This is module 5 of 10 for the Business Analytics course.

Module 4 << | >> Module 6

Readings

Data Analytics in Management & Entrepreneurship

+

Self-Directed Learning

Search the internet for articles, other resources, and examples of how business analytics is used in management & entrepreneurship. See what you can learn from what others are saying. Management & entrepreneurship is an important application of analytics for monitoring and optimizing a company’s performance.

+

Discussion of Module Topic

Write down your thoughts and experiences while you’re learning. For this module, this should include writing about your experience of learning about the use of data analytics in management & entrepreneurship. Here are some prompts to get you started for writing about the module topic:

• Provide links to any useful and relevant resources about data analytics in management & entrepreneurship that you can find on the internet.
• Do you have any experience in using analytics in management?
• Can you find interesting examples of companies that have applied analytics to their management practices?
• How can analytics help a business improve its performance? (e.g, increasing revenue or reducing costs)
• What are the pros and cons of companies collecting and analyzing data about their employees?
• Can you find examples of startups whose business is providing data analytics?
• What do you think is the future of data analytics in management?

+

Discussion of Module Submission

For this module, the discussion of the submission should include writing about your experience of working on the submission. You should write about your experience working with the specific data, but also try to think about how this approach could be applied to other datasets. Here are some prompts to get you started for writing about it:

• How do you identify an outcome field in a dataset?
• How do you identify potential drivers of that outcome?
• How can statistics be useful for doing this type of analysis?
• Are there any Excel features that might be particular helpful for this?
• How can data visualization be used to highlight the relationship between drivers and outcomes?
• How do you feel about transitioning from descriptive analytics to diagnostic analytics?
• Why is the final step of drawing business insights so important?

+

Module Exercises

In this module submission, we will focus on outcomes and drivers.

• What is the key outcome field in your data?
• What are the key potential drivers of that outcome in your data?

In this analysis, your goal is to analyze which drivers are more or less important and whether the influence is positive or negative.

Understanding the drivers of past outcomes is the foundation of diagnostic analytics. It is a powerful exercise in management analytics, because it gives managers ideas about levers they can pull today to influence outcomes in the future.

Here are the instructions for the assignment:

We will be doing the case work in Teams under Files. The goal is to work with the data in Excel, interpret your findings in Word, and then present your findings in PowerPoint in the second session. Please see the files in the Management Case Work folder under Files in M5.

For some guidance on what you can do with the Telco Customer Churn data – here is more of an “assignment” from a previous quarter in which I used this data. You DO NOT need to follow these steps, but they will give you some ideas.

The steps for doing your own analysis of the management data are as follows:

1. Download this >> “Telco Customer Churn” data set << from Kaggle. The file is 978kB and you will be working with the full dataset. The first field, customerID, is the unique customer identifier. The key outcome variable in this data is “Churn.” A value of “Yes” indicates that the customer has discontinued their service with this telecommunications firm. The “Telco” firm is analyzing this data to improve customer retention (reduce churn). Every other field is a factor that could potentially increase or reduce likelihood of churn. The demographic factors are gender, seniorCitizen, Partner, and Dependents. Other factors are related to use of the services.
2. Save the raw data as the first worksheet in an Excel workbook (not csv!).
3. In your second worksheet, you should have your working data.
4. In the third worksheet, analyze the demographic factors relative to churn.
   1. The first step is to convert gender, Partner, and Dependents into 0/1 fields in your working data by creating new fields with the IF function. Set Female=1 and Yes=1.
   2. Create a PivotTable in this worksheet that has “Churn” for rows (Yes first, No second) and shows the average of the four factors in four columns. The averages should show three decimal places each. Write “Demographic Factors” over the table.
   3. Create a chart that visualizes your results.
   4. Write a statement that summarizes your views on which demographic factors are important to churn and the direction of influence.
5. In subsequent worksheets (two or more), provide additional analysis of the contractual features of the customer history. Note that tenure, MonthlyCharges, and TotalCharges are the only fields with continuous variables. Many of the service fields have more than two values. You will need to think about how to address this with an IF function. You should produce PivotTables and charts similar to the third worksheet to analyze these other potential factors.
6. In your final worksheet, include your “Final Analysis.” Think of this as the worksheet that you would show to your boss. It should include:
   1. One or two final charts that summarize all of your analysis. These are charts you would put in a presentation.
   2. Your answer to the question, “What are the factors driving churn?” (make sure to indicate the direction of the influence)
   3. A statement about actions that the management team should take based on your analysis.