Abstract
The most successful companies are the one that know their customers very well and can anticipate their needs. Good customer profiles at the fingertips have businesses improve marketing campaigns, targeting feature launches and product roadmaps. In this study, exploratory data analysis was done on the shopping mall data, and customer segmentation was done using k-means clustering. Two different clusters were done based on age vs. spending score and annual income vs. spending score. Four optimum clusters were obtained for age and spending scores using the elbow graph method, and five optimum clusters were obtained for annual income and spending scores. Firstly, for clusters based on age and spending score, people with higher age groups have less spending scores. Secondly, clusters based on annual income and spending scores had high annual income and very low spending scores. Thus, the mall can offer these cluster customers to attract them, thereby increasing its profits.
TopIntroduction
The growth of the market has forced older companies to apply marketing strategies to stay competitive in the market as it has become more difficult to survive. Every day, the number of consumers increases significantly, and businesses find it difficult to cater for the needs of every customer. Thus, customer segmentation is used, which is the process of dividing customers into groups based on their common characteristics to target each group efficiently (Smith, 2016). The analysis allows companies to determine what their true customers are buying, thus allowing them to better serve their customers, resulting in customer satisfaction. The analysis also allows businesses to determine their target consumers and improve their marketing tactics to get more revenue. Successful marketing not only requires knowledge about who the customers are but also where exactly they are in the buying process and customer segmentation. Customer segmentation was previously a challenging and time-consuming task that demanded hours of manual pouring over different tables and querying the data in hopes of finding ways to keep customers together. But, in recent years it has become much easier by the application of machine learning algorithms that tune statistical regularity and data to such problems (Dullaghan & Rozaki, 2017). Machine learning models can process customer data and discover recurring patterns across various features (Janakirman & Umamaheswari, 2014). In many cases machine learning algorithms can help marketing analyst find customer segment that would be very difficult to spot through intuitions and manual examination of data. Customer segmentation is a perfect example of how combination of machine learning and human intuition can create something that is greater than the sum of its parts (Ezenkwu, Ozuomba & Kalu, 2015).
There are few advantages of customer segmentation. The first advantage of customer segmentation is price optimization (Wilson-Jeanselme & Reynolds, 2006). Understanding the customer and financial status of the customers will assist the company to pace up with the price optimization accordingly and thus it helps in better allocation of resources which in return helps the companies to gain economics of scale. The second advantage is that it enhances competitiveness. The More the customer retention, more will be the revenue generated and all of this will enhance their competitiveness in the market. If a company segments the market, then it will know who are its customers and thus it can come up with new products or variations according to the changing preferences of the customers. If the company is vigilant enough then it may also have the first mover advantage. The third advantage is the brand awareness. By segmenting the customers, the company can make the customers well aware of its brand. Identifying the brand will help customers to directly purchase the product which will increase the company’s goodwill in the market and the brand value which is established among other competitors. The fourth advantage is acquisition and retention of customer with a personalized connection and the customers which will help the company to win the satisfied customers. Satisfied customers are more likely to retain with the organization who regularly meet up with them. Better customer segmentation will lead to developing a better relationship with prospective customers. Customer segmentation allows the company to learn a great deal about its customers and thereby it can carter to their needs more effectively. The last advantage would be increased revenue and return on interest. By fine tuning the company’s marketing message, there will be an increase in revenue because users will be more likely to make a purchase when they are delivered exactly what they need (Mirela & Stanica, 2009).
Key Terms in this Chapter
Manhattan Distance: Manhattan distance is a distance metric between two points in an N-dimensional space. In geometric terms, it is the sum of the projections of a line segment between two points onto the coordinate axes. In other words, it is the sum of the absolute differences between two points in all dimensions.
K-Means: K-means clustering is a method of vector quantization, originally from signal processing, that seeks to partition n observations into k clusters in which each observation belongs to the cluster containing the nearest mean (cluster centers or cluster centroid), which serves as a prototype for the cluster.
Centroid-Based Clustering: A centroid-based clustering method organizes the data into non-hierarchical clusters, as opposed to a hierarchical clustering method. K-means clustering is the most widely used centroid-based algorithm.
Customer Relationship Management (CRM): An organization's customer relationship management (CRM) system manages all interactions and relationships with customers and prospects. Ultimately, the goal is to improve business relationships. Using a CRM system can help businesses streamline processes, improve profitability, and stay connected to customers.
Customer Segmentation: A Customer Segmentation is a method of segmenting a customer or business market based on a set of common characteristics.
Clustering: Clustering is the process of dividing a population or set of data points into a number of groups such that data points in the same group are more similar than those in other groups. Essentially, the objective is to categorize groups based on similar traits and assign them to clusters.
Elbow Method: The elbow method is a heuristic used in cluster analysis to determine the number of clusters in a data set. The method involves plotting the explained variation as a function of the number of clusters, then choosing the elbow of the curve as the number of clusters to use.
Chebyshev Distance: The Chebyshev distance calculation, also known as the “maximum metric” in mathematics, measures the distance between two points as the maximum difference between any two of their axis values.
Unsupervised Learning: Unsupervised learning, also known as unsupervised machine learning, utilizes machine learning algorithms to analyze and cluster unlabeled data. Without human intervention, these algorithms identify hidden patterns or groups of data. Its ability to find similarities and differences in information makes it the ideal solution for exploratory data analysis, cross-selling strategies, customer segmentation, and image recognition.
Minkowski Distance: A Minkowski distance or Minkowski metric is a metric in a normed vector space that can be thought of as a generalization of both the Euclidean distance and the Manhattan distance. It was named after German mathematician Hermann Minkowski.