SlideShare a Scribd company logo
1 of 14
Download to read offline
FLIGHT ARRIVAL DELAY
PREDICTION
Shabnam Abghari
Instructor: Hamidreza Chinaei
6th December 2016
CKME 136 – Ryerson University
INTRODUCTION
Primary Research question
Will a specific U.S. flight arrive at the destination on-time or with delay?
Secondary Research Questions
When is the best day of week/time of year to fly to minimize delays?
Which carrier suffers more delays?
How well does departure delay predict arrival delays?
DATASET
APPROACH
Data
Cleaning
Decriptive
Analysis
Feature
Selection
Model
Selection
Tuning,
Training,
Testing
DESCRIPTIVE ANALYSIS
DESCRIPTIVE ANALYSIS
DESCRIPTIVE ANALYSIS
Arrival delay per airportArrival and departure delay per airport chart
FEATURE SELECTION
MODEL SELECTION
TUNING AND TRAINING
Airline TrainAccuracy TestAccuracy Difference TestError RMSE Sensitivity Specifity
MQ 82.6% 81.3% 1.3% 18.69% 43.11% 87.85% 73.99%
OO 81.2% 79.7% 1.5% 20.30% 45.06% 89.98% 66.20%
UA 79.3% 76.7% 2.6% 23.30% 48.27% 81.97% 70.73%
AA 78.4% 76.0% 2.4% 24.03% 46.42% 82.70% 69.26%
WN 82.4% 74.6% 7.8% 25.38% 50.38% 68.00% 84.55%
Origin TrainAccuracy TestAccuracy Difference TestError RMSE Sensitivity Specifity
ORD 81.10% 79.07% 2.02% 20.93% 45.75% 80.58% 77.58%
DFW 81.27% 78.20% 3.07% 21.80% 44.42% 81.56% 74.83%
DEN 79.17% 76.86% 2.31% 23.14% 48.10% 82.01% 71.39%
ATL 79.52% 76.38% 3.14% 23.62% 48.60% 80.87% 72.00%
EWR 78.07% 74.09% 3.98% 25.91% 50.43% 75.73% 72.49%
Method Train Accuracy Test Accuracy Difference Test Error Sensitivity Specifity
SVM 80.20% 77.02% 3.18% 22.98% 83.59% 68.71%
CONCLUSION
Fewer flights are delayed in April, May, June, September, October,
November.
Flights are less likely to arrive with delay when their departure time is
between 20:00 and 05:00.
Carriers with the most delayed minutes are AA (American Airlines), WN
(Northwest Airline) and MQ (Envoy Air).
airports with the most number of on-time flights are Atlanta, Phoenix and
Kentucky
Orlando, Atlanta, Dallas and Newark are the most congested airports
CONCLUSION
In almost 77% of the cases, if there is a departure delay, then there is an
arrival delay or if the departure is on-time, there is no arrival delay. Our phi
coefficient is 0.53 So we can say departure delay is one of the positive
influencing factors on arrival delay.
After modeling with 3 methods, SVM is the winning method with 80.20%
training accuracy and in 76.45% of the tests, the prediction of aircrafts
arriving on-time or with delay, is correctly done.
Our prediction accuracy could potentially improve if we include other strong
influencing factors such as “weather”.
ANY QUESTIONS?
THANK YOU!

More Related Content

What's hot

Job opportunities in aviation
Job opportunities in aviationJob opportunities in aviation
Job opportunities in aviationmcky8817
 
Data mining & predictive analytics for US Airlines' performance
Data mining & predictive analytics for US Airlines' performanceData mining & predictive analytics for US Airlines' performance
Data mining & predictive analytics for US Airlines' performanceAkiso Yadav
 
Using machine learning to generate predictions based on the information extra...
Using machine learning to generate predictions based on the information extra...Using machine learning to generate predictions based on the information extra...
Using machine learning to generate predictions based on the information extra...University Politehnica Bucharest
 
Denver airport baggage handling system
Denver airport baggage handling systemDenver airport baggage handling system
Denver airport baggage handling systemMadushan Sandaruwan
 
Airline Reservation System
Airline Reservation SystemAirline Reservation System
Airline Reservation SystemArohi Khandelwal
 
