Using Deep Learning (ANN) to predict Bank Churn

• Performed Data Preprocessing techniques to clean and make the data ready for model building

• Exploratory Data Analysis was used to discover insights in the data

• Modelled the data with Deep Learning (ANN architecture)

• Performed regularization using DropOut

ANN of 30 epochs with 4 layers consisting of

• 32
• 64
• 32
• 1

Regularized ANN of 30 epochs with 4 layers consisting of

• 32
• 64 with 50% Dropout
• 32 with 20% Dropout
• 1