Graded Assignment: Modeling and Decision Trees
You work for a hypothetical university as an entry level data analyst and your supervisor has task you to learn more about the data mining process associated with modeling more specifically using decision trees following the steps below:
- In the discussion this week, a task to investigate modeling techniques was requested and your supervisor has asked you to go further into the realm of predictive modeling with a more in-depth investigation of decision trees. To get started, investigate some of the decision tree options in Rapid Miner Studio and research these types of trees to determine comparisons among them and how they are used to support various types of decisions. This portion and literature review of the paper should be a minimum of three pages of written content supported with a minimum of three academic sources of research.
- After completing the literature review comparing types of decision trees, use any of the sample data sets found in Rapid Miner Studio and create at least three decision trees using any of the modeling options provided. Another data set can be downloaded fromhttps://rapidminer.com/training/videos/ which is used in the free Rapid Miner video tutorials.
- Important Reminder: In support of this assignment, everyone should start working through model and validate video tutorials athttps://rapidminer.com/training/videos/. Additional learning videos could be found at www.youtube.com using keyword searches like “Rapid Miner Decision Trees.” For example, check out the resource found below:
- Sanyal, P. (2017). Building decision tree models using RapidMiner Studio. YouTube. Retrieved from https://www.youtube.com/watch?v=U3FVLqV5Jzg
- Rapid Miner. (2018). Operator reference manual. Rapid Minder. Retrieved fromhttps://docs.rapidminer.com/latest/studio/operators/rapidminer-studio-operator-reference.pdf (Note: Check out section 4.1 covering predictive models in this manual where coverage of decision trees is included).
- After creating the decision trees, include them as images in the main paper and conclude the paper with a holistic view of these decision trees sharing types of decisions which could be made based on the output. Do not worry about your decisions being right or wrong as the exercise is geared to further develop decision making skills based on data visualizations. The conclusion of the paper in this case with proposed and developed decisions based on decision tree output should account for a minimum of one additional page of written content.
- Once the overall paper is completed, remember that papers need to be professionally formatted using APA including an APA cover page, abstract, body pages, and reference page
- Complete and submit this assignment for grading on or before the due date. Remember, it is not a good idea to complete or attempt completing work late. See the course syllabus and the associated late policy.