View Proposal

---

Proposer

Andres Barajas Paz

Title

A Hybrid Model for Predicting Insurance Claims Using GLM and Neural Networks

Goal

To explore a hybrid machine learning model that combines a Generalized Linear Model (GLM) with a neural network to predict car insurance claims.

Description

In this project, the objective is to explore a hybrid machine learning model that combines a Generalized Linear Model (GLM) with a neural network to predict car insurance claims. GLMs are commonly used in insurance because they are easy to understand, but they may miss complex patterns in the data. Neural networks can find those patterns but are harder to explain. By combining both, the goal is to build a model that is accurate and still somewhat explainable. The model will be tested on an insurance dataset and compared with a regular GLM and a standalone neural network.

Resources

Background

Url

Difficulty Level

Challenging

Ethical Approval

None

Number Of Students

1

Supervisor

Andres Barajas Paz

Keywords

machine learning, neural network, car insurance claims, glms

Degrees

Bachelor of Science in Statistical Data Science
BSc Data Sciences