CUSTOMER SEGMENTATION OF GOODBABY CUSTOMERS
Ni, Na (2019)
Åbo Akademi
2019
Julkaisu on tekijänoikeussäännösten alainen. Teosta voi lukea ja tulostaa henkilökohtaista käyttöä varten. Käyttö kaupallisiin tarkoituksiin on kielletty.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe2019052216704
https://urn.fi/URN:NBN:fi-fe2019052216704
Tiivistelmä
When talking about China, the population has always been a hot topic. Since the two-child policy was fully opened at the end of 2015, people keep focusing on the maternal and child market that is expected to expand rapidly, and so does the author. The surge in birth population and the diversification of consumer demand have led to more demand for high quality products and services.
In recent years, this industry has been buoyed by capital, especially vertical e-commerce platform. The participation of e-commerce has made the maternal and child retail market increasingly competitive. How do traditional mother-and-baby companies compete with vertical e-commerce platforms? How do they seize the chance of transformation? Unfortunately, there is not enough literature or historical experience on the transition of the traditional mother-to-child retail company. Therefore, the author of this article thesis is committed to contributing to the transformation of these traditional companies that are in dire straits. And “Goodbaby”, as one of the largest distributors and retailers selling mother and baby products in China, became the object of this study.
After six-month intern in Goodbaby, several clear problems have been found after according to the basic statistics. The most fundamental cause of these problems is that they do not understand their customers, or they don't know who they are and what characteristics they have. Thus, in this thesis, the author would perform customer segmentation to assist the company make the first step in the transition.
The approach adopted to solve the problem is the combination of RFM (Recency, Frequency, Monetary) model and the famous algorithm of clustering analysis, K-means. In order to make the whole process more clear and standardized, the author regarded this experiment as a data mining work and applied the classic CRISP-DM model to implement the entire process of customer segmentation.
The results obtained in the model include seven meaningful clusters and one outlier. Combined with demographic attributes and the analysis of consumer behavior, all these seven clusters have been well defined, and corresponding marketing strategies were given according to the features of each cluster.
In recent years, this industry has been buoyed by capital, especially vertical e-commerce platform. The participation of e-commerce has made the maternal and child retail market increasingly competitive. How do traditional mother-and-baby companies compete with vertical e-commerce platforms? How do they seize the chance of transformation? Unfortunately, there is not enough literature or historical experience on the transition of the traditional mother-to-child retail company. Therefore, the author of this article thesis is committed to contributing to the transformation of these traditional companies that are in dire straits. And “Goodbaby”, as one of the largest distributors and retailers selling mother and baby products in China, became the object of this study.
After six-month intern in Goodbaby, several clear problems have been found after according to the basic statistics. The most fundamental cause of these problems is that they do not understand their customers, or they don't know who they are and what characteristics they have. Thus, in this thesis, the author would perform customer segmentation to assist the company make the first step in the transition.
The approach adopted to solve the problem is the combination of RFM (Recency, Frequency, Monetary) model and the famous algorithm of clustering analysis, K-means. In order to make the whole process more clear and standardized, the author regarded this experiment as a data mining work and applied the classic CRISP-DM model to implement the entire process of customer segmentation.
The results obtained in the model include seven meaningful clusters and one outlier. Combined with demographic attributes and the analysis of consumer behavior, all these seven clusters have been well defined, and corresponding marketing strategies were given according to the features of each cluster.