Question

Question 1 (15 Marks) Define the three types of Business Analytics approaches. Categories the following techniques into their appropriate type of Business Analytics. Provide at least two examples for each of the following application areas and also explain how they are playing a crucial role in their appropriate category of Business Analytics. a) Expert Systems; b) Data Mining; c) Data Warehousing

Answer 1

Business analytics help in determining the position of the business and metrics for its success.

Three types of business analytics approaches are:

Descriptive:

In this approach, important information is extracted. It helps in determining the occurrence of events, their causes, and influence.

• It helps in understanding how certain approaches can impact the business in the long term.

Predictive:

In this approach, the insights from the descriptive analytics are used to predict the future. It is helpful in offering guidance to take control of the current and past trends.

• It also helps in foreseeing the results of data distribution and the scope of the projects.

Prescriptive:

In this approach, various scenarios are considered. It helps in offering recommendations and solutions based upon the results from descriptive and predictive analytics.

• It is essential for the efficiency of the business.
• It helps in optimizing the resources and make effective decisions.

a) Expert systems:

Expert systems can be categorized as prescriptive analytics techniques. This is because it uses the intelligent recommendations in the form of if-then rules and suggest the optimal steps for a problem.

• This helps in driving the results and accelerate the outcomes for a scenario.
• This is the same as prescriptive analytics.

Example 1:

MYCIN is an example of an expert system. It is fed with the required knowledge and data. This system is used to identify bacterial infections. This information is taken from doctors and experts in the field. The data is programmed into the MYCIN.

• The system uses the given information to create a report about the patient and suggested solutions.
• It uses prescriptive analytics to come up with a prescription by using the data fed into the system.

Example 2:

DENDRAL is another example of an expert system. This system is developed to identify organic molecules by evaluating mass spectra. It is also fed with information about several molecules and their structures.

• It makes use of prescriptive analytics to come up with a solution using the information fed into it.

b) Data Mining:

Data mining can be categorized as a predictive analytics technique. It works by discovering patterns in the given sets of data. The useful information is extracted from the raw data. This is how predictive analytics works.

• It helps in providing companies with reports on sales, customers, finances, etc and predicts customer behaviour or future sales etc.  

Example 1:

Marketing is an example of data mining. Using predictive analytics, large databases are explored to improve the segmentation of the market. It helps in understanding the relationship between customers, interests, products, and more.

• The data can be used to understand what users are likely to buy in the future.
• It is helpful to offer insights.

Example 2:

Retail is another example of data mining. The joint purchasing used to recognize the associations between products is an example of predictive analytics.

• It helps in deciding the place of products in the aisles.
• It also helps in detecting the products valued by the clients.

c) Data Warehousing:

It can be categorized as descriptive analytics technique. This is because descriptive analytics focuses on the previous data collected to provide context for the understanding of the data. The data stored covers a diverse range of topics.

• It also helps in offering a historic review of the data.
• Data warehouse gathers information from different resources and uses that information for various purposes.

Example 1:

IoT or internet of things devices makes use of descriptive analytics or data warehousing to work as standalone devices.

• It allows the users to improve the processes and refine the information using previously recorded ways.

Example 2:

Marketing data warehouses used by supermarkets are a very good example. They are used to gather and store business requirements. They help in looking at the wide business picture.

• It also helps in deriving insights.
• The data in these data warehouses are collected from various departments of the organization.