Question 1:
What is the Virtuous Cycle of Data Mining? describe in detail each of its four stages.
a. Identify the business problem: Finding the problem through the data. Talking to people
b. Transform data into actionable results: Using data to find business-oriented results.
c. Act on the knowledge: Including Insights, fixing data, real-time scoring etc….
d. Measure the results : Did data work and would output expect results in relation to the business?
Question 2:
• What is a good business goal? Break the business goal down in terms of data mining tasks, and explain one of the tasks for that specific goal.
• List and explain what the six phases of The Cross-Industry Standard for Data Mining do and how might they affect a business ?
Question 3:
(1.) Identify and explain the:
(a.) Advantages of decision trees
(b.) Applications of decision trees
(2.) (a) Give two examples of decision tree algorithms.
(b.) Explain the challenges that might be faced using these algorithms.
(c.) Discuss potential applications of decision trees to business data mining.
Question 4:
- List all five steps to applying neural networks to applications and explain and discuss was it entailed in each step.
- How does a neural network learn with back propagation? List the three ways and discuss and expand on each step.
- Where can neural networks be used in practice and discuss how do they work in that industry?
Question 5:
(a). What purpose does cluster analysis serve, and discuss how does it benefit
analysts?
(b.) What are the most widely used clustering methods? Explain what they do.
(c.) What are the variations on K-Means? Explain the uses.
(d.) What are two real applications of cluster analysis? Explain how cluster
analysis is used in these applications.
Full Answer Section
-
Transform data into actionable results. The second step is to transform the data into a format that can be used for data mining. This may involve cleaning the data, removing errors, and integrating data from different sources. Once the data is in a usable format, you can start to apply data mining techniques to extract insights.
-
Act on the knowledge. The third step is to act on the knowledge that you have gained from data mining. This may involve making changes to business processes, developing new products or services, or targeting marketing campaigns more effectively.
-
Measure the results. The fourth step is to measure the results of your actions. This will help you to determine whether or not your data mining efforts have been successful.
Example
A retail company is trying to increase sales. They use data mining to identify their best customers and to understand what products those customers are buying. The company then uses this information to develop targeted marketing campaigns. The company also uses data mining to identify new products that their customers might be interested in.
Benefits of the Virtuous Cycle of Data Mining
The Virtuous Cycle of Data Mining offers a number of benefits to businesses, including:
- Improved decision-making: Data mining can help businesses to make better decisions by providing them with insights into their customers, products, and services.
- Increased efficiency: Data mining can help businesses to improve their efficiency by identifying areas where they can save time and money.
- Competitive advantage: Data mining can help businesses to gain a competitive advantage by identifying new opportunities and by developing innovative products and services.
Good Business Goals and Data Mining Tasks
A good business goal is something that is specific, measurable, achievable, relevant, and time-bound. For example, a good business goal for a retail company might be to increase sales by 10% in the next quarter.
Data mining tasks can be used to break down business goals into smaller, more manageable tasks. For example, the retail company could use data mining to identify the following tasks:
- Identify the company's best customers.
- Understand what products the company's best customers are buying.
- Develop targeted marketing campaigns for the company's best customers.
- Identify new products that the company's best customers might be interested in.
The Cross-Industry Standard for Data Mining (CRISP-DM)
CRISP-DM is a six-phase process for data mining. The six phases are:
-
Business understanding. The first phase is to understand the business problem that you are trying to solve. This involves talking to people from different departments and levels of the organization to get their input.
-
Data understanding. The second phase is to understand the data that you will be using for data mining. This involves exploring the data to identify its characteristics and to identify any potential problems with the data.
-
Data preparation. The third phase is to prepare the data for data mining. This may involve cleaning the data, removing errors, and integrating data from different sources.
-
Modeling. The fourth phase is to build a model of the data. This involves applying data mining techniques to the data to extract insights.
-
Evaluation. The fifth phase is to evaluate the model. This involves testing the model to see how well it performs on new data.
-
Deployment. The sixth phase is to deploy the model. This involves making the model available to users so that they can use it to make predictions.
How CRISP-DM Affects Businesses
CRISP-DM provides businesses with a structured process for data mining. This can help businesses to ensure that their data mining efforts are successful.
CRISP-DM can also help businesses to avoid common data mining mistakes. For example, CRISP-DM emphasizes the importance of business understanding and data understanding. This can help businesses to avoid building models that do not address the business problem or that are not based on reliable data.
Conclusion
The Virtuous Cycle of Data Mining is a four-stage process for using data to solve business problems. The four stages are: identify the business problem, transform data into actionable results, act on the knowledge, and measure the results.
Data mining tasks can be used to break down business goals into smaller, more manageable tasks. CRISP-DM is a six-phase process for data mining that can help businesses to ensure that their data mining efforts are successful.