In this case study, students will continue their work from Assignment #$1,$ focusing on developing a functional

RapidMiner process flow to cleanse and repair the data obtained from the open data repository. The goal is to

prepare the data for further analysis, ensuring accuracy and reliability in diagnostic analytics. Students will delve

into the practical application of diagnostic analytics by focusing on the cleansing and repair of data obtained

from open data repositories using RapidMiner. Diagnostic analytics involves analyzing historical data to identify

patterns, anomalies, and root causes of problems or issues within a system. Through this case study, students

will gain hands$-$on experience in preparing data for analysis, ensuring its accuracy and reliability.

Review Target Company$/$Organization$/$Business Type:

o Students will revisit the target organization selected in Assignment #$1,$ ensuring a clear

understanding of its industry, operations, and objectives. For example, if the chosen organization

is a luxury automobile seller, students will research the automotive industry, market trends, and

customer preferences.

$2.$ Review Target City and Data Set:

o Students will reevaluate the chosen city with its open data repository, verifying the availability of

relevant datasets for their target organization. They will explore datasets related to sales,

customer demographics, or market trends.

$3.$ Define Objective for Data Cleansing:

o Students will define the objective for data cleansing, identifying specific issues or challenges

within the dataset that need to be addressed. For instance, if the dataset contains missing values

or inconsistencies, the objective could be to clean and prepare the data for predictive modeling.

$4.$ Update Rationale and Explanation:

o Students will update their rationale, explaining why each selected operator is necessary for

cleansing the data. They will justify the order of operators based on the logic of data preparation

and the requirements of subsequent analysis. For example, they might use the $$Replace Missing

Values$$ operator to handle missing data and the $$Filter Examples$$ operator to remove outliers.

$5.$ Research and Apply RapidMiner Operators for Data Cleansing:

o Students will research and understand various RapidMiner operators related to data

preprocessing, merging datasets, and handling incomplete or erroneous data. They will explore

the RapidMiner documentation and other resources to familiarize themselves with the

functionalities of different operators.

o Using RapidMiner, students will apply appropriate operators to cleanse and repair the data. They

will document each step thoroughly, explaining the purpose of each operator and how it

contributes to the overall data preparation process.

$6.$ Design Process Flow Diagram in RapidMiner:

o Using RapidMiner, students will create a detailed process flow diagram demonstrating how they

would handle and merge datasets to cleanse the data. The diagram should include start and end

points, each step represented by appropriate symbols or shapes, connections between steps

indicating the flow of data, and annotations or descriptions for each step.

o Students will ensure that the process flow reflects the sequence of operators used for data

cleansing and repair. They will document all ETL $($Extract$,$ Transform, Load$)$ steps taken in

cleansing the data.