MIS655 DQ1T1

.docx

School

Grand Canyon University *

*We aren’t endorsed by this school

Course

MIS 655

Subject

Information Systems

Date

May 15, 2024

Type

docx

Pages

2

Report

Uploaded by ProfInternet10544

In the assigned reading for this topic, you learned that there are several methodologies for data mining including SEMMA and CRISP-DM, among others. Regardless of the model used, the steps are essentially the same. Summarize the key steps in the data mining process and provide a specific example of the type of activity that would be completed in each step. Why is it important to remember that the data mining process is not linear? How could viewing the process as linear hamper and impair the results of using the process? Provide examples to illustrate your ideas. According to Oracle (2005), the first step in data mining involves understanding the business and project. This includes knowing the requirements and understanding the objectives from the business perspective to convert this knowledge into project design and definition (2005), For example, if the surgical department is looking for a way to become more efficient in their processes and use of less materials. Once the understanding of the business question is resolved, understanding the data is next and this involves data collection, familiarization with the data, identification of quality issues, and preliminary insights (2005). Continuing with the surgical department example, this could be collection material costs, uses, staffing hours, surgeries planned, cancelled, performed, and so on. Now prepping the data is next after essentially cleaning the data, tidy data is informative data! Data preparation includes cleaning data, removing unnecessary variables, and data transformation for modeling (2005). Here we take our variables listed before and look for outliers, missing entries, maybe add a variable of duration of surgeries. Modeling the data sounds like the fun part. Here is where the use of different modeling techniques and using different parameters to get the optimal outcome for the question at hand (2005). Based on the technique used, going back and forth between data prep and modeling is common because some modeling techniques require different parameters for successful outcomes (2005). An example is taking the data from above to show that there is a possible overstaffing issue or too many canceled surgeries after the surgical room is prepped. After the model is made, evaluation of the model to ensure completeness, and the steps taken were appropriate, and the business objective is met (2005). The surgical manager determines if the model shows enough to cut costs and predict favorable patterns for staffing and surgery planning. If all is well with the model, it is then deployed. Here is where the model is organized for presentation. The ending result for the cost analysis could be that is repeated for future use or predict when costs could rise and the need to charge more for a procedure needs to go up. Linear projects to me seem like a science fair project. This day in age any project is iterative and requires flexibility, possible jumping into a step and out of step to a previous one. Maybe for the sake of the project a step needs to be refined or added. When doing these projects, putting processes in a proverbial box, and following a rigid plan can lead to missed opportunities for intuition or acumen to step in to lead to better analysis.
Oracle. (2005, June 16). Data Mining Concepts . Data Mining Process. https://docs.oracle.com/cd/B19306_01/datamine.102/b14339/5dmtasks.htm Shmueli, G. (2018). Data mining for Business Analytics: Concepts, techniques, and applications in R . John Wiley & Sons.
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help