Byleveraging insights and data-driven solutions, marketing campaigns can be fine-tuned andoptimized to better meet customer needs, increase engagement, and achieve higher sales.The combi
Overview
Marketing campaigns are essential for promoting a company's products and services, aiming to raise awareness, generate leads, and boost sales Their primary goal is to foster positive customer engagement, build brand trust, and encourage purchasing behavior In today's data-driven landscape, the role of a Data Analyst is vital for the successful execution of these marketing initiatives.
A Data Analyst in marketing campaigns is crucial for assessing participation and effectiveness by analyzing data and metrics They measure engagement, reach, and impact on the target audience through key performance indicators (KPIs) such as website traffic, conversion rates, click-through rates, social media interactions, and customer feedback.
Evaluating the success of past campaigns is crucial for Data Analysts, as it involves analyzing historical data to uncover trends and insights that enhance future marketing efforts By recognizing effective strategies and areas for improvement, they provide data-driven recommendations to optimize marketing approaches This integration of data and marketing enables campaigns to be refined, better addressing customer needs, increasing engagement, and ultimately driving higher sales The synergy between data analysis and marketing fosters powerful campaigns that promote growth and elevate sales revenue.
Data Analysts are essential in developing data-driven strategies for marketing campaigns They utilize their analytical expertise to uncover opportunities and enhance performance by segmenting audiences, personalizing messages, optimizing advertising budgets, and discovering new channels to engage the target market By leveraging data to guide decision-making, Data Analysts empower marketing teams to make informed choices that boost campaign effectiveness.
In summary, the role of a Data Analyst is essential in marketing campaigns They gauge participation, assess past campaign success, and propose data-driven solutions By
1 leveraging data and analytics, they help companies optimize their marketing strategies,enhance customer engagement, and drive business growth.
State the Problem & Questions
Our team is committed to helping businesses boost their revenue through detailed solutions and answers to various challenges We specialize in sales optimization, customer retention strategies, market analysis, and pricing optimization Utilizing data-driven insights, we empower businesses to make informed decisions and implement effective strategies, maximizing their revenue potential Our objective is to deliver practical, tailored solutions that address each business's unique needs, driving growth and increasing profitability.
1 What does the average customer look like?
- What are the demographic characteristics of the average customer? (age, gender, location)
- Are there any specific psychographic traits or behaviors that define the average customer?
- Are there any noticeable differences in the average customer across different product lines or target markets?
2 Best-performing products and revenue channels?
- Which products or services consistently generate the highest sales and revenue?
- What are the distinguishing features or factors that make these products stand out?
- Are there any noticeable differences in performance across different revenue channels?
- Which marketing campaigns have achieved the greatest success?
- Which channels and mediums (e.g., social media, email marketing, content marketing) have been most effective in reaching the target audience?
- Are there any specific elements or strategies that have contributed to the success of these campaigns?
Application tools in the project
Dataset
Source of dataset
The dataset is available on Kaggle and contains data related to customer for Machine Learning. https://www.kaggle.com/code/rohitshirudkar/customer-personality-data-analysis-eda/ output
Overview
Customer personality analysis enables businesses to gain in-depth insights into their ideal customers by examining behaviors, needs, and motivations beyond mere demographics Utilizing machine learning techniques on datasets, such as the one from Kaggle with 2,240 records and 29 pertinent columns, companies can uncover valuable information that supports data-driven decision-making.
Benefits of Customer Personality Analysis:
Targeted Marketing: Instead of relying on broad brushstrokes, businesses can pinpoint specific customer segments most likely to resonate with new products or campaigns.
Effective product development hinges on a deep understanding of customer preferences and pain points By aligning products and services with the specific needs of various market segments, businesses can enhance product-market fit and significantly boost customer satisfaction.
Enhanced Customer Relationships: A deeper understanding of customers enables businesses to personalize interactions and communications, fostering stronger relationships and brand loyalty.
The Kaggle dataset, featuring 2,240 records and 29 diverse data points, serves as a powerful tool for customer personality analysis This extensive resource enables businesses to gain valuable insights that can be transformed into effective strategies for targeted marketing, improved product development, and enhanced customer relationships.
Customer personality analysis provides a crucial edge in the competitive market landscape Utilizing machine learning and datasets from platforms like Kaggle allows businesses to deeply understand their customers, facilitating the customization of products and marketing strategies for optimal effectiveness.
