Data mining

1. “Data mining is a tool, not a magic wand. It will not sit in your database watching what happens and send you e-mail to get your attention when it sees an interesting pattern or find optimal results. It does not eliminate the need to know your application, to understand your data, or to understand traditional methods.”

Explain the message/argument in the above statement based on your knowledge of “data mining” or “business analytics” in general. Support the argument by providing specific examples from the different techniques discussed in class.

2. As a data analyst, you should perform data exploration, visualization, and pre-processing before proceeding directly to applying any high-powered predictive techniques.

1. Using the techniques covered in this course (i.e., decision tree, logistic regression, artificial neural network), explain how data exploration, visualization, and pre-processing steps impact your data analysis process and your potential findings. Be sure to provide sufficient details and examples in your explanation.

1. Explain how your approaches and methods differ when applying data exploration, visualization, and pre-processing methods for numerical versus categorical variables in your data. Use specific and relevant examples in your explanation

3. Data by itself, regardless of its volume, variety or velocity, is worthless unless it is supported by organizational readiness or capabilities in many aspects to generate useful results. What would you identify as critical success factors for analytics practice in an organizational setting? Outline and discuss these factors using different contexts and examples.