Management of any process, including marketing, involves an objective assessment of the market situation. Gradually advancing through all stages of the analysis of market opportunities, which include the selection of target markets, and the development of a marketing mix, and the implementation of marketing activities, one involuntarily encounters the need for research. At the same time, one has to not only rely on the talent and experience of the analyst himself, but also on his skillful use of data processing methods.
In the modern economy, with its complexity and multifaceted processes, a huge amount of information, finding the most significant data without using various statistical packages becomes very problematic.
A special role in conducting marketing research is occupied by cluster analysis. By its nature, this is a combined method that combines several methods of statistical research. It is based on the classification of multidimensional observations, each of which corresponds to its own set of descriptive variables. Cluster analysis suggests a way to classify an object according to relative homogeneous (homogeneous) groups, having an initial set of variables for consideration. In other words, objects are divided into groups. In groups, they show similarity in several ways.
Cluster analysis methods are used for a wide range of marketing tasks.
Market segmentation allows you to divide the consumer category into clusters based on the expected benefits from the acquisition of a particular product. Each cluster can consist of consumers looking for similar benefits. The name was chosen for him accordingly - the method of segmentation of benefits.
Analysis of customer behavior. In solving this problem, cluster analysis is used to create homogeneous consumer groups with the goal of modeling their behavior.
By determining the capabilities of a new product, it is possible to cluster it by trademarks, while a pronounced pattern is observed when trademarks of the same cluster show more intense competition among themselves than with brands in other clusters.
By grouping cities into clusters, you can choose the most suitable markets for a particular product.
Cluster analysis reduces data dimension. Observing individual clusters, they then proceed to multiple discriminant analysis. It is much simpler and cheaper than considering each case individually.
The purpose of clustering is to group objects according to similar characteristics. For a more objective assessment of the degree of similarity, a certain reference unit should be introduced. When clusters are formed, they usually rely on two or more features at the same time.
Cluster analysis involves the use of a wide range of clustering methods. Among them, one can single out such as a probabilistic approach, approaches based on artificial intelligence systems, a logical approach, and a hierarchical approach.
Hierarchical cluster analysis involves a complex system that has a number of nested groups or clusters of various orders. This method uses two kinds of features. Agglomerative (unifying) signs are adjacent to divisive (dividing) ones. The number of features leads to the division into monothetic classification methods and polythetic.
Using all these methods in statistics, there are about a hundred clustering algorithms. But hierarchical cluster analysis occupies a leading place in this list. Its attractiveness lies in the fact that it functions perfectly in case of data deficit, and even when the available data do not satisfy the conditions according to the requirement of normal distribution of random variables, as well as other requirements of classical statistical methods.