Prediction of Aviation Accidents using Logistic Regression Model
Aswathy Benny, Maria Johny, Linda Sara Mathew
Aviation accidents, Logistic regression model, XGboost, Random Forest
When it comes to long distance movement the only easiest and fastest option we got is aircraft. Plane crashes have always been a big tragedy. Even though we are able to create machines that can carry 850 plus passengers, the safety of this aircraft comes with some questions. No mode of transport is safe. Even a child riding a bicycle isn’t. But we can’t turn our back on the growing world, speaking of which aircraft play a major role in the development of the society. Just because it isn't safe or a few doesn’t reach their destination humanity can’t refuse airplanes. The study about recent aircraft accidents proves there is a strong chance of an unlikely end. A flight crash is caused due to multiple factors. If we can save the lives of people, delay the undeniable death, we are making the world great again. Here we are trying to build Machine Learning models to anticipate and classify the severity of any airplane accident based on past incidents. With this method, the entire aviation industry can predict the airplane accidents caused due to various factors. Then they can make a plan of action to minimize the risk of accident.We have used logistic regression to identify whether a particular feature is important or not and then we adapted random forest technique for classification. Finally we used XGBoost, which provides a gradient boosting framework for python to produce the model. The final result of the method will give the aviation accident prediction based on severity of the accidents.
Article Details
Unique Paper ID: 150433

Publication Volume & Issue: Volume 7, Issue 6

Page(s): 241 - 245
Article Preview & Download

Share This Article

Conference Alert


AICTE Sponsored National Conference on Smart Systems and Technologies

Last Date: 25th November 2021

SWEC- Management


Last Date: 7th November 2021

Latest Publication

Go To Issue

Call For Paper

Volume 8 Issue 4

Last Date 25 September 2021

About Us enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on

Social Media

Google Verified Reviews

Contact Details