We chose to complete this project because it was beginner-friendly. Since our team is not as familiar with data science, this was an important factor in choosing our project.
What it does
Our project provides an in-depth analysis of Pizza Mamma Mia's day-to-day costs and revenue. We use factors such as customer type and cost factors to determine ways to improve customer satisfaction.
How we built it
The project was built using the Celonis Data Environment in which we were able to upload spreadsheets of Pizza Mamma Mia's pizza transaction history. From there, we used data science to represent the information in graphics including a pie chart and an OPAL table.
Challenges we ran into
One challenge that we ran into was determining how to use the key performance indicators. This prevented us from being able to easily create charts. We were able to overcome this challenge with the help of a Celonis representative.
Accomplishments that we're proud of
We are proud of our final graphic as it connects all the components of the data given. The user is able to test different variables to see their impact on the other dependent variables.
What we learned
We learned a lot about data mining and how to graphically represent data. For example, we learned which type of graph works best for specific variables. We also learned PQL, which is a publisher query language.
What's next for Pizza Mamma Mia Analysis
Our next step would be to create more graphics in order to test the correlation between variables from different spreadsheets. We would also like to implement the changes we suggested and determine whether or not they actually help.
This project uses data mining to improve day-to-day operations at Pizza Mamma Mia. We were tasked with determining which factors, such as customer type and cost factor, increase profitability for the company. The following information is what we have gathered. In the workspace that was created, it was insightful to see the different models that were populated from the data and witness the interconnection of the tables and data provided. The primary key, _CASE_KEY, in the table Pizza_Case was the connection as a foreign key in the Pizza_Event table. In a similar manner, Customer_ID was the foreign key in Pizza_Customer Info that connected the table to Pizza_Case. The biggest cause that we identified to have a negative impact on customer satisfaction is revenue. This is likely because customers are unwilling to pay a large amount for pizza. We noticed that the threshold seems to be around $20, below which customers are more satisfied and above which customers are dissatisfied. A way to combat this would be to offer a discount after spending more than $20. For example, for every $25 spent, a discount of $10 could be offered. In addition, we implemented a costs dropdown menu feature. For example, given customer type adult and a revenue of $30 if the costs were $8, the profit would be $22. The biggest cause that we identified to have a negative impact on profit is the distribution fee. The lower the distribution fee, the lower the profit. However, this does affect customer satisfaction inversely as when the distribution fee increases, customer satisfaction decreases. In order to combat this, Pizza Mamma Mia may want to increase distribution fees but should not increase them past a limit. A factor we found interesting was customer type. We expected customer type to hold a higher impact on profitability as students are usually more likely to spend less money than adults. However, the impact on company profitability based on customer type was negligible.