1.2.1 The reason why choose Customer Personality Data Analysis.
In the fast-paced market of today, businesses must go beyond basic demographic knowledge to succeed By exploring customer personality, companies can uncover crucial insights into preferences, behaviors, and motivations This in-depth understanding allows for the development of highly personalized and targeted strategies that resonate with consumers.
Crafting hyper-personalized experiences involves tailoring products and marketing campaigns to match individual customer personalities By analyzing customer personality data, businesses can identify what resonates with different segments, enabling the creation of personalized experiences that significantly boost engagement and conversion rates.
Segment for Strategic Success: Gone are the days of one-size-fits-all approaches.
Personality data enables the segmentation of customers into specific groups with common characteristics, allowing for the creation of tailored strategies that address the unique needs and preferences of each segment, ultimately enhancing the effectiveness of your marketing efforts.
Understanding the personality traits that influence customer loyalty is crucial for retention By tailoring interactions and offerings to meet individual preferences, businesses can strengthen relationships, ultimately fostering brand loyalty and encouraging repeat business.
Gain a Competitive Edge: In a crowded marketplace, differentiation is key.
Businesses that effectively connect with their customers on a personal level differentiate themselves in the market Analyzing customer personality data provides critical insights that enable data-driven decision-making, enhancing product development, marketing strategies, and customer service This approach eliminates guesswork, allowing companies to achieve measurable results Investing in customer personality data analysis not only deepens customer understanding but also fosters stronger relationships, ultimately driving success in a competitive landscape.
Before delving into intricate visualizations, we aim to ensure the quality of our data using Python software This preliminary step is essential to gain a more profound
6 comprehension of how we should effectively handle our data in subsequent stages of the project.
The `Year_Birth` variable provides essential data regarding customers' birth years, which can be transformed into their ages by subtracting this value from the current year, assumed to be 2022 This transformation from raw data to age is crucial for analyzing customer demographics, as it allows for a deeper understanding of purchase patterns, marketing preferences, and the impact of life stages on customer behavior.
Education data provides insights into customers' academic backgrounds, measuring the total years of education completed This quantitative approach goes beyond simple classifications, enabling analysis of correlations between education levels and factors such as income, spending habits, and responses to marketing efforts By understanding how educational attainment influences these aspects, businesses can develop more targeted and effective customer engagement strategies.
The marital status of customers is categorized into two groups: "In couple" and "Alone." This simplification enhances data analysis while preserving essential insights By distinguishing between coupled and single customers, businesses can develop targeted marketing strategies and product offerings that cater to the distinct needs and desires of each segment.
The "Spending" composite variable offers a comprehensive view of customer income and overall financial behavior, enabling the identification of high-value customers and the analysis of spending patterns By examining correlations between income, demographics, and purchasing habits, businesses can optimize resource allocation and implement targeted marketing strategies effectively.
The "Has_child" binary variable effectively captures familial status by combining "Kidhome" and "Teenhome" into one indicator, providing insights into whether a customer has children This seemingly straightforward feature opens up numerous segmentation opportunities, enabling businesses to develop targeted marketing strategies, personalized product recommendations, and customer service approaches that align with the unique needs and preferences of each segment.
1.2.2 Data types and data completeness.
Figure 1.2.2.1 Check Information of Dataset
The DataFrame comprises 2,240 observations, numbered sequentially from 0 to 2,239 It features 34 columns, with each column representing a distinct variable or attribute within the dataset.
Data Preprocessing
During the feature engineering phase of the Marketing Campaign Analysis project, we focus on converting raw data into valuable and understandable variables that accurately reflect our customers' profiles and behaviors This critical step significantly impacts the quality of insights obtained from the data and enhances the overall effectiveness of our marketing strategies.
The conversion of raw data into insightful features enables a comprehensive understanding of customer behaviors and preferences, which is crucial for customizing marketing strategies and enhancing campaign effectiveness.
New Variables Created and Their Significance:
- Age: Derived by subtracting the birth year from the current year (2022), the
The 'Age' variable provides valuable insights into customer demographics, enabling effective market segmentation Understanding customers' ages allows businesses to customize marketing campaigns for specific age groups, as spending behaviors and interests frequently change with age.
- Spending: By summing amounts spent across six product categories, the
The 'spending' variable offers valuable insights into a customer's total expenditure, which is crucial for identifying high-value customers and analyzing overall spending trends This understanding facilitates effective resource allocation and enhances personalized marketing strategies.
