100 prompts for Data Analytics

 Note: The prompts in this cheat sheet are for reference only. Use them as inspiration to create your own, and refer to our article for guidance on writing effective prompts. Since these were not written by professional developers, please review and validate before applying in practice.


Data Cleaning & Preparation

1.       Clean a dataset with missing values using imputation methods.

2.       Remove duplicate rows from a customer transaction dataset.

3.       Standardize inconsistent date formats in a sales dataset.

4.       Normalize numerical columns in a dataset for better analysis.

5.       Detect and remove outliers in a dataset.

6.       Convert categorical variables into numerical form for analysis.

7.       Handle null values in multiple columns efficiently.

8.       Merge two datasets with different column names but same data.

9.       Split a column containing full names into first and last names.

10.   Convert all currency values in a dataset to USD.

Exploratory Data Analysis (EDA)

11.   Summarize key statistics of a dataset (mean, median, mode).

12.   Create a correlation matrix for all numeric variables.

13.   Plot a histogram of customer ages in a dataset.

14.   Visualize the distribution of sales by region.

15.   Identify top 5 most frequent product categories.

16.   Compare male vs female purchase patterns.

17.   Find the top 10 most profitable customers.

18.   Identify seasonal trends in time-series data.

19.   Detect skewness in the dataset.

20.   Create a boxplot for sales across product categories.

SQL Queries

21.   Write an SQL query to find top 5 selling products.

22.   Find customers who made more than 10 purchases.

23.   Retrieve total sales for each region.

24.   Get the average transaction value by customer.

25.   Find employees who earn above the company average salary.

26.   List all customers who never placed an order.

27.   Write a query to find the second-highest salary.

28.   Join orders and customer tables to display customer names with their purchases.

29.   Calculate month-over-month growth in sales.

30.   Find duplicate records in a table.

31.   Retrieve customers who purchased both Product A and Product B.

32.   Write a query to calculate cumulative sales.

33.   Find the percentage of total revenue contributed by each product category.

34.   Identify the top 3 employees by sales performance.

35.   Get the list of inactive customers in the last 6 months.

Python for Data Analysis

36.   Write Python code to import a CSV file using pandas.

37.   Create a bar chart of sales by product category.

38.   Calculate moving average of sales over 7 days.

39.   Use pandas to group data by region and calculate sum of sales.

40.   Implement linear regression on a dataset.

41.   Create a scatter plot of advertising spend vs sales.

42.   Write Python code to detect outliers using IQR.

43.   Build a heatmap of correlation using seaborn.

44.   Automate data cleaning with a function.

45.   Generate a time-series plot of monthly revenue.

46.   Merge customer and order datasets using pandas.

47.   Create a pivot table using pandas.

48.   Write Python code to find the most common words in product reviews.

49.   Automate a weekly sales report in Python.

50.   Build a dashboard using Plotly/Dash.

Excel/Google Sheets

51.   Create a pivot table for sales by region and category.

52.   Write a VLOOKUP formula to fetch customer details.

53.   Use conditional formatting to highlight top 10% sales.

54.   Create a line chart for monthly revenue trends.

55.   Build a dashboard showing KPIs (sales, profit, customer count).

56.   Write an IF formula to categorize customers as high/medium/low spenders.

57.   Calculate CAGR (compound annual growth rate) in Excel.

58.   Use INDEX-MATCH instead of VLOOKUP for better performance.

59.   Create a histogram of customer age distribution.

60.   Automate monthly reporting using Excel macros.

Visualization & Storytelling

61.   Build a sales performance dashboard in Power BI/Tableau.

62.   Create a funnel chart for customer journey stages.

63.   Visualize customer churn rate over time.

64.   Create a heatmap of sales by region and product.

65.   Build a tree map of revenue contribution by product category.

66.   Show YOY (year-over-year) growth using line charts.

67.   Create an interactive dashboard with slicers.

68.   Use storytelling with charts to explain sales decline.

69.   Build a cohort analysis visualization.

70.   Create a KPI dashboard showing targets vs actuals.

Business Problem Solving

71.   Analyze why sales dropped in Q3 compared to Q2.

72.   Find the most profitable customer segment.

73.   Identify factors contributing to customer churn.

74.   Recommend products for cross-selling opportunities.

75.   Analyze the effectiveness of marketing campaigns.

76.   Calculate customer lifetime value (CLV).

77.   Measure ROI of digital ad campaigns.

78.   Identify bottlenecks in supply chain data.

79.   Analyze employee performance based on KPIs.

80.   Forecast next quarter’s revenue using past data.

Advanced Analytics & ML

81.   Train a logistic regression model to predict churn.

82.   Build a decision tree to classify customer behavior.

83.   Perform clustering to segment customers.

84.   Run sentiment analysis on customer reviews.

85.   Apply ARIMA model for sales forecasting.

86.   Build a recommendation system for products.

87.   Detect anomalies in transaction data.

88.   Train a random forest model for fraud detection.

89.   Use NLP to categorize customer complaints.

90.   Predict stock prices using machine learning.

Career & Portfolio

91.   Write a case study of your analysis project.

92.   Create a portfolio dashboard in Tableau/Power BI.

93.   Share your Python EDA notebook on GitHub.

94.   Build a blog post explaining one of your data projects.

95.   Present a storytelling case using PowerPoint.

96.   Analyze a Kaggle dataset and publish insights.

97.   Document best practices in SQL queries.

98.   Record a walkthrough video of your project.

99.   Write a LinkedIn post summarizing your project insights.

100.           Create a resume-ready project demonstrating end-to-end data analysis.

No comments:

Post a Comment

Beginners Guide for prompt engineering

What is prompt engineering? Prompt engineering is no longer just a trendy skill—it has become a high-demand, high-value competency in the A...