult to analyze the effect of multiple features on price.
3. Manual systems cannot predict prices automatically.
4. There is no intelligent system to estimate price based on input features.
5. Decision making becomes difficult without analytical models.

Therefore, a machine learning-based system can help automatically estimate pizza prices using data-driven approaches.

4. Proposed System

The proposed system uses Machine Learning and Automated Machine Learning techniques to predict pizza prices based on various features.

In this system:

1. A dataset containing pizza attributes such as toppings, ingredients, and size is used.
2. Data preprocessing techniques are applied to clean and prepare the dataset.
3. Machine learning algorithms such as Linear Regression, XGBoost, and CatBoost are trained to build prediction models.
4. EvalML AutoML is used to automatically compare different machine learning models and select the best pipeline.
5. The best-performing model is used to predict the price of pizza based on given parameters.

This automated approach improves prediction accuracy and simplifies the machine learning workflow.

5. Implementation Procedure

The implementation of this project is carried out in the following steps:

Step 1: Data Collection

1. Collect the pizza dataset containing features affecting pizza price.
2. The dataset includes attributes such as:
3. Diameter of pizza
4. Number of toppings
5. Ingredients like tomatoes or cheese
6. Pizza price

Step 2: Data Analysis

1. Analyze the dataset to understand relationships between pizza attributes and price.
2. Visualize the distribution of features using graphs and charts.

Step 3: Data Preprocessing

1. Handle missing values if present.
2. Perform encoding techniques for categorical features.
3. Normalize or scale data when necessary.

Step 4: Model Building

1. Train machine learning models such as:
2. Linear Regression
3. XGBoost
4. CatBoost
5. Other regression algorithms

Step 5: Automated Machine Learning

1. Apply EvalML AutoML to automate model selection.
2. EvalML automatically trains and compares different models.

Step 6: Model Evaluation

1. Evaluate models using performance metrics such as:
2. Mean Squared Error (MSE)
3. Root Mean Squared Error (RMSE)
4. R² Score

Step 7: Best Model Selection

1. Compare the results of all models.
2. Select the best performing model for pizza price prediction.

6. Software Requirements

The software used in this project includes:

Operating System

1. Windows / Linux / macOS

Programming Language

1. Python 3.x

Development Environment

1. Jupyter Notebook
2. Google Colab
3. VS Code

Libraries and Frameworks

1. EvalML (AutoML)
2. Scikit-learn
3. NumPy
4. Pandas
5. Matplotlib
6. Seaborn

Web Browser

1. Chrome / Firefox

7. Hardware Requirements

The hardware required for this project includes:

1. Processor: Intel i3 / i5 or higher
2. RAM: Minimum 4 GB (8 GB recommended)
3. Storage: Minimum 128 GB free space
4. System: Laptop / Desktop Computer
5. Internet Connection

8. Advantages of the Project

1. Automates the process of pizza price prediction.
2. Demonstrates the use of machine learning in regression problems.
3. Helps learners understand the complete ML workflow.
4. Uses AutoML to simplify model selection.
5. Reduces the need for manual model comparison.
6. Improves prediction accuracy through data analysis.
7. Useful for educational and skill-building purposes.
8. Can be extended to real-world food pricing prediction systems.