- Marital_Situation: Simplifying various marital statuses into two categories
The distinction between being 'In couple' and 'Alone' enables a more precise examination of how marital status impacts spending habits and reactions to marketing campaigns This strategic simplification highlights the importance of relationship status, which can greatly influence consumer purchasing decisions and priorities.
The binary indicator "Has_child" provides essential insights into customer segmentation by revealing whether a customer has children Understanding this aspect can significantly influence marketing strategies, as customers with children often have distinct needs and spending priorities, which can affect their responses to various products and campaigns.
Measuring education in terms of years provides valuable insights into the connections between education, income, and spending behaviors This approach is essential for comprehensively understanding customer profiles and crafting targeted messages that effectively engage individuals from diverse educational backgrounds.
- Calculating Age: The transformation from 'Year_Birth' to 'Age' makes the data more relatable and easier to work with, as age is a more direct measure of customer demographics.
- Summing up Spending: Creating a single 'Spending' figure from multiple categories provides a more holistic view of a customer's purchasing behavior, facilitating the identification of overall spending trends and high- potential customers.
- Categorizing Marital Status: Simplifying the 'Marital_Status' into two broad categories reduces complexity and allows for more straightforward comparisons and analysis of how relationship status affects customer behavior.
The 'Has_child' variable serves as a crucial binary indicator, offering immediate insight into whether a customer has children This information is vital, as it can greatly affect spending behaviors and the effectiveness of targeted marketing campaigns.
Transforming the 'Education' category into a numerical 'Educational_years' variable enables advanced statistical analyses and correlations, uncovering valuable insights into the influence of education on customer behavior and preferences.
The development and transformation of key variables yield a dataset that offers a deeper understanding of the customer base, facilitating more accurate segmentation and enhancing the prediction of customer behavior By analyzing factors such as age, spending habits, marital status, parental status, and education, businesses can design marketing campaigns that effectively resonate with their target audience This process of feature engineering is essential for converting raw data into actionable insights, ultimately boosting campaign performance and customer engagement, and driving the success of marketing initiatives and business strategies.
The statistical summary offers valuable insights into the customer database, playing a crucial role in analyzing marketing campaigns Understanding the key characteristics and trends within the data is essential for crafting targeted marketing strategies.
The data encompasses a diverse age range from 26 to 129 years, with an average age of 53 and a standard deviation of approximately 12 years This variety highlights the need for marketing strategies that cater to a wide array of age-related interests and behaviors.
The income distribution shows a significant disparity, with a mean income of $52,247 compared to a median of $51,300, highlighting a right-skewed distribution An outlier earning $666,666 notably distorts the average, suggesting that a small group of customers possesses much higher income levels than the overall customer base.
- Spending: Over the last two years, customers have spent an average of
$605.80, though the median value of $396 suggests that spending is also right-skewed The maximum reported spending of $2,525 points to a segment of high-spenders within the customer base.
The average educational attainment among customers is 14.5 years, which is comparable to holding a Bachelor's degree This range varies from 5 to 21 years, indicating that most customers possess a significant level of formal education.
Insights from 5-Number Summary and Distributions:
The analysis of income and spending reveals a disparity, indicating that while most customers engage in moderate spending and earning, there exists a notable affluent minority This finding can inform marketing strategies, enabling teams to create premium products tailored specifically for this affluent segment.
Visual Exploratory Data Analysis (EDA)
1.4.1 Diploma Distribution by Income Level
The histogram depicting the correlation between income levels and educational attainment provides valuable insights into the economic demographics of the dataset It features income on the horizontal axis and the relative frequency of individuals within each income bracket on the vertical axis, with distinct colors representing different education levels.
- A significant proportion of individuals in the lower income range hold Basic or 2n Cycle qualifications.
- Those earning between 0 and 20k predominantly consist of Basic diploma holders, who represent 68% of this income segment, followed by 2n Cycle holders at 14%.
- Higher incomes are more commonly associated with advanced degrees such as Master's and Ph.D.
- Among those with incomes between 140k and 160k, Ph.D holders constitute the largest portion at 48%, with Master's degree holders at 31%.
Targeting Based on Education and Income:
- The data suggests that marketing premium products might be particularly effective among individuals with higher educational qualifications, who are also associated with higher income levels.
