“Financial Risk Prediction Using a Neural Network Classifier”

This presentation outlines a financial risk prediction project leveraging a feedforward neural network to classify customers into 'High Risk' or 'Low Risk' groups based on a synthetic dataset. The model employs ReLU and Sigmoid activation functions, optimised using binary crossentropy loss with Adam. Key evaluation metrics include AUC (0.7902), accuracy (0.72), and recall (0.75), with detailed visualisations provided. Insights into business impact highlight improved financial decision-making...