Prediction of auto-insurance claims
The purpose of this report is to explain and justify the steps taken to predict auto-insurance claim status using machine learning techniques. The techniques being explored are the gradient boosted trees and random forests. A novel way of applying convulational neural network to 1d data is also expl...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/75265 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | The purpose of this report is to explain and justify the steps taken to predict auto-insurance claim status using machine learning techniques. The techniques being explored are the gradient boosted trees and random forests. A novel way of applying convulational neural network to 1d data is also explored. The analysis is done using Python and the neural network is being built with Tensor Flow. The steps undertaken for each technique can be broadly classified under the following categories: Data exploration, data pre-processing, feature selection and algorithm optimization. |
|---|