You have a Fabric tenant that contains customer churn data stored as Parquet files in OneLake. The data contains details about customer demographics and product usage.
You create a Fabric notebook to read the data into a Spark DataFrame. You then create column charts in the notebook that show the distribution of retained customers as compared to lost customers based on geography, the number of products purchased, age, and customer tenure.
Which type of analytics are you performing?
The type of analytics being performed is descriptive analytics. This type of analysis focuses on summarizing historical data to understand what has happened. In the given scenario, the creation of column charts to show the distribution of retained and lost customers based on geography, the number of products purchased, age, and customer tenure is purely a descriptive task. It involves presenting past data in a visual format without attempting to explain the reasons behind the data or predict future trends.
Descriptive analytics tells what happened in the past, presenting it as numbers and visuals in reports and dashboards. Diagnostic analytics gives the reason why something happened. Predictive analytics determines the potential outcomes of present and past actions and trends. Prescriptive analytics offers decision support for the best course of action. Given the scenario in the question where data is read into a Spark DataFrame and column charts are created to show the distribution of retained customers compared to lost customers based on various factors, this falls under the definition of descriptive analytics. No future predictions or prescriptions are made, nor are reasons for the past events provided. Final Answer: The type of analytics being performed in the scenario described is descriptive analytics. https://www.selecthub.com/business-intelligence/predictive-descriptive-prescriptive-analytics/
Descriptive - it's just describing the customers, not saying why they stayed or left
A. diagnostic
https://azure.microsoft.com/es-es/blog/answering-whats-happening-whys-happening-and-what-will-happen-with-iot-analytics/ contains text "Examine data from multiple angles to understand why something is happening." for Diagnostic. In this case we are looking at data from multiple angles.
For me this is a diagnostic analysis, since we try to evaluate the root cause of churn (i.e. loosing customers).
Verified by ChatGPT
The creation of column charts to show the distribution of retained and lost customers based on various attributes is aimed at summarizing and visualizing historical data, which aligns with the principles of descriptive analytics. This is not enough to determine why something happened. It involves analyzing data to identify causes and correlations (Diagnostic Analytics).
sounds like B - descriptive analytics to me. comparing one metric against another by different categories. I cannot see that we are saying "why" did something happen, which means it would not be A
the terms as compared in the phrase tell use it is a descriptive comparaison : show the distribution. of retained customers as compared to lost customers based on geography,
I think that this chart tries to show why people are leaving, so I would go with A diagnostic
No. It's just describing what happened, not explaining why.
B. descriptive
A, diagnostic - why did it happen