ITSCM 777 Project 1e

pdf

School

Ohio State University *

*We aren’t endorsed by this school

Course

531

Subject

Business

Date

Feb 20, 2024

Type

pdf

Pages

Uploaded by SuperHumanBraveryDove41

ITSCM 777: DATA MINING FOR BUSINESS Prof. Alana Platt Project 1 – Data Pre-processing and Decision Trees In this assignment, you will do a series of tutorials followed by a data mining task. You will apply the CRISP-DM data mining technique to your selected domain. Specifically, gain insights into the data, formulate a set of hypothesizes, preprocess your data, and build a decision tree model. This assignment is graded on a scale of 100. For reference, when discussing the data mining process please reference CRISP-DM (shown below). You should submit the final Rapid Miner models. You will also include an analysis document. Figure 1: CRISP-DM ______________________________________ Step 1: Data preprocessing tutorials (15 points) Analysis Task: After you have installed RapidMiner, please complete the following data preprocessing tutorials (please note, the datasets you need for the tutorials are included in the RapidMiner download). https://academy.rapidminer.com/learn/video/data-preparation Upon completing each tutorial, briefly summarize what you did and discuss how it relates to what we have discussed in class. Step 2: Decision Tree tutorial (15 points) Analysis Task: Read the following documentation and complete the example at the end of this document: https://docs.rapidminer.com/latest/studio/operators/modeling/predictive/trees/parallel_decision_tree. html Again, briefly summarize what you did and discuss how it relates to what we have discussed in class. 1. Business Understanding 2. Data Understanding 5. Evaluation 4. Modeling 3. Data Preparation 6. Deployment Data

Step 3a: Data Understanding (10 points) Analysis Task: Download and open the Supermarket Transactions dataset. You should go through the dataset and think about each attribute. Then in your analysis document, for each attribute you should give its name, a description, its type (numeric or categorical), if you notice any outliers or missing values, and any other interesting things you notice. You should also address data reduction & attribute reduction. You should also describe the class labels and explain what they mean. Step 3b: Building your Model – Preprocessing (25 points) RapidMiner Task: Import your data into Rapid Miner. For each attribute, you should perform appropriate data pre-processing. Analysis Question: For each attribute, describe what sort of data preprocessing that you performed. For each attribute, you should describe and justify your decisions on handling missing data, anomalies, and normalization. (Feel free to explore other operators not demoed in class.) You should also mention if you chose to perform any data reduction. You should include screenshots in your explanation. Step 4: Modeling (25 points) RapidMiner Task: Select and build at least 2 models (e.g. variations of a decision tree). You can build different decision trees by modifying operators/parameters (e.g. changing the splitting criterion, applying or not applying pruning, etc. While it is up to you to decide how you want to build your models, you need to demonstrate that you went through a non-trivial modeling process to receive full credit. Analysis Question: Identify and explain all the work you did in the modeling task. You should justify your decisions. Be sure to include screenshots. Step 6: Reflection (10 points) Analysis Question: What did you learn from doing this assignment? Did it impact your perception of how BI techniques can be applied to data? If faced with a similar challenge in the future, how would you change your approach?

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

ITSCM 777 Project 1e

Related Documents