House Price Estimation with MLP Neural Networks

This is a project developed as a work for the Artificial Intelligence course at UNIFESP (Universidade Federal de São Paulo) by students Matheus Silva (RA 140317) and Marcos Lucas (RA 140782).

Project Description

The objective of this project is to estimate house prices from a dataset using MLP (Multi-Layer Perceptron) neural networks. The project also includes a comparison of the results obtained using other regression algorithms, such as Decision Tree Regressor and Linear Regression. The project was implemented in Python and utilizes machine learning libraries, such as scikit-learn, to build and train the MLP neural network model.

Project Features

The project has the following features:

• Implementation of MLP neural networks for house price estimation.
• Comparison of results obtained by Decision Tree Regressor and Linear Regression.
• Use of a dataset for training and testing the model.
• Generation of an interactive map with the house price data using visualization libraries, such as matplotlib and folium.

Click here to view the generated map

How to Run the Project

To run the project, follow the steps below:

1. Clone this repository to your local environment.
2. Make sure to configure the correct path for the dataset in the pricing_houses.ipynb file before executing the code.
3. Open the pricing_houses.ipynb file in a Python development environment, such as Jupyter Notebook or Google Colab.
4. Execute the code in the development environment to train the MLP neural network model, as well as the Decision Tree Regressor and Linear Regression models, and generate the interactive map with the results.

References

This project was developed based on the knowledge acquired in the Artificial Intelligence course at UNIFESP. Some of the resources and libraries used in the project:

• scikit-learn: Machine learning library in Python.
• folium: Data visualization library for maps in Python.
• matplotlib: Data visualization library in Python.