Get startedGet started for free

Why did it happen?

1. Why did it happen?

Hi and welcome. In this video, we will focus on the diagnostic questions from various industries. That is, questions to understand why something happened. We will cover the analytical questions as well as the relevant techniques that can be used.

2. Understanding why something happened

Diagnostic analytics solutions can be invaluable for identifying the root causes of problems. Analyzing data and identifying patterns and anomalies, can help different types of organizations understand why certain events or outcomes occurred and help make data-driven decisions to optimize processes, improve efficiency, and reduce costs. Let’s see some practical applications.

3. Education industry example

In the education industry, a university wants to understand why they are experiencing a decline in program enrollment since last year. The analytics question is the following "What specific factors are contributing to the decline in enrollment rates based on this year's enrollment data?". Using drill-down analysis the team can break down the problem into smaller, more specific parts to identify the root cause. Assume that when breaking down the enrollment rates by the different programs, they have found that enrollment has declined significantly in the psychology program. Then hypothesis testing was used to validate whether factors such as program quality, program cost, or marketing efforts are contributing to the decline. The testing results have shown that the program cost was higher than other programs.

4. Manufacturing industry example

Another application of diagnostic analytics can be shared in manufacturing where the operations team wants to understand why the defect rate of their products is increasing. The analytical question is “Which manufacturing processes are contributing to the increase in defect rate?”. The analysts conducted a root cause analysis to identify the underlying reasons that led to an issue by considering various variables including the material quality levels, the machines, the operators, and the machine maintenance frequency. The results have shown that the root cause of the increase in defect rate is a malfunctioning machine in one of the production lines.

5. Marketing industry example

In the marketing industry, the marketing team wants to know why the open email rates are declining in their last email campaigns. To answer this, the analytics team forms the following question: Which factors contribute to the decline in email open rates? The analytics team used correlation analysis to analyze the relationship between email subject lines, email content, and send times with the open rates. Based on the heat map on the right, we can observe that the subject line "Get 20% off your next purchase" has higher open rates, especially during the evening sent times. In the end, it was revealed that recent changes in email subject lines and send times have contributed to the decline. Based on these findings, the team made data-driven recommendations to improve the email marketing strategy, by creating more targeted content, and optimizing send times.

6. Retail industry example

Lastly, let’s see the following scenario that applies to the Retail industry. A retail chain has seen a significant decline in sales in the past quarter and they want to understand why. The analytics team forms the following question: What is the relationship between the decline in sales and the following variables: price change rate, product stock availability rate, and marketing expenditure? The team analyzes the data using multiple regression analysis to identify the variables that are contributing the most to the decline in sales. After running the regression analysis, the results show that the recent price increases have the strongest correlation with the decline in sales. Another finding was that when there is a stock unavailability of popular products, sales also decline. Based on these findings, the company decides to focus on improving product stock availability and developing more effective pricing strategies.

7. Let's practice!

Let's check your understanding!