Customer Segmentation for Targeted Campaigns with Markov's Data Analytics Tool

As a marketer, understanding your customer base is key to running effective campaigns. But diving into your data to uncover insights can be overwhelming, especially if you are not a data expert. That's where Markov's Data Analytics Tool comes in!

With this tool, you can easily analyze your retail data and segment your customers to create personalized marketing campaigns—all without needing any technical skills. Whether you are just starting or have some experience, this tool is designed to help you make smarter, data-driven decisions quickly.

In this tutorial, you will learn to use Markov's Data Analytics Tool to segment your customers using a sample retail dataset. This dataset includes the following columns: Transaction ID, Date, Customer ID, Gender, Age, Product Category, Quantity, Price per Unit, and Total Amount.

You will explore the insights below using three different modes: Text Mode, Text-SQL Mode, and SQL Mode.

• Segmenting by demographics (gender and age)
• Identifying high-value customers
• Analyzing product preferences
• Tracking purchasing frequency
• Assessing sales performance by category

Let’s see how you can use these modes to uncover the above insights for your campaigns.

📘

Note

The main goal of this tutorial is to show you how to use the data analytics tools, rather than diving too deeply into customer segmentation analysis.

Mode 1: Text (Simple and quick insights)

Text Mode is perfect if you want quick insights without writing any code. Just ask questions in simple, everyday language, and MarkovML will give you the answers. This is ideal for marketers who want fast, straightforward analysis.

1. Segment by Demographics: Use Gender and Age to Group Customers

To start, let’s break down your customers by gender and age. This will help you understand who your customers are so you can create targeted campaigns. For example, if you know women aged 25-34 are your biggest demographic, you can create campaigns that speak directly to their needs and interests.

Sample question:How many male and female customers are in each age group?

2. Identify High-Value Customers: Find Customers Who Spend the Most

Next, let's identify your high-value customers—those who are spending the most. These are the customers you want to focus on with exclusive offers. For instance, if you know these high-value customers, you can reward them with exclusive discounts or early access to sales.

Sample question: Who are the top customers by total spending?

3. Analyze Product Preferences: What Products Do Customers Like?

You can also analyze which products are popular with your customers, based on their demographics. This helps you promote the right products to the right people. For example, if this group loves fitness products, you can design an email campaign with promotions for fitness-related items.

Sample question: What products do women in the 25-34 age group prefer?

4. Track Purchasing Frequency: How Often Do Customers Buy?

Tracking how often customers make purchases helps you plan promotions and loyalty programs. For example, you can send a "Buy 1, Get 1 Free" offer to regular buyers to boost sales.

Sample question: How often do customers buy more than once a month?

In the case of the sample data you are using, no customer has bought the product more than once. This means more effort should be put into sales.

Mode 2: Text-SQL Mode (Simple English to SQL)

Text-SQL Mode allows you to ask questions in plain English and get SQL queries automatically generated for you. This is perfect for marketers who have some familiarity with SQL but prefer to avoid writing complex queries from scratch.

1. Segment by Demographics: Group Customers by Gender and Age

This query groups customers by Gender and Age Group, giving you a clear picture of who your customers are. You can use these insights to create targeted ads or campaigns.

Sample question: How many male and female customers are there in each age group?

Generated SQL query and result:

SELECT 
    "Gender", 
    "Age", 
    COUNT(DISTINCT "Customer ID") AS customer_count
FROM 
    "retail_sales_dataset 2"
GROUP BY 
    "Gender", 
    "Age"
ORDER BY 
    "Age", 
    "Gender";

2. Identify High-Value Customers: Find Top-Spending Customers

This query lists the top 10 customers based on their Total Amount spent. Use this information to create special rewards or offers for your best customers.

Sample question: Who are the top 10 customers by total spending?

Generated SQL query and result:

SELECT "Customer ID", SUM("Total Amount") AS total_spending
FROM "retail_sales_dataset 2"
GROUP BY "Customer ID"
ORDER BY total_spending DESC
LIMIT 10;

3. Analyze Product Preferences: Most Popular Products by Age Group

This query will show the Product Category with the highest purchase count for customers aged 25-34. You can tailor your marketing campaigns around the most popular products for this group.

