1. Abstract

This project focuses on predicting the cost of art sculptures using machine learning techniques. The price of a sculpture depends on several factors such as its size, shape, shipping details, artist information, and other characteristics related to the artwork and buyers.

In this project, a dataset containing information about people who purchased sculptures from different artists is used. The dataset includes details about the sculptures and buyers. Since the dataset is not well-organized and contains noisy data, only a relevant subset of the dataset is selected for analysis. The dataset includes information from nearly 3000 artists who were selling sculptures, including sculptures of famous personalities.

Data preprocessing techniques such as cleaning the dataset and removing outliers are applied to improve the accuracy of the model. Outlier removal is particularly important in this project because unusual values in the dataset can significantly affect the prediction performance.

A Random Forest Regressor machine learning model is trained using the cleaned dataset to predict the cost of a sculpture. After training the model, a web application is developed using the Django framework, where the trained model is integrated to provide predictions.

Finally, the Django web application is deployed on the Heroku cloud platform using GitHub integration, allowing users to access the prediction system online. This project demonstrates the application of machine learning, data preprocessing, and web deployment in predicting the price of artworks.

2. Objectives

The main objectives of this project are:

1. To understand the concept of price prediction using machine learning.
2. To analyze a dataset related to art sculptures and buyers.
3. To clean and preprocess the dataset.
4. To understand the importance of outlier removal in machine learning models.
5. To develop a regression model using the Random Forest Regressor algorithm.
6. To train and evaluate the model for predicting sculpture prices.
7. To develop a web application using the Django framework.
8. To deploy the application on Heroku using GitHub integration.

3. Existing System

In the existing system, the pricing of sculptures is mainly determined by artists, galleries, or art experts based on their experience and market demand.

This traditional system has several limitations:

1. Price estimation depends on manual evaluation.
2. The pricing process may vary depending on the seller or market trends.
3. Large datasets related to artworks are difficult to analyze manually.
4. The dataset may contain irregular or inconsistent data.
5. There is no automated system to predict sculpture prices using historical data.

Because of these limitations, traditional pricing methods may not always be accurate or consistent.

4. Proposed System

The proposed system uses machine learning techniques to predict the cost of sculptures automatically.

In this system:

1. A dataset containing information about sculptures and buyers is used.
2. A subset of the dataset is selected because the original dataset is not fully organized.
3. Data preprocessing is performed to clean the dataset.
4. Outliers are removed to improve prediction accuracy.
5. A Random Forest Regressor model is trained using the dataset.
6. A Django-based web application is developed to provide an interactive interface.
7. Users can input sculpture details and receive predicted prices.
8. The application is deployed online using Heroku and GitHub integration.

This system provides faster and more consistent predictions compared to manual estimation.

5. Implementation Procedure

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

Step 1: Data Collection

1. Obtain the dataset containing information about sculptures and buyers from various artists.

Step 2: Data Preprocessing

1. Select a relevant subset of the dataset.
2. Clean the dataset and remove unnecessary data.
3. Identify and remove outliers that may affect the prediction accuracy.

Step 3: Feature Analysis

1. Analyze important features such as sculpture size, shape, shipping type, and delivery options.
2. Convert categorical data into numerical format.

Step 4: Model Development

1. Select the Random Forest Regressor algorithm.
2. Train the machine learning model using the cleaned dataset.

Step 5: Model Evaluation

1. Test the model using test data.
2. Evaluate the performance using regression evaluation metrics.

Step 6: Web Application Development

1. Develop a web application using the Django framework.
2. Integrate the trained machine learning model with the Django application.

Step 7: Deployment

1. Upload the project to GitHub.
2. Deploy the Django application on Heroku cloud platform.
3. Make the application accessible online.

6. Software Requirements

The software used in this project includes:

1. Operating System: Windows / Linux / macOS
2. Programming Language: Python 3.x
3. Framework: Django
4. IDE: Jupyter Notebook / VS Code / PyCharm

Libraries:

1. NumPy
2. Pandas
3. Matplotlib
4. Seaborn
5. Scikit-learn

Deployment Tools:

1. GitHub
2. Heroku

Web Browser: 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. Predicts sculpture prices automatically using machine learning.
2. Reduces dependency on manual pricing methods.
3. Handles large datasets efficiently.
4. Improves model accuracy through outlier removal.
5. Provides a user-friendly web interface.
6. Allows real-time price prediction.
7. Easily deployable using cloud platforms.
8. Demonstrates the integration of machine learning with web development.