Improving Space and Time Efficiency in Hadoop Architecture Using Machine Learning Algorithms

This research study explores the application of Hadoop Distributed File System (HDFS), MapReduce, and Machine Learning algorithms, along with Social Spider Optimization (SSO), to effectively analyze and utilize large volumes of unstructured data generated by social media platforms. The study focuses on analyzing user behavior and preferences within the context of online shopping, considering individual and business perspectives. The research proposes novel approaches, including the derby model, virtual local file system, a refined recommender system, and parallelized SSO, to efficiently handle various data formats and improve the performance of data processing tasks. The proposed methods demonstrate improved efficiency in terms of space and time requirements compared to existing approaches. This research contributes to the advancement of big data analytics techniques and has the potential to revolutionize how businesses understand and leverage user behavior in the digital age.