docx
keyboard_arrow_up
School
Jomo Kenyatta University of Agriculture and Technology *
*We aren’t endorsed by this school
Course
142
Subject
Information Systems
Date
Nov 24, 2024
Type
docx
Pages
8
Uploaded by jonahkemei
1
DAD 220 Project
Student Name
Course Name
Institution
03 December 2023
2
Scenario
“The product manager of Quantigration has asked your data analytics team for a report summarizing your analysis of the return merchandise authorizations (RMAs) that have been received. These are the same sets that you’ve already been working with. Your report should focus on summarizing the analysis and presenting your findings to the product manager.”
Directions
RMA Report
Introduction.
In response to the request of the Product manager. Our aim is to provide a comprehensive analysis of the return merchandise authorizations (RMAs) data. This will assist in provision of vital insights that can be used to streamline the operations of the company. 1.
Begin by writing SQL commands to capture usable data (which you’ve preloaded into Codio) for your analysis.
First is to show the databases that we have by using the command: show DATABASES;
We then choose the database that we are going to use – use QuantigrationRMA;
The execution is shown below:
3
The next step after the choosing of the database chosen is to load the data in the CSV files, Customers, Orders, and RMA into respective tables. *********
>LOAD DATA INFILE '/home/codio/workspace/Customers.csv'
->INTO TABLE Customers
->FIELDS TERMINATED BY ','
->LINES TERMINATED BY '\r\n';
*********
>LOAD DATA INFILE '/home/codio/workspace/Orders.csv'
->INTO TABLE Orders
->FIELDS TERMINATED BY ','
->LINES TERMINATED BY '\r\n';
**********
>LOAD DATA INFILE '/home/codio/workspace/rma.csv'
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
4
->INTO TABLE RMA
->FIELDS TERMINATED BY ','
->LINES TERMINATED BY '\r\n';
***********
The execution is shown in the snippet execution below.
2.
Specifically, the product manager wants you to analyze the following:
o
Analyze the number of returns by state and describe your findings in your report.
>SELECT customer.State, COUNT(r.RMAID) AS NumOfReturns FROM Customers customer
->JOIN Orders o ON customer.CustomerID = o.CustomerID ->JOIN RMA r ON o.OrderID = r.OrderID
->GROUP BY customer.State
->ORDER BY NumOfReturns DESC;
5
This analysis giving us returns by states shows us that the return by states are not the same. In
this analysis Columbus and Arlington have returns that are head above the rest. This information is important to direct the company to look at these leading states and get targeted strategies to address customer’s concerns.
o
Analyze the percentage of returns by product type
and describe your findings in your report.
>select Orders.SKU, COUNT(*) * 100 / (SELECT COUNT (*) FROM RMA) AS PERCENTAGE --
FROM RMA INNER JOIN Orders ON Orders.OrderID = RMA.OrderID
->GROUP BY SKU ORDER BY PERCENTAGE DESC;
->ORDER BY PERCENTAGE DESC;
The execution is seen below;
6
From analysis the highest percentage is 22.07% (for BAS-48-1c and the lowest with below 1% (BAS-24-1 C). For prioritization and improve the customer satisfaction quickly the company focuses on the products that show a bigger percentage of returns. In our case solving issues in the first two products with the highest returns will get us resolution of more than 38% of all returns. 3.
In your report, clearly summarize your analysis of the data for stakeholders. Include screenshots of the results of each query. When summarizing results, you may want to consider the following questions:
o
How does the data provide the product with usable information?
This information is helpful for the product managers to see where there are most returns and otherwise. With this information, the organization can get more information of why this is the
case. Studies can be done on places where there are most returns to understand the root cause and thereafter, present solutions to resolve the problem if the problem was in the product. The
defect in the product can be changes. Sometimes, the issues are with user training and the company can organize to do this.
o
What are the potential flaws in the data that has been presented?
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
7
When presenting data and analysis, the data used and analyzed more often would have potential flaws that should be understood so that any decisions that are made takes care of these flaws. For our case some of the potential flaws are listed below:
a)
Data Entry Errors – Typos and incorrect values are some common mistakes that can affect the conclusion or misinterpretation of results.
b)
Incomplete or Missing Data – If there missing data of some products or within some states, we can get skewed data that may influence decision making.
c)
Lack of context – Without understanding context we might get inferences wrong. For example, if in some state, the rate of returns is contributed mainly by non-
understanding of product usage by the users.
d)
Time period consideration – If data presented is for non-specified periods of time, the changes in preferences over time, company policies, and the product quality can affect
the results.
To reduce the effect of these potential flaws, it is important for data analyst to validate data, do data cleaning, and verify the process of data collection inclusive of contextualizing the information.
o
Are there any limitations on your conclusions, or any other ways of looking at it that you haven’t considered? Clearly communicate your findings to stakeholders.
Dear Stakeholders,
I appreciate that at this time we can present an analysis of RMAs (return merchandize authorizations) data. Through this data we can get valuable insights, but it is important to acknowledge some limitations as well as other ways of looking at the problem. This can influence the conclusions we draw from the results of our analysis.
Limitations
1.
Data completeness – The analysis was conducted using available data. Missing data may skew the results.
2.
Contextual Information – The analysis given in this report is based purely on quantitative data. Getting context might explain some of the situations that were noted in our data and give a better understanding.
3.
Changing time periods and criteria – there’s a possibility of changes in recording
criteria differently and having the data over different periods that might not give the same base information.
Alternative Perspectives
1.
External contributors – Our analysis does not consider external factors that include customer sentiments, competitor activities, and economic conditions that might contribute to return rates.
8
2.
Product complexity – Due to this customer might return as they are not familiar with how to use the product.