Airport Collaborative Decision Making: Systems Approach
Airport Collaborative Decision Making: Systems ApproachAirport Collaborative Decision Making: Systems Approach
Airport Collaborative Decision Making: Systems ApproachEnrique Melendez, C.M., PMP
 
Air Passenger Prediction Using ARIMA Model
Air Passenger Prediction Using ARIMA Model Air Passenger Prediction Using ARIMA Model
Air Passenger Prediction Using ARIMA Model AkarshAvinash
 
Air Cargo Project Final PPT
Air Cargo Project Final PPTAir Cargo Project Final PPT
Air Cargo Project Final PPTSamdish Chumber
 
Aviation Analytics Presentation
Aviation Analytics  PresentationAviation Analytics  Presentation
Aviation Analytics PresentationJon Soars
 
Prediction of Car Price using Linear Regression
Prediction of Car Price using Linear RegressionPrediction of Car Price using Linear Regression
Prediction of Car Price using Linear Regressionijtsrd
 
Bird strikes hazards and avoidance
Bird strikes hazards and avoidanceBird strikes hazards and avoidance
Bird strikes hazards and avoidancepankajmathur378
 
Airlines tickets price determination and factors
Airlines tickets price determination and factorsAirlines tickets price determination and factors
Airlines tickets price determination and factorsJithinthomasPhilip
 
Denver airport baggage handling system (2)
Denver airport baggage handling system (2)Denver airport baggage handling system (2)
Denver airport baggage handling system (2)Madushan Sandaruwan
 
Hybrid Technique for Associative Classification of Heart Diseases
Hybrid Technique for Associative Classification of Heart DiseasesHybrid Technique for Associative Classification of Heart Diseases
Hybrid Technique for Associative Classification of Heart DiseasesJagdeep Singh Malhi
 
Federal aviation administration
Federal aviation administrationFederal aviation administration
Federal aviation administrationFreelancer
 

What's hot (20)

Job opportunities in aviation
Job opportunities in aviationJob opportunities in aviation
Job opportunities in aviation
 
Data mining & predictive analytics for US Airlines' performance
Data mining & predictive analytics for US Airlines' performanceData mining & predictive analytics for US Airlines' performance
Data mining & predictive analytics for US Airlines' performance
 
Using machine learning to generate predictions based on the information extra...
Using machine learning to generate predictions based on the information extra...Using machine learning to generate predictions based on the information extra...
Using machine learning to generate predictions based on the information extra...
 
Denver airport baggage handling system
Denver airport baggage handling systemDenver airport baggage handling system
Denver airport baggage handling system
 
Airline Reservation System
Airline Reservation SystemAirline Reservation System
Airline Reservation System
 
Airline Innovation Trends
Airline Innovation TrendsAirline Innovation Trends
Airline Innovation Trends
 
Airport Collaborative Decision Making: Systems Approach
Airport Collaborative Decision Making: Systems ApproachAirport Collaborative Decision Making: Systems Approach
Airport Collaborative Decision Making: Systems Approach
 
Air Passenger Prediction Using ARIMA Model
Air Passenger Prediction Using ARIMA Model Air Passenger Prediction Using ARIMA Model
Air Passenger Prediction Using ARIMA Model
 
Air Cargo Project Final PPT
Air Cargo Project Final PPTAir Cargo Project Final PPT
Air Cargo Project Final PPT
 
Aviation Analytics Presentation
Aviation Analytics  PresentationAviation Analytics  Presentation
Aviation Analytics Presentation
 
Prediction of Car Price using Linear Regression
Prediction of Car Price using Linear RegressionPrediction of Car Price using Linear Regression
Prediction of Car Price using Linear Regression
 
Bird strikes hazards and avoidance
Bird strikes hazards and avoidanceBird strikes hazards and avoidance
Bird strikes hazards and avoidance
 
Route development
Route developmentRoute development
Route development
 
Final ppt
Final pptFinal ppt
Final ppt
 
Airlines tickets price determination and factors
Airlines tickets price determination and factorsAirlines tickets price determination and factors
Airlines tickets price determination and factors
 
Denver airport baggage handling system (2)
Denver airport baggage handling system (2)Denver airport baggage handling system (2)
Denver airport baggage handling system (2)
 