- More economical products might be better suited for promotion among those in the lower income brackets, where Basic and 2n Cycle qualifications are more prevalent.
- By understanding the income distribution across different educational backgrounds, marketing efforts can be more strategically aligned with the expected financial capacity and interests of various segments.
- This analysis can inform how to craft and position marketing messages, creating personalized experiences that resonate with the target audience and have a higher likelihood of conversion.
In conclusion, the histogram's visual representation significantly improves the understanding of demographic profiles by income level, making it an essential tool for refining marketing strategies By identifying these trends, marketers can customize their campaigns to better match the spending power and preferences of different customer segments, ultimately enhancing the effectiveness and impact of their marketing efforts.
Our project examines the relationship between education and income to enhance our marketing strategies and address potential economic disparities The accompanying bar chart displays average income based on educational qualifications, with education represented on the x-axis and average income on the y-axis, allowing for an easy comparison of income across different education levels.
Individuals with a Ph.D degree earn an average income of $56,161, highlighting the strong correlation between higher education and increased earning potential In contrast, those with only basic education have a significantly lower average income of $20,306, suggesting limited earning opportunities for individuals with less formal education Graduates and Master's degree holders experience average incomes that rise progressively with their education levels, further emphasizing the financial benefits of advanced degrees.
The implications of these findings are multifaceted:
A well-crafted marketing strategy should leverage data to align promotional efforts with the financial capabilities linked to varying educational levels Target luxury products and services at individuals with advanced degrees, as they generally possess higher incomes Conversely, focus on more affordable offerings for those with basic educational backgrounds, making them more appealing and accessible.
- Content Design: The complexity of the marketing content can be adjusted to suit the educational background of the target audience This means creating
20 more intricate and detailed content for audiences with higher education and simpler, more accessible content for those with lower levels of education.
Insights from the analysis reveal significant income disparities associated with educational attainment, indicating the need for social initiatives The company has the opportunity to implement corporate social responsibility (CSR) activities focused on educational support, which could effectively bridge the income gap and enhance the earning potential of individuals with lower educational backgrounds.
In summary, the analysis of the project indicates a strong correlation between higher education and increased average income, which is crucial for developing targeted marketing strategies, producing relevant content, and informing social responsibility efforts aimed at tackling educational and income disparities.
Our project's scatter plot with a regression line serves as a visual analysis of the relationship between customers' income and their spending patterns.
The scatter plot illustrates the relationship between customer spending and income, with individual points representing each customer's data A regression line, or line of best fit, indicates a general trend, revealing a positive correlation: as customer income rises, their spending also tends to increase.
The analysis indicates that higher-income individuals typically exhibit greater spending power, resulting in increased discretionary spending Additionally, the clustering of data points near the regression line reinforces this trend.
21 us an indication of the correlation's strength—a denser cluster of points suggests a stronger and more reliable relationship between income and spending.
Effective marketing segmentation is crucial for targeted campaigns, particularly for luxury products By focusing on higher income brackets, brands can enhance their marketing strategies, as these customers typically exhibit greater spending capabilities This targeted approach ensures that marketing efforts resonate more with the right audience, maximizing campaign effectiveness.
- Predictive Analytics: Income's predictive power can be harnessed for forecasting future spending behaviors, which is integral for planning marketing budgets and projecting revenue streams.
An effective inventory and product strategy hinges on understanding the relationship between income and spending, which informs the diversity and volume of products available By aligning supply with customer demand, businesses can optimize their offerings and prevent overstocking items that may not appeal to specific income groups.
In conclusion, analyzing spending patterns by income is essential for effective strategic marketing planning and resource allocation This approach highlights the importance of understanding the financial capabilities of various customer segments, allowing businesses to create marketing campaigns and product lines that are not only efficient but also align with the spending behaviors of their target audience.
Figure 1.4.3.1 Positive Correlation between Spending and Income level
1.4.4 Diploma Distribution by Marital Situation
Our project's sunburst chart provides a detailed visual representation of the distribution of educational qualifications among different marital statuses within our customer base.
The chart presents a detailed analysis of customer demographics, categorizing individuals by marital status into 'In couple' and 'Alone' in the inner ring The outer ring further delineates the educational qualifications of these groups, with the size of each segment visually representing the proportion of individuals at each educational level within their respective marital status category.
Analysis reveals that educational qualifications are evenly distributed among individuals who are 'In couple' and those who are 'Alone.' This indicates that there is no significant prevalence of any specific degree within either marital status group, suggesting that education levels are independent of an individual's relationship status in our customer dataset.
This finding indicates that our marketing strategy can remain largely uniform across different marital statuses when targeting educational content and products, given the consistent educational levels among these groups To enhance our marketing effectiveness, it may be advantageous to explore additional demographic factors or their combinations, as these could offer more insightful indicators of consumer spending behaviors and product preferences beyond just marital status and education.
Model
Training model
Create functions to prepare data for model training:
Initially, we provided code, a set of import statements and configurations commonly used in data analysis and visualization tasks Let's break down each line and explain its purpose:
'import numpy as np' : Import the NumPy library and give it the abbreviation "np".
NumPy is a popular library in Python for working with multidimensional arrays and matrices, providing powerful mathematical and statistical functions.
'from numpy import isnan' : Import the isnan function from the NumPy library.
This function is used to check if a value is NaN (Not a Number).
'import pandas as pd': Import the Pandas library and give it the abbreviation "pd".
Pandas is a popular library in Python for working with tabular and time series data, providing powerful tools for processing, querying, and analyzing data.
Import the Seaborn library using 'import seaborn as sns' to create compelling graphs and visualizations for your data Seaborn is a user-friendly and robust data visualization library that enhances Matplotlib's capabilities.
To utilize the Matplotlib library for creating and displaying graphs, charts, and images in Python, you can import the pyplot module with the command 'import matplotlib.pyplot as plt' This assigns the abbreviation "plt" for easier reference in your code.
'import scipy.stats astats': Import the scipy.stats library and give it the abbreviation stats scipy.stats provides probability distributions, statistical tests, and other statistical tools.
'from numpy import median': Import the median function from the NumPy library.
This function is used to calculate the median value of an array.
'from numpy import std': Import std function from NumPy library This function is used to calculate the standard deviation of an array.
Jupyter Notebook facilitates advanced data analysis and visualization by utilizing essential libraries such as NumPy, Pandas, Seaborn, Matplotlib, and Plotly These tools enable users to effectively explore, manipulate, and visualize supply chain data, leading to enhanced understanding and valuable insights from the dataset.
Exploratory Data Analysis (EDA): The code loads the supply chain dataset
To begin exploring the DataCo Supply Chain Dataset, the data is loaded using `pd.read_csv`, and display options are adjusted to reveal additional rows and columns This initial examination allows for an assessment of missing values, data types, and summary statistics, providing insights into the dataset's structure and distribution.
Data visualization plays a crucial role in analyzing supply chain data by employing plotting functions from libraries like Seaborn and Plotly to produce interactive and insightful graphics These visualizations enable the identification of patterns, trends, and outliers, offering valuable insights into various supply chain elements, including order status, product categories, and customer behavior.
The notebook is configured for interactive plotting with Plotly, enabling dynamic visualizations that enhance the exploration and customization of supply chain data This approach offers a more engaging and flexible method for analyzing and presenting information.
Linear Regression: This model can identify the relationship between independent variables (e.g., customer demographics, pricing, promotional activities) and the dependent
27 variable (buying/payment trends) It provides insights into the impact of different factors on buying behavior and payment patterns.
The KNeighborsRegressor model analyzes customer similarities through various features, allowing for the prediction of purchasing and payment trends by comparing customers with similar behaviors This approach effectively identifies clusters of customers exhibiting analogous patterns, enhancing targeted marketing strategies.
In our project, we utilize TensorFlow to develop and analyze a binary classification model TensorFlow is a powerful framework that allows for the design of neural networks with diverse layers, activation functions, and connections, while providing various loss functions, optimization methods, and evaluation metrics tailored for binary classification tasks By defining a loss function to compare predicted and actual labels, we can select an optimization method to adjust model weights and minimize loss The training process involves using batches of data to compute gradients and weights through forward and backward passes Ultimately, TensorFlow enables us to assess model performance on test data with key metrics such as accuracy, sensitivity, specificity, and AUC-ROC score.
Results
The evaluation results of the model on the test data set demonstrate its effectiveness, evidenced by a low average loss value, a high prediction accuracy rate, and an AUC value nearing 1 The mean loss reflects the average discrepancy between predicted and actual labels, with lower values indicating a closer match The correct prediction rate, representing the percentage of accurate predictions, further confirms the model's classification capabilities Additionally, the AUC value, which measures the area under the ROC curve, suggests superior classification ability, highlighting high positive and correct classification rates on the test data set.
The classification report indicates the model's performance on the test set, highlighting a precision of 0.92 for the "FAILURE" class, which signifies that the model accurately identifies 92% of "FAILURE" samples Additionally, the recall for the "FAILURE" class is 0.97, demonstrating that the model successfully captures 97% of the actual "FAILURE" samples.
The f1-score is a key indicator of a model's classification performance, with a score closer to 1 reflecting superior accuracy For the “FAILURE” class, the f1-score is 0.94, significantly higher than the 0.62 for the “SUCCESS” class The support metric reveals the number of samples per class, aiding in the understanding of data distribution The model boasts an overall accuracy of 0.90, indicating it correctly predicts 90% of samples Additionally, the macro average f1-score is 0.78, while the weighted average f1-score, which accounts for class weight and sample rate, stands at 0.89.
From the classification report you provided, we can deduce the following values to construct the confusion matrix:
In the successful predictions (SUCCESS), 45 samples were correctly classified (true positives), while 42 samples were misclassified (false negatives).
In the failed predictions (FAILURE), there were 459 samples correctly classified (true positives), 13 samples were misclassified (false negatives).
Findings and Business Implications
Concluding Thoughts on the Analysis
Our analysis reveals key insights into our customer demographics, highlighting their engagement with our marketing efforts The average customer belongs to an older demographic, indicating a mature market segment with stable income and established spending habits Most customers have educational levels at or above high school, and with an average income of approximately $50,000, there is potential for discretionary spending that can be leveraged through targeted marketing strategies.
Customer enrollment trends show a notable increase around 2013, alongside a prevalence of small household sizes, highlighting distinct lifestyle patterns that warrant further exploration in our marketing strategies Additionally, the diverse customer base, particularly those holding international qualifications, indicates that customized approaches could enhance the effectiveness of regional marketing campaigns.
Our analysis highlights that wines and meats are key categories where our brand excels, reflecting strong customer resonance Conversely, lower revenue from other product lines suggests potential growth opportunities or the need for strategic realignment Additionally, recent campaigns have outperformed previous ones, with repeat customers demonstrating high participation rates, indicating both brand loyalty and effective targeting of our audience.
The analysis offers a clear overview of the company's current position and highlights potential growth opportunities It is clear that while certain strategies are effective, others require refinement to better meet the changing needs and behaviors of our customers.
Recommendations for Future Strategies Based on the Analysis
Building on the analysis, we recommend the following strategies to enhance our marketing approach and overall business growth:
Market segmentation and personalization are crucial for effective marketing strategies By analyzing insights related to age, income, education, and lifestyle, businesses can create more defined market segments This targeted approach allows for the development of marketing campaigns that are specifically tailored to each segment, significantly enhancing their effectiveness and engagement.
To enhance growth, prioritize the expansion of product lines in successful categories like wines and meats, potentially introducing premium selections At the same time, seek innovative strategies to rejuvenate underperforming categories, ensuring a balanced approach to product development and diversification.
Enhance loyalty and engagement programs to foster stronger connections with existing customers, especially those who consistently interact with our campaigns These initiatives should be crafted to motivate customers to make repeat purchases and become passionate advocates for our brand.
- Inclusive Pricing Strategies: Develop a tiered pricing strategy to make our products and campaigns appealing to a broader income spectrum, ensuring that we cater to both higher and lower-income segments.
- Localized Marketing: Tailor marketing campaigns to address the geographic and cultural diversity within our customer base, acknowledging the variety of international backgrounds.
- Digital Marketing Expansion: Augment online and social media marketing to complement in-store experiences, tapping into the digital engagement preferences of our customers.
- Feedback – Driven Improvement: Actively collect and analyze customer feedback to understand the drivers behind the success of our campaigns, using these insights to refine future marketing strategies.
Further research is essential to enhance our understanding of regional market preferences, product performance, and long-term customer value By exploring diverse sales channels and incorporating a wider array of socio-demographic factors, we can gain a comprehensive view of our customer base and their interactions with our brand This ongoing research and the execution of recommended strategies will be vital for creating more effective marketing campaigns, boosting customer satisfaction, and ultimately improving overall company performance.