Sample question: What products are most popular among customers aged 25-34?

Generated SQL query and result

SELECT "Product Category", SUM("Quantity") AS total_quantity
FROM "retail_sales_dataset 2"
WHERE "Age" BETWEEN 25 AND 34
GROUP BY "Product Category"
ORDER BY total_quantity DESC;

4. Track Purchasing Frequency: Customers Who Buy More Than Once a Month

This query will give you the names of the customers who make repeat purchases. Use this data to create loyalty programs or incentives for these frequent buyers.

Sample question: Total number of customers with multiple purchases in a month

Generated SQL query and result:

SELECT COUNT(DISTINCT "Customer ID") AS total_customers
FROM (
    SELECT "Customer ID", strftime('%Y-%m', CAST("Date" AS DATE)) AS month_year
    FROM "retail_sales_dataset 2"
    GROUP BY "Customer ID", month_year
    HAVING COUNT(DISTINCT "Transaction ID") > 1
) AS multiple_purchases;

Mode 3: SQL Mode (Advanced Queries)

SQL Mode allows you to write your own custom queries and execute them directly. This is great for advanced users who need highly customized insights.

1. Segment by Demographics: Group Customers by Gender and Age

Example: SQL code to find the total number of male and female customers with the age range of 18-24 and 25-34.

SELECT 
    "Gender",
    CASE 
        WHEN "Age" BETWEEN 18 AND 24 THEN '18-24'
        WHEN "Age" BETWEEN 25 AND 34 THEN '25-34'
    END AS age_range,
    COUNT(DISTINCT "Customer ID") AS total_customers
FROM 
    "retail_sales_dataset 2"
WHERE 
    "Age" BETWEEN 18 AND 34
GROUP BY 
    "Gender", age_range;

2. Identify High-Value Customers: Top-Spending Customers

Example: SQL for top 10 customers by total spending

SELECT "Customer ID", SUM("Total Amount") AS total_spending
FROM "retail_sales_dataset 2"
GROUP BY "Customer ID"
ORDER BY total_spending DESC
LIMIT 10;

3. Analyze Product Preferences: Popular Products by Age Group

Example: SQL to find products that are most popular among customers aged 18-24.

SELECT "Product Category", SUM("Quantity") AS total_quantity
FROM "retail_sales_dataset 2"
WHERE "Age" BETWEEN 18 AND 24
GROUP BY "Product Category"
ORDER BY total_quantity DESC;

4. Track Purchasing Frequency: Customers Who Make Repeat Purchases

Example: SQL to find the total number of customers with multiple purchases in a month

SELECT COUNT(DISTINCT "Customer ID") AS total_customers
FROM (
    SELECT "Customer ID", strftime('%Y-%m', CAST("Date" AS DATE)) AS month_year
    FROM "retail_sales_dataset 2"
    GROUP BY "Customer ID", month_year
    HAVING COUNT(DISTINCT "Transaction ID") > 1
) AS multiple_purchases;

Leveraging Insights for Targeted Marketing

After gathering insights from the dataset, you can use them in your marketing strategy:

• Demographic Segmentation: Use the gender and age breakdown to create personalized campaigns.
• High-Value Customers: Offer exclusive rewards or VIP status to your top spenders.
• Product Preferences: Promote products that customers in specific age groups or genders are most interested in.
• Purchasing Frequency: Engage repeat buyers with tailored offers or loyalty programs.

That's it!

With Markov's Data Analytics Tool, you don't need to be a data expert to uncover valuable insights from your retail dataset. Whether you are using Text Mode for quick insights, Text-SQL Mode for more control, or SQL Mode for advanced queries, this tool is flexible enough to suit your needs. By segmenting your customers, you can create smarter, more effective marketing campaigns that drive better results.

Ready to get started? Upload your dataset, choose your query mode, and start exploring insights today!