KNN
KNNKNN
KNN
 
Weather Now
Weather NowWeather Now
Weather Now
 
Hybrid Technique for Associative Classification of Heart Diseases
Hybrid Technique for Associative Classification of Heart DiseasesHybrid Technique for Associative Classification of Heart Diseases
Hybrid Technique for Associative Classification of Heart Diseases
 
Federal aviation administration
Federal aviation administrationFederal aviation administration
Federal aviation administration
 

Viewers also liked

Webinar | Using Big Data and Predictive Analytics to Empower Distribution and...
Webinar | Using Big Data and Predictive Analytics to Empower Distribution and...Webinar | Using Big Data and Predictive Analytics to Empower Distribution and...
Webinar | Using Big Data and Predictive Analytics to Empower Distribution and...NICSA
 
Best practices for building and deploying predictive models over big data pre...
Best practices for building and deploying predictive models over big data pre...Best practices for building and deploying predictive models over big data pre...
Best practices for building and deploying predictive models over big data pre...Kun Le
 
14.05.12 Analysis and Prediction of Flight Prices using Historical Pricing Da...
14.05.12 Analysis and Prediction of Flight Prices using Historical Pricing Da...14.05.12 Analysis and Prediction of Flight Prices using Historical Pricing Da...
14.05.12 Analysis and Prediction of Flight Prices using Historical Pricing Da...Swiss Big Data User Group
 
Supporting Flight Test And Flight Matching
Supporting Flight Test And Flight MatchingSupporting Flight Test And Flight Matching
Supporting Flight Test And Flight Matchingj2aircraft
 
mavdumplog_machine_learning_2016
mavdumplog_machine_learning_2016mavdumplog_machine_learning_2016
mavdumplog_machine_learning_2016Nancy Abramson
 

Viewers also liked (8)

Big Data For Flight Delay Report
Big Data For Flight Delay ReportBig Data For Flight Delay Report
Big Data For Flight Delay Report
 
BIG DATA TO AVOID WEATHER RELATED FLIGHT DELAYS PPT
BIG DATA TO AVOID WEATHER RELATED FLIGHT DELAYS PPTBIG DATA TO AVOID WEATHER RELATED FLIGHT DELAYS PPT
BIG DATA TO AVOID WEATHER RELATED FLIGHT DELAYS PPT
 
Webinar | Using Big Data and Predictive Analytics to Empower Distribution and...
Webinar | Using Big Data and Predictive Analytics to Empower Distribution and...Webinar | Using Big Data and Predictive Analytics to Empower Distribution and...
Webinar | Using Big Data and Predictive Analytics to Empower Distribution and...
 
Best practices for building and deploying predictive models over big data pre...
Best practices for building and deploying predictive models over big data pre...Best practices for building and deploying predictive models over big data pre...
Best practices for building and deploying predictive models over big data pre...
 
Phase1review
Phase1reviewPhase1review
Phase1review
 
14.05.12 Analysis and Prediction of Flight Prices using Historical Pricing Da...
14.05.12 Analysis and Prediction of Flight Prices using Historical Pricing Da...14.05.12 Analysis and Prediction of Flight Prices using Historical Pricing Da...
14.05.12 Analysis and Prediction of Flight Prices using Historical Pricing Da...
 
Supporting Flight Test And Flight Matching
Supporting Flight Test And Flight MatchingSupporting Flight Test And Flight Matching
Supporting Flight Test And Flight Matching
 
mavdumplog_machine_learning_2016
mavdumplog_machine_learning_2016mavdumplog_machine_learning_2016
mavdumplog_machine_learning_2016
 

Similar to Flight Arrival Delay Prediction

Equipment for Aircraft and Air Traffic Control
Equipment for Aircraft and Air Traffic ControlEquipment for Aircraft and Air Traffic Control
Equipment for Aircraft and Air Traffic ControlÜlger Ahmet
 
THE IMPACT OF ON TIME PERFORMANCE ON OPERATION MANAGEMENT AND PASSENGER LOYAL...
THE IMPACT OF ON TIME PERFORMANCE ON OPERATION MANAGEMENT AND PASSENGER LOYAL...THE IMPACT OF ON TIME PERFORMANCE ON OPERATION MANAGEMENT AND PASSENGER LOYAL...
THE IMPACT OF ON TIME PERFORMANCE ON OPERATION MANAGEMENT AND PASSENGER LOYAL...Reefear Ajang
 
