Laksmi Wulandiari
Airline membership segmentation, for marketing purposed
In this project, I'm analyzing the characteristics of airline member, based on various category and segmenting the members. The result from this analysis, will help identify the right marketing steps for each segment. An airline can be defined as a company that offers regular services for transporting passengers or goods via the air. These companies are said to make up the airline industry, which is also regarded as a sub-sector of the aviation sector and the wider travel industry.
For the dataset, I'm using flight.csv, and KMeans Clustering method to help clustering the dataset. K-means clustering is a method of vector quantization, originally from signal processing, that aims to partition n observations into k clusters in which each observation belongs to the cluster with the nearest mean.
MEMBER_NO
: ID Member
FFP_DATE
: Frequent Flyer Program Join Date
FIRST_FLIGHT_DATE
: First flight date
GENDER
: Member's gender
FFP_TIER
: Tier of Frequent Flyer Program
WORK_CITY
: Member's Hometown
WORK_PROVINCE
: Member's Hometown province
WORK_COUNTRY
: Member's home country
AGE
: Member's age
LOAD_TIME
: Times when data collected
FLIGHT_COUNT
: Amount of flight taken
BP_SUM
: Travel plan
SUM_YR_1
: Fare Revenue
SUM_YR_2
: Votes Prices
SEG_KM_SUM
: Total miles
LAST_FLIGHT_DATE
: Last flight date
LAST_TO_END
: Distance between latest flight with last flight
AVG_INTERVAL
: Average time distance
MAX_INTERVAL
: Maximum time distance
EXCHANGE_COUNT
: Point exchange
avg_discount
: Member's average discount
Points_Sum
: Member's point amount
Point_NotFlight
: Unused point
Python, numpy, pandas, sklearn, seaborn and matplotlib