Apartment Price Prediction

This project aims to predict the price of an apartment based on its features. The model takes into account essential details such as the area of the apartment, the number of bedrooms, and whether the apartment has a pink book. It also considers additional features such as the location of the apartment, the presence of a parking lot, a swimming pool, and a gym.

Let's predict the price of an apartment by entering its details in the form below. You can see the dataset features by clicking on the question mark icon next to the form title.

Project Details

Here are breakdowns of the project:

• Dataset

  • The dataset used in this project contains information about mid-range apartments in Ho Chi Minh City.
  • The dataset consists of 120 examples and 16 features.

• Model

  • The model used in this project is a neural network.
  • The neural network consists of multiple layers of neurons that process the input data and generate predictions for the prices of the apartments.

  Technologies Used

  Technology	Description
  Python	A high-level programming language used for data analysis and model development.
  Pandas	A data manipulation library used for reading and processing datasets.
  Matplotlib	A plotting library used for visualizing data and model performance.
  Scikit-learn	A machine learning library used for data preprocessing and model evaluation.
  TensorFlow	An open-source deep learning library used for building neural networks.

  Dataset Split

  Dataset	Size
  Training Set (80%)	96 examples
  Testing Set (20%)	24 examples

  Model Architecture

  • Model Type: Sequential Neural Network.
  • Total Parameters: 1,217 (4.75 KB).
  • Trainable Parameters: 1,217 (4.75 KB).
  • Non-trainable Parameters: 0 (0.00 B).

  Layer (type)	Output Shape	Param #
  Hidden Layer 1 (Dense)	(None, 32)	544
  Hidden Layer 2 (Dense)	(None, 16)	528
  Hidden Layer 3 (Dense)	(None, 8)	136
  Output Layer (Dense)	(None, 1)	9

  Training Configuration

  Epochs	Batch Size	Optimizer	Loss Function
  100	32	Adam	Mean Squared Error

• Training

  • The model is trained on a subset of the dataset.
  • The training process involves adjusting the weights and biases of the neural network to minimize the loss function.

  Loss and Mean Squared Error

  

• Testing

  • The model is tested on a separate subset of the dataset to evaluate its performance.
  • The testing process involves making predictions on the test examples and comparing them with the actual prices of the apartments.

  Predicted vs. Actual Prices

  

• Results

  • The model is evaluated based on its accuracy in predicting the prices of the apartments.
  • The results of the evaluation are presented in the form of metrics such as the mean squared error and the classification accuracy.