This repository focuses on developing a deep neural network model to predict risk ratings for life insurance applicants.
The core of this project lies in the Life_Insurance_Assessment.ipynb notebook, where the development and implementation of the predictive model take place. Additionally, we offer an interactive learning experience through the LIA_Hyperparameter_tutorial.ipynb notebook. This tutorial guides users through the process of building and optimizing a Multi-Layer Perceptron (MLP) model step by step, offering graded exercises to reinforce understanding.
The Tutorial
directory includes the following files:
-
File: LIA_Hyperparameter_tutorial.ipynb
Description: This notebook provides an interactive lab experience, guiding users through the implementation of an MLP model for risk prediction. Users can follow along with guided exercises to deepen their understanding of the model-building and hyperparameter tuning process. -
File: LIA_Hyperparameter_tutorial_Solution.ipynb
Description: This notebook presents the solutions to the exercises provided in the interactive tutorial, offering users a reference point to compare their own implementations.
The Tuners
directory contains optimal hyperparameter values obtained through searches for different models. The Models
directory contains some of the trained models considered as candidates for the risk assessment task. These files are necessary to reproduce the obtained results and optimize resources.