BIG DATA AND DATA MINING
Weekly Learning Outcomes
This week students will
- Evaluate the data mining techniques of a selected company.
- Examine the four Vs of big data.
- Create a data mining model.
In Week 4, you will shift your focus to big data and data mining practices. You will study the four Vs of big data and how companies use big data to gain competitive advantages. You will also examine data mining practices of organizations, including text mining and web mining. In this week’s assignment you will examine some data mining best practices, as well as dangerous pitfalls that organizations often fall into that can severely compromise data.
Big Data and Data Mining Reflection [WLOs: 1, 2] [CLO: 4]. 1st Post Due by Day 3. Prior to completing this discussion forum, read Chapter 21 of your textbook. There is no standard definition for big data or data mining. In this discussion forum, we follow the general definitions used in our textbook. “Big data” refers to a dataset that is too complex and big to apply traditional data analysis methods. “Data mining” is discovery-oriented in comparison to traditional databases when users know what they are looking for in the database. Our textbook refers to the four Vs (i.e., volume, variety, velocity, and veracity) that make the big data big. Volume or the size is what everyone corresponds with big data, but the other three variables contribute to the complexity that is associated with big data.
In your post,
• Provide an example of a company that is collecting big data for competitive advantage. Explain
how each of the three Vs, outside the volume, is helping the company achieve competitive
advantage.
• Explain the values of data mining in a business and at least three challenges in managing a
data mining project.
Data Mining Discovery Reflection [WLOs: 1, 3] [CLO: 4]. 1st Post Due by Day 3. Prior to completing this discussion forum, read Chapter 21 of your textbook. In this discussion, we will continue to review big data and data mining. Research the data mining practices of the organization you work for, or one that you are familiar with. Specifically, research their text mining and web mining practices. If they do not utilize text and web mining, research an organization that provides text and web mining services. Using this research, • Explain how your chosen company benefits from text mining. Give an example of how your chosen company has successfully implemented text mining. Justify your answer. • Explain how your chosen company benefits from web mining. Give an example of how your chosen company has successfully implemented web mining. Justify your answer
Week 4 Reflective Journal [WLO: 1] [CLOs: 1, 3, 4]. Due by Day 7. Prior to beginning work on this assignment, read Chapters 7 and 8 in Superforecasting. The intent of the journal is to apply what you have learned to how data analytics is applied in industry. After reading the assigned chapters of Superforecasting this week, write a reflective journal of the three most important take-aways contained in the chapters. Your journal should be between two to three pages excluding cover and reference page.
Data Mining Best Practices [WLO: 1] [CLO: 4]. Due by Day 7. Prior to beginning work on this assignment, review Chapter 21 of your textbook. In this assignment, you will analyze current data mining practices and evaluate the pros and cons of data mining. Provide one example of a company that has successfully practiced data mining and discuss why they were successful. Then, research a company that experienced a failed data mining practice. What data mining best practices could they have implemented to avoid this failure?
In your paper,
• Discuss the industry standards for data mining best practices.
• Identify pitfalls in data mining, including practices that should be avoided.
• Provide an example of company that has successfully practiced data mining. What steps and
precautions did they take to ensure the success of their data mining endeavor? How did they
keep customer data safe?
• In a second example, research a company that experienced a failed data mining experience.
What pitfalls did the organization fall into? What would you have done differently?
