Customer Segmentation

Customer Segmentation

Summary of Customer Segmentation

Customer segmentation is a very critical component of marketing as it ensures that customers have been grouped according to their common characteristics. It helps an organization as they will be in a position of efficiently and effectively meeting the needs of their target customers. Selecting customers and grouping them according to their inherent characteristics is critical as this will ensure that their needs are studied and satisfied appropriately. The customer could be grouped based on their previous consumption patterns, the region, age, gender or even the geographical and spatial distribution(Ibrahim et al., 2010). Segmentation is one of the critical elements to the marketers as it always ensures that the needs of s given niche market have been studied exclusively using the models that are presented. It helps address the problems and issues within a segment independently.

In the segmentation process, it is vital to ensure that the knowledge systems, as well as previous customer experiences, have been incorporated; this is effective as it will help an organization get to know their target market effectively and at the same time develop strategies that are effective for ensuring that the emerging needs of such a segment and the emerging markets have been satisfied(Ibrahim et al., 2010). Customer segmentation will be achieved when an organization have the right customer data as well as being informed on some of the needs and the changing patterns in the customers. Customers are diverse, and as such, this knowledge will be useful in ensuring that an organization realizes their critical objective of customer satisfaction.

Knowledge Discovery in Database

Knowledge Discovery in Database (KDD) is a process of discovering useful data from the knowledge or a collection of data. Overall, KDD is among the processes involved in data mining, and it includes the preparation as well as a selection of data, cleansing of the data, and incorporation of the prior knowledge regarding datasets as well as the interpretation of the accurate solutions from the results that have been observed.

KDD includes an amalgamation of several activities, and this includes storage of data as well as the access, scaling of algorithms to massive data sets and the interpretation of results. Data cleansing and data access processes will include the facilitation of data warehousing. Artificial intelligence supports the KDD process through the discovery of the empirical laws from observation and experiment(Ibrahim et al., 2010). Some of the patterns that are recognized in the data must thus be valid on the new data as well as possess some degree of certainty. The discovered patterns are considered as new knowledge. The following are the main steps of KDD as tabulated appropriately:

Step Objective Data Mining technique involved Precaution when the mining algorithm is applied
Understanding of the application domains It  is one of the critical steps which makes an organization to understand the fields to use in customer management. K-Means data mining algorithm, and it creates groups from a set of objects.


There is a need to classify the data based on their inherent characters.
Simplify the data sets through the removal of the variables that are unwanted


To remove the variables that are not needed Naïve Bayes Data Mining Algorithm Differences could be experienced in the groups that have been selected.
Search and analyze the patterns of interest- this will include the classification of the trees, use of regression analysis as well as clustering techniques.


To classify the data using regression analysis C4.5 Data Mining Algorithm Ensure that the data within the range is analyzed and closely observed.
  1. Identification of the KDD process from the perspective of the customers
  2. Understanding of the application domains that are involved and the knowledge required
  • Selection of target data or the subset of data samples where discovery need to be done
  1. Cleanse and process the data through making a decision on the strategies in handling the missing fields as well as altering the data as per the needs and requirements.
  2. Simplify the data sets through removal of the variables that are unwanted
  3. Match KDD goals with the methods of data mining so as to suggest the patterns that are hidden (Ibrahim et al., 2010)
  • Choice of a mining algorithm – it includes a decision on the models and parameters appropriate for the overall process.
  • Search and analyze the patterns of interest- this will include the classification of the trees, use of regression analysis as well as clustering techniques
  1. Interpretation of the knowledge from the patterns
  2. Use of knowledge and its incorporation into other systems for action
  3. Documentation of the results and making it available to interested persons.



Ibrahim, M., Küng, J., Revell, N., International Workshop on Database and Expert Systems Applications, & LINK (Online service). (2010). Database and expert systems applications: 11th international conference, DEXA 2000, London, UK, September 4-8, 2000: proceedings. Berlin: Springer.

Do you need high quality Custom Essay Writing Services?

Custom Essay writing Service