A monte carlo simulation for evaluating airborne collision risk in intersecti...
A monte carlo simulation for evaluating airborne collision risk in intersecti...A monte carlo simulation for evaluating airborne collision risk in intersecti...
A monte carlo simulation for evaluating airborne collision risk in intersecti...MEHenry
 
PROBABILISTIC TRAJECTORIES OF LIGHT GENERAL AVIATION OPERATIONS by Damiano Ta...
PROBABILISTIC TRAJECTORIES OF LIGHT GENERAL AVIATION OPERATIONS by Damiano Ta...PROBABILISTIC TRAJECTORIES OF LIGHT GENERAL AVIATION OPERATIONS by Damiano Ta...
PROBABILISTIC TRAJECTORIES OF LIGHT GENERAL AVIATION OPERATIONS by Damiano Ta...ALIAS Network
 
masFlight March 2013 Monthly Performance Report
masFlight March 2013 Monthly Performance ReportmasFlight March 2013 Monthly Performance Report
masFlight March 2013 Monthly Performance ReportJoshua Marks
 
Smart Thinking: Sita Infographic
Smart Thinking: Sita InfographicSmart Thinking: Sita Infographic
Smart Thinking: Sita InfographicCorinne Wan
 
Ncw Suav Presentation
Ncw Suav PresentationNcw Suav Presentation
Ncw Suav Presentationpmatsang
 
Latest data analytics - Nick gates
Latest data analytics - Nick gatesLatest data analytics - Nick gates
Latest data analytics - Nick gatesSITA
 
Which Factors Impact Flight Punctuality Unravelling Secrets to On-time Take-offs
Which Factors Impact Flight Punctuality Unravelling Secrets to On-time Take-offsWhich Factors Impact Flight Punctuality Unravelling Secrets to On-time Take-offs
Which Factors Impact Flight Punctuality Unravelling Secrets to On-time Take-offsaeileenalice
 
Traffic Alert and collision avoidance system (TCAS)
Traffic Alert and collision avoidance system (TCAS)Traffic Alert and collision avoidance system (TCAS)
Traffic Alert and collision avoidance system (TCAS)ARVIND KUMAR SINGH
 
Traffic Alert and collision avoidance system (TCAS)
Traffic Alert and collision avoidance system (TCAS)Traffic Alert and collision avoidance system (TCAS)
Traffic Alert and collision avoidance system (TCAS)ARVIND KUMAR SINGH
 
FAA Airline Project
FAA Airline ProjectFAA Airline Project
FAA Airline ProjectNicholas Lal
 

Similar to Flight Arrival Delay Prediction (20)

Equipment for Aircraft and Air Traffic Control
Equipment for Aircraft and Air Traffic ControlEquipment for Aircraft and Air Traffic Control
Equipment for Aircraft and Air Traffic Control
 
THE IMPACT OF ON TIME PERFORMANCE ON OPERATION MANAGEMENT AND PASSENGER LOYAL...
THE IMPACT OF ON TIME PERFORMANCE ON OPERATION MANAGEMENT AND PASSENGER LOYAL...THE IMPACT OF ON TIME PERFORMANCE ON OPERATION MANAGEMENT AND PASSENGER LOYAL...
THE IMPACT OF ON TIME PERFORMANCE ON OPERATION MANAGEMENT AND PASSENGER LOYAL...
 
Presentations
PresentationsPresentations
Presentations
 
A monte carlo simulation for evaluating airborne collision risk in intersecti...
A monte carlo simulation for evaluating airborne collision risk in intersecti...A monte carlo simulation for evaluating airborne collision risk in intersecti...
A monte carlo simulation for evaluating airborne collision risk in intersecti...
 
PROBABILISTIC TRAJECTORIES OF LIGHT GENERAL AVIATION OPERATIONS by Damiano Ta...
PROBABILISTIC TRAJECTORIES OF LIGHT GENERAL AVIATION OPERATIONS by Damiano Ta...PROBABILISTIC TRAJECTORIES OF LIGHT GENERAL AVIATION OPERATIONS by Damiano Ta...
PROBABILISTIC TRAJECTORIES OF LIGHT GENERAL AVIATION OPERATIONS by Damiano Ta...
 
masFlight March 2013 Monthly Performance Report
masFlight March 2013 Monthly Performance ReportmasFlight March 2013 Monthly Performance Report
masFlight March 2013 Monthly Performance Report
 
