Scalable Machine Learning: Development of Efficient Clustering Algorithms for High-Volume Temporal Data Analysis
Madhur Taneja · 2023
In the era of big data, the analysis of large-scale time series data has gained significant importance across various applications such as finance and healthcare. However, traditional clustering approaches, often encounter accuracy and scalability issues when applied to extensive data sets. This paper introduces innovative clustering method specifically tailored for time series data to enter these challenges. These methods leverage advanced data structures for computational efficiency, optimal distance measurements to improve, improve accuracy, and parallel computing framework for enhanced Scalability. Rig testing involving millions of time series occurrences from real world. Data sets was conducted to evaluate the effectiveness of the proposed methods. The results indicate that these novel clustering algorithms can deliver high-quality outcomes even when handling massive data sets. The exhibit verity in accommodating different time series lengths and resilience in handling noise. These characteristics contribute to effective and scalable time series clustering, entering the proposed approaches suitable for real-time analytics in data intensive environments. Consequently, this research facilitates the extraction of actionable insights in real time, offering valuable contributions for both academia and industry practitioners. Additionally, it broadens the spectrum of tools available for the analysis and interpretation of large-scale time series data.