Читать книгу Artificial Intelligence and Quantum Computing for Advanced Wireless Networks - Savo G. Glisic - Страница 26

A university wants to offer to its customers (companies in industry) new continuous education type of courses. Currently, they look at the details of each customer and based on this information, decide which offer should be given to which customer. The university can potentially have a large number of customers. Does it make sense to look at the details of each customer separately and then make a decision? Certainly not! It is a manual process and will take a huge amount of time. So what can the university do? One option is to segment its customers into different groups. For instance, each department of the university can group the customers for their field based on their technological level (tl; general education background of the employees), say, three groups high (htl), average (atl), and low (ltl). The department can now draw up three different strategies (courses of different level of details) or offers, one for each group. Here, instead of creating different strategies for individual customers, they only have to formulate three strategies. This will reduce the effort as well as the time.

The groups indicated in the example above are known as clusters, and the process of creating these groups is known as clustering. Formally, we can say that clustering is the process of dividing the entire data into groups (also known as clusters) based on the patterns in the data. Clustering is an unsupervised learning problem! In these problems, we have only the independent variables and no target/dependent variable. In clustering, we do not have a target to predict. We look at the data and then try to club similar observations and form different groups. Hence, it is an unsupervised learning problem.

In order to discuss the properties of the cluster, let us further extend the previous example to include one more characteristic of the customer: