Week 8 Assignment – Devise Text and Web Mining Predictive Models to Gain Insights Into Customer Churn

Scenario

Imagine that you’re a marketing executive at a major telecommunication company that has been facing the issue of increased customer churn recently. You’re using traditional analytical methods with financial and location data to construct a predictive model for customer churn. However, you want to leverage memo data that has been obtained from the customer contact center and local selling stores. You also believe that web blogs and posts contain very important information that you could use to attack customer churn. Examining the unstructured data and the structured data together may provide more insight into why customers want to leave one company and join another company.

Instructions

Write a 4–5 page paper in which you:

• Evaluate, with supporting evidence, the importance of unstructured data in the churn analysis.
• Propose a series of steps for deriving a predictive model using text and web mining, including one example of how the process can be integrated into the structured data modeling process.
• Evaluate the use of three technologies that you can use to construct the predictive model, highlighting their pros and cons.
• Support your writing with at least three credible, relevant, and appropriate sources.
  • Cite each source on your source list at least one time within your assignment.
  • For help with research, writing, and citation, access the library or review applicable library guides.
• Write clearly and concisely in a manner that is well-organized, grammatically correct, and free of spelling, typographical, formatting, and punctuation errors.

This course requires the use of Strayer Writing Standards. For assistance and information, please refer to the Strayer Writing Standards link in the left-hand menu of your course. Check with your professor for any additional instructions.The specific course learning outcome associated with this assignment is:

• Propose a predictive model to solve a business problem using text and web mining.