# FlightDelayPrediction

**Repository Path**: watermelonTT/FlightDelayPrediction

## Basic Information

- **Project Name**: FlightDelayPrediction
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-01-07
- **Last Updated**: 2021-01-07

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# FlightDelayPrediction
Predicting the delay in arrival and departure of the flights and comparing different models for accuracy
Project Title:

Prediction of departure and arrival delay for the flights using Machine Learning models

Description:

Growth in the aviation industry has resulted in air-traffic congestion causing flight delays. Flight delays not only have economic impact but also harmful environmental effects. Air-traffic management is becoming increasingly challenging. In this project, we apply machine learning algorithms like Random Forest Regressor, XGBoost Regressor, logistic regression, and Linear Regression to predict if a given flight’s arrival will be delayed or not. [1]

Air transportation plays a vital role in the transportation infrastructure as well as contributes significantly to the economy. [2]

An aircraft is said to be delayed when it departs and/or arrives later than its actual planned time. There are several causes of an aircraft being delayed such as weather changes, problems in maintenance, previous delays being propagated down the line, traffic congestion, and many more. These delays are a huge challenge for the aviation industry as well as their customers and passengers. In the USA alone, these delays result in a loss of about 22 billion US dollars every year. [2]

Notable reasons for commercially scheduled flights to delay are adverse weather conditions, air traffic congestion, late reaching aircraft to be used for the flight from previous flight, maintenance and security issues. [3]

According to a survey in the USA, in 2015, 18% of the domestic flights were delayed and 1.5% were canceled and out of which 40% were delayed due to late arrival of the aircraft. Delays have a huge impact on the economy and if we are able to predict the delay we can take actions in order to save the loss or improve the delay [4]

This project has experimented on the confidential data provided by the Data team at AirAsia and it consists of data related to flights from date of departure 16th Feb 2020 to date of departure 15th July 2020.
The data consists of fields such as Airline Code, flight number, Tail number, Aircraft type, Scheduled departure date and time, Scheduled Arrival date and time, Departure Airport, Arrival Airport, Actual departure time and day, Actual arrival time and day, Flight Door close time, Flight take-off time, Flight touchdown time, Total passengers, Baggage pieces, longitude and latitude of the departure and arrival airport, the distance between departure and arrival airport, separation with previous flight, tail number of previous flights, departure delay, arrival delay, and net arrival delay.

REFERENCE:
[1] Gopalakrishnan, Karthik, and Hamsa Balakrishnan. “A comparative analysis of models for predicting delays in air traffic networks.” (2017).


[2] R. Nigam and K. Govinda, "Cloud-based flight delay prediction using logistic regression," 2017 International Conference on Intelligent Sustainable Systems (ICISS), Palladam, 2017, pp. 662-667, DOI: 10.1109/ISS1.2017.8389254.


[3] Kuhn, Nathalie, and Navaneeth Jamadagni. “Application of Machine Learning Algorithms to Predict Flight Arrival Delays.” (2017).


[4] Chakrabarty, Navoneel. (2019). A Data Mining Approach to Flight Arrival Delay Prediction for American Airlines.