Smart Thinking: Sita Infographic
Smart Thinking: Sita InfographicSmart Thinking: Sita Infographic
Smart Thinking: Sita Infographic
 
Ncw Suav Presentation
Ncw Suav PresentationNcw Suav Presentation
Ncw Suav Presentation
 
FAA Risk Management
FAA Risk ManagementFAA Risk Management
FAA Risk Management
 
Latest data analytics - Nick gates
Latest data analytics - Nick gatesLatest data analytics - Nick gates
Latest data analytics - Nick gates
 
AIAA-2013-4399
AIAA-2013-4399AIAA-2013-4399
AIAA-2013-4399
 
Apres Cobem09
Apres Cobem09Apres Cobem09
Apres Cobem09
 
Which Factors Impact Flight Punctuality Unravelling Secrets to On-time Take-offs
Which Factors Impact Flight Punctuality Unravelling Secrets to On-time Take-offsWhich Factors Impact Flight Punctuality Unravelling Secrets to On-time Take-offs
Which Factors Impact Flight Punctuality Unravelling Secrets to On-time Take-offs
 
Atm98
Atm98Atm98
Atm98
 
Flight safety Seminar. Major and Landing Accidents
Flight safety Seminar. Major and Landing AccidentsFlight safety Seminar. Major and Landing Accidents
Flight safety Seminar. Major and Landing Accidents
 
Traffic Alert and collision avoidance system (TCAS)
Traffic Alert and collision avoidance system (TCAS)Traffic Alert and collision avoidance system (TCAS)
Traffic Alert and collision avoidance system (TCAS)
 
Traffic Alert and collision avoidance system (TCAS)
Traffic Alert and collision avoidance system (TCAS)Traffic Alert and collision avoidance system (TCAS)
Traffic Alert and collision avoidance system (TCAS)
 
A-CDM
A-CDMA-CDM
A-CDM
 
FAA Airline Project
FAA Airline ProjectFAA Airline Project
FAA Airline Project
 
FAA Standdown - Dont be Surprised, Be Prepared!
FAA Standdown - Dont be Surprised, Be Prepared!FAA Standdown - Dont be Surprised, Be Prepared!
FAA Standdown - Dont be Surprised, Be Prepared!
 

Flight Arrival Delay Prediction

  • 1. FLIGHT ARRIVAL DELAY PREDICTION Shabnam Abghari Instructor: Hamidreza Chinaei 6th December 2016 CKME 136 – Ryerson University
  • 2. INTRODUCTION Primary Research question Will a specific U.S. flight arrive at the destination on-time or with delay? Secondary Research Questions When is the best day of week/time of year to fly to minimize delays? Which carrier suffers more delays? How well does departure delay predict arrival delays?
  • 7. DESCRIPTIVE ANALYSIS Arrival delay per airportArrival and departure delay per airport chart
  • 10. TUNING AND TRAINING Airline TrainAccuracy TestAccuracy Difference TestError RMSE Sensitivity Specifity MQ 82.6% 81.3% 1.3% 18.69% 43.11% 87.85% 73.99% OO 81.2% 79.7% 1.5% 20.30% 45.06% 89.98% 66.20% UA 79.3% 76.7% 2.6% 23.30% 48.27% 81.97% 70.73% AA 78.4% 76.0% 2.4% 24.03% 46.42% 82.70% 69.26% WN 82.4% 74.6% 7.8% 25.38% 50.38% 68.00% 84.55% Origin TrainAccuracy TestAccuracy Difference TestError RMSE Sensitivity Specifity ORD 81.10% 79.07% 2.02% 20.93% 45.75% 80.58% 77.58% DFW 81.27% 78.20% 3.07% 21.80% 44.42% 81.56% 74.83% DEN 79.17% 76.86% 2.31% 23.14% 48.10% 82.01% 71.39% ATL 79.52% 76.38% 3.14% 23.62% 48.60% 80.87% 72.00% EWR 78.07% 74.09% 3.98% 25.91% 50.43% 75.73% 72.49% Method Train Accuracy Test Accuracy Difference Test Error Sensitivity Specifity SVM 80.20% 77.02% 3.18% 22.98% 83.59% 68.71%
  • 11. CONCLUSION Fewer flights are delayed in April, May, June, September, October, November. Flights are less likely to arrive with delay when their departure time is between 20:00 and 05:00. Carriers with the most delayed minutes are AA (American Airlines), WN (Northwest Airline) and MQ (Envoy Air). airports with the most number of on-time flights are Atlanta, Phoenix and Kentucky Orlando, Atlanta, Dallas and Newark are the most congested airports
  • 12. CONCLUSION In almost 77% of the cases, if there is a departure delay, then there is an arrival delay or if the departure is on-time, there is no arrival delay. Our phi coefficient is 0.53 So we can say departure delay is one of the positive influencing factors on arrival delay. After modeling with 3 methods, SVM is the winning method with 80.20% training accuracy and in 76.45% of the tests, the prediction of aircrafts arriving on-time or with delay, is correctly done. Our prediction accuracy could potentially improve if we include other strong influencing factors such as “weather”.

