https://github.com/fedesgh/ann_regression_for_house_price_using_keras_tuner

ANN model optimized with keras tuner
https://github.com/fedesgh/ann_regression_for_house_price_using_keras_tuner

keras keras-tuner

Last synced: 15 days ago
JSON representation

ANN model optimized with keras tuner

• Host: GitHub
• URL: https://github.com/fedesgh/ann_regression_for_house_price_using_keras_tuner
• Owner: Fedesgh
• Created: 2024-10-21T23:37:46.000Z (17 days ago)
• Default Branch: main
• Last Pushed: 2024-10-23T14:58:42.000Z (16 days ago)
• Last Synced: 2024-10-23T18:36:17.355Z (15 days ago)
• Topics: keras, keras-tuner
• Language: Jupyter Notebook
• Homepage:
• Size: 5.59 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Using a dataset of house prices from (https://www.kaggle.com/datasets/harlfoxem/housesalesprediction)

We aim to build an artificial neural network (ANN) optimized with Keras-Tuner.

♦About the data set: 

Number of rows: 21613

Number of columns: 21

We use 18 columns as features (inputs), 1 as target (continuous variable "price"), and drop 2

## Model results

♦Structure:

![model.ss.jpg](model.ss.jpg)

♦Hyperparameters:

num_layers: 6

units_0: 63

activation: leaky_relu

dropout: False

lr: 0.00110654178783952

♦Metrics: 

MAE:  71602.69808292852

MAPE:  0.1280146931732677

![scatterplot.jpg](scatterplot.jpg)