Predict housing prices with a simple neural network

Predict Housing Prices with a Neural Network This n8n template demonstrates how a simple Multi-Layer Perceptron (MLP) neural network can predict housing prices. The prediction is based on four key features, processed through a three-layer model. Input Layer Receives the initial data via a webhook that accepts four query parameters. Hidden Layer Composed of two neurons. Each neuron calculates a weighted sum of the inputs, adds a bias, and applies the ReLU activation function. Output Layer Contains one neuron that calculates the weighted sum of the hidden layer's outputs, adds its bias, and returns the final price prediction. Setup This template works out-of-the-box and requires no special configuration or prerequisites. Just import the workflow to get started. How to Use Trigger this workflow by sending a GET request to the webhook endpoint. Include the house features as query parameters in the URL. Endpoint: /webhook/regression/house/price Query Parameters - squarefeet: The total square footage of the house. - numberrooms: The total number of rooms. - ageinyears: The age of the house in years. - distancetocityinkm: The distance to the nearest city center in kilometers. Example Here’s an example curl request for a 1,500 sq ft, 3-room house that is 10 years old and 5 km from the city. Request curl "https://your-n8n-instance.com/webhook/regression/house/price?squarefeet=1500&numberrooms=3&ageinyears=10&distancetocityinkm=5" Response JSON { "price": 53095.832123960805 }