Scribd
Upload
416 views24 pages

Netaji Subhash Engineering College

The document contains details of 4 students including their names and university roll numbers. It also contains an introduction to machine learning based flight delay prediction. Key steps discussed include problem definition, dataset used containing over 100,000 flight records, modeling approaches including logistic regression, decision tree and random forest, and future work on improving models and predicting taxi delays.

Uploaded by

Ramesh Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
416 views24 pages

Netaji Subhash Engineering College

The document contains details of 4 students including their names and university roll numbers. It also contains an introduction to machine learning based flight delay prediction. Key steps discussed include problem definition, dataset used containing over 100,000 flight records, modeling approaches including logistic regression, decision tree and random forest, and future work on improving models and predicting taxi delays.

Uploaded by

Ramesh Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 24

Name-Samir Akhter Name-Ramesh Kumar

Univ Roll-10900216026 Univ Roll-10900216031

Name-Saurabh Kumar Name-Payal Kumari


Univ Roll-10900216022 Univ Roll-10900216037

NETAJI SUBHASH ENGINEERING COLLEGE


Machine Learning
FLIGHT DELAY PREDICTION
Roadmap
• Machine Learning
• Introduction
• Application
• Problem Definition
• Dataset Used
• Our Approach
• Data Visualization
• System Design
• Future Work
• Conclusion
What is Machine Learning?
• application of artificial intelligence (AI)
• automatically learn and improve from experience without being explicitly
programmed.
• needs large volume of data to find patterns in them, learn and make
predictions based on what it learns.
What is Flight Delay?
• Delay is one of the most the annoying thing we people face in our day to
day life.
• What basically delay is -simply delay is the difference between scheduled
time and real time of departure or arrival of a plane.
Application
• Imagine you're scheduled to fly out of Delhi four hours from now and
there's a storm in between. The airline could use this data to determine
that the storm is likely to delay your plane. They could then contact you
and offer you a seat on an alternate flight. You will save time, and the
airline doesn't have to accommodate you on a later flight after the delay
happens."
Problem Definition
• In this context, there are many studies. Some of them treat flight delay
prediction as a regression problem, predicting the delay by the minute,
and others as a classification problem, predicting a time interval where the
delay will fall.
• So in this project, two types of prediction mechanisms are considered:
regression, where the continuous output is an estimate of the arrival delay,
and classification, where the output is a binary prediction of whether the
arrival delay more or less than the predefined threshold.
Dataset Used
The results presented in this paper were obtained
using data from the www.umetrip.com. In order to
get the flight information, we develop a crawler to
crawl data from the website. We had access to a
large dataset of 119432 regular commercial
passenger flights performed from November 3,
2015 to March 5, 2016. The database provides
detailed data for individual flight by phase of flight,
airport weather data, arrival and departure time.
Our Approach
After going through the previous work on it , we are glad to know about its
initiative and we have curiosity to proceed it further. Now we're going to
implement the same algorithm to build machine learning models to predict the
flight delay. Moreover, we will try our best to give maximum accuracy in our
project. We'll train the following models:
• Logistic Regression
• Decision Tree
• Random Forest
Logistic Regression
• Classification Algorithm
• Used to predict binary outcome(1/0 , Yes/No , True/False) given a set of
independent variable.
• To represent binary and categorial outcome , we use dummy variables.
• Special case of linear regression when the outcome variable is categorical.
Random Forest Classifier
• a type of ensemble classifier
• also a supervised algorithm.
• It basically creates a set of decision trees.
Decision Tree
• belongs to the family of supervised learning algorithms.
• Unlike other supervised learning algorithms, decision tree algorithm can
be used for solving regression and classification problems too.
• The general motive of using Decision Tree is to create a training model
which can use to predict class or value of target variables by learning
decision rules inferred from prior data(training data).
System Design
• The first step is the conversion of this raw data into processed data.
• So the first step is feature extraction, where the key attributes are extracted
from the whole list of attributes available in the raw dataset.
• The feature extraction process is followed by a classification process wherein
the data that was obtained after feature extraction is split into two different
and distinct segments.
• The splitting is done in a way that training data maintain a higher proportion
than the test data.
Steps for machine learning process
Real life working model
User
Interface

Real life working model


Future Work
• For further work I like to improve my model, perhaps with more training-
data or deeper neural network, or both.
• Taxi-delay prediction is a natural progression to this work, considering
amount of fuel wasted while taxing.
• Accurate taxi-delay prediction requires taking airport runway and taxiway
configurations into consideration where very little work exists.
Conclusion
• This project and the analysis retrieved will be useful not only for passengers
point of view, but for every decision maker in the aviation industry.
• Apart from the financial losses incurred by the industry, flight delay also
portray a negative reputation of the airlines, and decreases their reliability.
• The analysis carried here not only predicts delays based on the previous
available data, but also give statistical description of airlines, their rankings
based on their on-time performance, and delays with respect to time,
showing the peak hours of delay.
References
• [1] C. Cetek, E. Cinar, F. Aybek, and A. Cavcar, “Capacity and delay analysis for
airport manoeuvring areas using simulation,” Aircraft Engineering and Aerospace
Technology, vol. 86, no. 1, pp. 43–55, 2013. [Online]. Available:
https://doi.org/10.1108/AEAT-04-2012-0058
• [2] K. B. Nogueira, P. H. Aguiar, and L. Weigang, “Using ant algorithm to arrange
taxiway sequencing in airport,” International Journal of Computer Theory and
Engineering, vol. 6, no. 4, p. 357, 2014.
• [3] R. R. Clewlow, I. Simaiakis, and H. Balakrishnan, “Impact of arrivals on
departure taxi operations at airports,” 2010
Thank You

You might also like