CustomerSegmentationModel: Autoencoder for Customer Segmentation

Model Details

• Model Architecture: Autoencoder
• Framework: PyTorch
• Input Dimension: User-defined (input_dim)
• Output: Reconstructed customer features
• Dataset: Predicting Credit Card Customer Attrition

Model Description

The CustomerSegmentationModel is an autoencoder designed to extract low-dimensional representations of customer data. It consists of:

• An encoder that compresses the input into a 2D latent space.
• A decoder that reconstructs the original input from the compressed representation.

This approach enables customer segmentation based on the learned latent space.

Training Details

• Loss Function: Smooth L1 Loss
• Optimizer: Adam
• Batch Size: 256
• Number of Epochs: 100
• Regularization: Dropout (50%) and Layer Normalization

Model Architecture

class CustomerSegmentationModel(nn.Module, PyTorchModelHubMixin):
    def __init__(self, input_dim):
        super(CustomerSegmentationModel, self).__init__()
        self.encoder = nn.Sequential(
            nn.Linear(input_dim, 256),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(256, 128),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.LayerNorm(128),
            nn.Linear(128, 64),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.LayerNorm(64),
            nn.Linear(64, 2),
        )
        self.decoder = nn.Sequential(
            nn.Linear(2, 64),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(64, 128),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(128, 256),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(256, input_dim),
            nn.Sigmoid(),
        )

    def forward(self, x):
        x = self.encoder(x)
        x = self.decoder(x)
        return x


This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Library: [More Information Needed]
- Docs: [More Information Needed]