Skip to content

Latest commit

 

History

History
16 lines (16 loc) · 1.64 KB

README.md

File metadata and controls

16 lines (16 loc) · 1.64 KB
Raw

Airline-Customer-Satisfaction

This a supervised machine learning project to predict customer satisfaction based on factors like Gender, Customer Type, Age, Type of travel, Class, Flight distance, Cleanliness, Departure and Arrival Delay, etc

Acheivements

  • Through exploratory analysis i was able to gain the following insights on the customers:
    • 81.7% of customers are loyal while 18.3% are not
    • 54.4% of customers travelling for business are satisfied with the airline's services while 41.6% are not
    • 53.4% of customers taking personal trips are satisfied with the airline's services while 46.6% are not
    • On an average the higher the depature and arrival delay time the more dissatisfied the customers are with the airline's services
    • 62.0% of satisfied customers traveled in Business Class, 32.3% traveled in Economic Class while 5.7% traveled in Economic Plus Class
    • 70.9% of customers that traveled in Business Class are satisfied with the airline's services while 29.1% are not
    • 60.6% of customers that traveled in Economic Class are satisfied with the airline's services while 39.4% are not
    • 57.3% of customers that traveled in Economic Plus Class are satisfied with the airline's services while 42.7% are not
    • 60.4% of satisfied customers were Females
    • 65.1% of customers Female customers are satisfied with the airline's services while 34.9% are not
    • 56.0% of customers Male customers are satisfied with the airline's services while 44.0% are not
  • I split the dataset into test and train datasets and trained the LogisticRegression model using the train dataset and tested using the test dataset and achieved a 83.0% accuracy