Sailfish Optimizer Driven Framework for Mining Dynamic Consumer Purchase Patterns

Mining dynamic consumer purchase patterns is crucial for understanding shifting market trends and improving personalized marketing strategies. The proposed framework leverages the Sailfish Optimizer to intelligently mine and adapt to evolving consumer behaviors. Existing methods often struggle with highdimensional, non-linear, and time-varying consumer data, resulting in suboptimal clustering accuracy and slow adaptation to dynamic changes. To address these limitations, this paper introduces the Sailfish Optimizer-Based Fuzzy Clustering Means (SFO-FCM) framework, where the Sailfish Optimizer finetunes the fuzzy clustering parameters to achieve optimal performance. The framework effectively segments consumer data into adaptive clusters by balancing explorat ion and exploitation, allowing more accurate tracking of evolving purchase patterns. This optimized clustering is then used to generate actionable insights, such as real-time personalized offers and inventory management strategies in retail systems. Experimental results demonstrate that the proposed SFO-FCM framework outperforms conventional FCM. The proposed SFO-FCM achieves a clustering accuracy of 89.4%, a precision of 86.0%, a recall of 88.4%, an F1-score of 0.87, and a computation time of just 9.1 seconds. Additionally, it attains a high NMI score of 0.77, and other metaheuristic-based approaches in terms of clustering accuracy, adaptability, and computational efficiency, making it well -suited for dynamic and large-scale e-commerce environments.

Keywords :

Consumer Purchase Patterns, Sailfish Optimizer, Fuzzy C-Means, Dynamic Clustering, Ecommerce Analytics, Behavioral Segmentation.