Editor's Notes

  1. slide 0: title slide
  2. slide 1: problem (in a simple English what the problem is, and probably why it is important), and the expected results. So, the overview of the problem in a high level. The inconveniences resulted from flight delays have been a long-time challenge for passengers, airports and airlines. According to the study conducted by the U.S. Federal Aviation Administration (FAA) in 2010, the data from 2007 was analyzed in order to quantify the economic impact of flight delays. It was found that 32.9 billion USD was borne by the American passengers and airlines. The purpose of this paper is to use the dataset that is thoroughly to train and test a predicting Machine Learning model to predict arrival flight delays based on the features with the highest relevance to the topic. This will be decided based on descriptive statistical analysis on the data. The aim is to predict whether a flight will arrive at the destination with delay or not, given the circumstances.
  3. slide 2: snapshot of dataset (with names of important features) dataset which includes all commercial flight arrival and departure details in the USA, between Oct 1987 and Apr 2008 After cleaning the data and removing the features that are not impactful and records with “NA” values, we end up with 20 features and 14,130,317 records with the following data types:
  4. slide 3: overview or your approach (similar to waterfall figure that you all have in your reports) slide 4: more details of your approach slide 5: more details of your approach
  5. slide 7: results Now we can answer the first research question “When is the best day of week/time of year to fly to minimize delays?” Passengers who travel on Saturdays, Tuesdays and Wednesdays are less likely to experience delay compared to other weekdays. This also applies months with less flight delays such as April, May, June, September, October, November. To answer the second research question, “Which carrier suffers more delays?” we first look at the top 10 airlines with the most number of delayed minutes in arrival and departure and we separately look at the overall outlook of the top 10 carriers with the most delayed minutes. AA (American Airlines) and WN (Northwest Airline) MQ (Envoy Air), UA (United Airlines) and OO (SkyWest Airlines) are at the top.
  6. Looking at arrival and departure times shows that it’s better to avoid flights that leave the origin at 6:00 am, those flights are more likely to arrive with delays. 6:00 also carries the most traffic of departures. Best hours to fly with the lowest probability of running into arrival delays are between 20:00 and 05:00.
  7. slide 7: results If we look at 2007 Arrival and Departure delays per airport, this is the image we will get. Orlando, Atlanta, Dallas and Newark are the most congested airports If we look at the Airlines, Airports and Arrival Delay at the same time, we can clearly see EV (EVA Airlines) experiences its longest delays at Atlanta, AA (American Airlines) and MQ (Envoy Air) at Orlando and Dallas. XE (ExpressJet) at Newark. To answer the last research question “How well does traveling distance predict plane delays?”, we plot the different possibilities of “Arrival delays” and “Departure delays” together. The pie chart below shows that in almost 77% of the cases, if there is a departure delay, then there is an arrival delay or if the departure is on-time, there is no arrival delay. In this case our phi coefficient is 0.53 which shows a weak positive association between the two variables. So we can say departure delay is one of the positive influencing factors on arrival delay.
  8. the algorithm outputs an optimal hyperplane which categorizes new examples.
  9. Characterization and prediction of air traffic delays (Rebollo & Balakrishnan, 2014) Predicting airline delays (Bandyopadhyay & Guerrero, 2012) Flight delay prediction (Martinez, 2012) Estimating flight departure delay distributions (TU, Ball, & Jank) Multi-Factor model for predicting delays at U.S. airports (Xu, Sherry, & Laskey)