Overview

Business is booming. After a famous fashion influencer Tweeted about the company in Q2 2020, demand has been off the charts. The company has not been able to keep up with demand. Jimmy, the CEO, loves the publicity and mystery caused by the sold-out shoes with long wait times. However, he is concerned that he is missing out on sales and that customers could quickly sour on Jimmy Shoo shoes if he doesn’t figure out a way to increase production quickly.

About the Dataset

Jimmy Shoo Limited has cobbled together three tables from across the organization and put them into a single Excel file for our convenience.
Those tables are: Production – contains data for each order produced in the last four quarters, including who produced the pair of shoes and how much time it took. Employees – contains the list of 30 employees first names and employee ID numbers. Sales – contains a snapshot of the unit sales over the last four quarters (note: the units sold will differ from the units produced when production capacity is exceeded).

Challenge Prompt (Recommended Analysis)

Since we don’t know whether recent demand will be long-lasting, I want to investigate how Jimmy Shoo Limited might increase the output of shoes without having to expand to a new factory.
I will use a Power BI report to answer these questions:

1. Has output truly plateaued? Is it due to slower production?
2. What could we look at improving? Some ideas include:
3. Have top-producing shoemakers share efficiency tips with low-producing shoemakers.
4. Hire operations consultants to redesign our most time-consuming production phase.
5. Abandon the current Job Production method and adopt a different overall production method.
6. For promising ideas, we need to quantify the impact. In other words, if the idea works, show how much output would increase.

ETL and Data Modeling

Loading a dataset with more than 30 employees and 4773 orders of Jimmy Shoo shoes into to power bi. I used Power Query for the data cleaning and removal of columns I will not be using for the analysis. This made the dataset easier to use in Power BI for the analysis.

Insights

1. Adopting an assembly line approach is estimated to reduce the total production time by 30%.
2. The new system would take the 10 fastest employees in each phase (cutting, stitching and finishing) to achieve an Estimated Total Production Time of 8.41 hours.
3. Under this approach, we are estimating to shave 2.5 hours from the Total Production time.
4. This will enable Jimmy Shoo to produce over 400 more orders per quarter.
5. This new system will allow Production to meet the expected demand for the following quarter (Q1).