A Traveler's Data Guide to the Sky

Posted on Apr 30, 2017
The skills the author demoed here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.


Maybe you’ve been here before. After a long flight, you make your way down to baggage claim, ready to grab your bags and finally make your way to your destination. A few minutes pass, and you see other passengers grab their bags. After twenty minutes, the crowd around the carousel starts to thin. Finally, you’ve had enough. You speak to the nearest TSA agent and then find out after some data investigation that your bags didn’t make the trip with you.

United Airlines and other airline companies have recently captured the nation’s headlines because of terrible flying experiences caught on camera. Two weeks ago, a man was forcibly removed from his seat on a United Airlines flight, and just last week, it was reported that a passenger’s pet giant bunny was found dead after their flight. Such incidents, as well as my own flying experiences, piqued my interest. I wanted to use data to find which airline and airport are the worst in terms of TSA claim frequency and why.

The Data

The data used to investigate each TSA claim event was taken from the Department of Homeland Security. The data spanned from 2010-2015, with a total of just over 30,000 claims. Some of the variables that proved most valuable were:

  • Incident Date
  • Airport Name & Airport Code
  • Disposition (if the claim was denied, settled, or approved in full).
  • Claim Type (Property Damage and Passenger Properly loss accounting for 75% of total claims)
  • Item Category (Gives the number of items that were claimed in each event).
  • Close amount (how much was paid out to the passenger).

Additionally, data was pulled from the Bureau of Transportation Statistics for information on number of flights per top airlines and airports in 2014 and 2015. From this data, we are able to get a rough estimate of how often a claim might be filed per airline and airport.

Data Insights

First, I wanted to get a sense of how many claims happened per airport. I use latitude and longitude data to created a map with googleVis and leaflet, which shows different sized circles in each airport location proportional to the number of claims filed at each.

We can see that, regardless of year, JFK has the most claims by far, followed by LAX, and then Chicago. This doesn’t seem too surprising however, since we’d expect to see much higher claim counts from major metropolitan cities. The map will prove to be more useful once we have a better insight as to how many flights go in and out of each of these airports. That will allow for a more accurate assessment of  the claim rate.

A Traveler's Data Guide to the Sky

Next, I was curious to see if there was a seasonal pattern involved in the frequency of claims. However, surprisingly enough, there was no clear seasonal trend according to the time series visualization.

A Traveler's Data Guide to the Sky


As we have an actual count of how many items were claimed per event, I thought it would be cool to visualize how many specific items were lost or damaged by the top airports and airlines. The heat maps allow us to filter by disposition, but for sake of brevity, we’ll look only at approved claims (claims that were paid out in full by the airlines). Some insights were:

  • Travel accessories, clothing, and baggage reign supreme in items that are claimed the most.
  • JFK leads all airports in travel accessory claims with 14 in 2015, as well as 14 clothing items and 15 baggage items.
  • PHX had more approved clothing claims than JFK with 15.
  • Las Vegas is responsible for the most claimed hunting items in 2015, with a total of 9.
  • Not shown on the heat map, but still noteworthy, was that Las Vegas leads all major airports with Personal Injury claims. From 2010-2015, LAS had 10 claims, and all of them were denied.
  • Of the top 10 most travelled US airports, SFO has the smallest number of claims.

A Traveler's Data Guide to the Sky

For airlines in 2015:

  • Delta and Southwest both had 49 travel accessory claims, but Delta exceeded Southwest in baggage claims with 45 to Southwest’s 26.
  • United Airlines and American Airlines both had  about 25 baggage claims, 25 clothing claims, and 28 travel accessory claims in 2015.
  • Spirit Airlines, though consistently rated as one of the worst airlines in terms of customer satisfaction, actually had a minimal number of claims as compared to other major airlines.

Airline Heatmap

Though I went into this project assuming that United Airlines or Spirit Airlines would be the worst airlines in terms of number of TSA claims, the data did not indicate that these airlines, which dominated the headlines in recent weeks, were responsible for the most passenger dissatisfaction.

Incorporating the BTS data showed a different angle however, based on the number of flights each airline flew per year in 2014 and 2015. In 2015, American Airlines, Southwest Airlines, Delta, United, and JetBlue rounded out the top 5 most flown airlines. To my surprise, Atlanta was responsible for the most flights in 2015, followed by LAX, O’Hare, Dallas/Fort Worth, and then JFK.

Now the map actually tells us something. JFK was clearly the number one airport for most claims from 2010 - 2015, yet was only the 5th most traveled in 2015. As for the claim rate by airlines, United claims the top spot in 2014 and 2015, followed by JetBlue, and then Spirit Airlines. Maybe the news headlines were onto something!

A Traveler's Data Guide to the Sky

A Traveler's Data Guide to the Sky


Admittedly, my claim rates calculation should be taken with a grain of salt. The rate was calculated based on the overall average number of passengers per flight in 2014 (89) and 2015 (94). Interestingly, 2015 saw about 25,000 fewer flights than in 2014, but 2015 recorded more almost 50 million more passengers than in 2014. Perhaps the increase in passengers and decrease in flights in 2015 caused a higher rate of claims, but I believe more data would be needed to confirm this claim.

Another notion worth investigating is the number of connecting flights and passengers per airport. Atlanta leads all airports in number of flights by a wide margin, but has a low claim rate, suggesting that maybe passengers who fly to Atlanta don't actually file their claims until they arrive at their final destination.

Lastly, although this is a very high level analysis at domestic airport claims, it does make me feel a little better that recent articles like this one from The Economist come to similar conclusions as my findings. I hope I may be of service by allowing you to interact with my Shiny app, which you might find useful in deciding where your next flight might be, and which airline you may choose to get there.

Link to my GitHub.

About Author

Andrew Rubino

Andrew graduated from UC Santa Barbara with a degree in English and Statistics. He previously worked at an adtech company where he learned the ins and outs of cleaning, transforming, and reporting on big data using a variety...
View all posts by Andrew Rubino >

Related Articles

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI