Customer segmentation in the digital marketing using a Q-learning based differential evolution algorithm integrated...

Area of Science:

• Artificial Intelligence
• Digital Marketing
• Data Science

Background:

• Effective customer segmentation is crucial for targeted marketing strategies.
• Artificial intelligence (AI) offers advanced capabilities for analyzing complex customer data.
• Existing segmentation methods face challenges in accurately identifying distinct customer needs.

Purpose of the Study:

• To propose an AI-integrated customer segmentation framework for digital marketing.
• To enhance the accuracy and efficiency of customer segmentation processes.
• To leverage advanced algorithms for deeper customer insights and improved marketing outcomes.

Main Methods:

• Utilized Principal Component Analysis (PCA) for feature denoising and dimensionality reduction.
• Integrated a reinforcement learning-based differential evolution algorithm with K-means clustering.
• Employed Q-learning for adaptive parameter adjustment to improve K-means performance.

Main Results:

• The proposed framework achieved over 95% classification accuracy in segmenting customer data.
• Principal Component Analysis effectively reduced noise and multicollinearity in customer features.
• Q-learning significantly enhanced the clustering performance of the K-means algorithm.

Conclusions:

• The developed AI framework provides accurate customer characteristic identification and segmentation.
• The approach enhances marketing efficiency, customer satisfaction, and corporate profit growth.
• This method offers a robust solution for complex customer segmentation challenges in digital marketing.