Customer Segmentation through Path Reconstruction.

Area of Science:

• Consumer behavior analysis
• Data mining and analytics
• Retail management technology

Background:

• Understanding customer movement is crucial for retail operations.
• Traditional methods lack dynamic insights into in-store behavior.
• Technological advancements enable detailed tracking of customer journeys.

Purpose of the Study:

• To develop an automated system for customer classification based on in-store movement.
• To identify distinct customer behavior patterns and dynamics within a retail environment.
• To enable real-time monitoring and prediction of customer traffic.

Main Methods:

• Collecting customer coordinate data within a sports shop at one-minute intervals.
• Constructing customer trajectory models and calculating relevant behavioral parameters.
• Applying a clustering process to categorize customer movement patterns.

Main Results:

• Successful identification of diverse customer types based on their movement.
• Detailed insights into the dynamics of customer behavior within the shop.
• Capability to monitor store status and predict customer traffic peaks.

Conclusions:

• Automated customer movement analysis provides valuable insights for retail management.
• The developed classification method enhances understanding of in-store customer dynamics.
• This approach supports operational adjustments and traffic prediction in retail settings.