Downloads: 2
Review Papers | Computer Engineering | Volume 15 Issue 4, April 2026 | Pages: 1137 - 1144 | India
A Review on Several Machine Learning Algorithms Used to Handle Big Data Classification Problem
Abstract: In the highly technologically advanced and digitally transformative era where several new technologies are emerging and creating enormous amounts of data, big data is growing faster. A vast amount of digital data has been generated by several electronic devices, including smart phones, computers, sensors, smart kitchens, and domestic appliances, leading to a global shift in the acceptability of the internet. The data in each domain grew over the time period. Big data analytics may help different domain like banking, Finance, business and medical, but it takes exceptional skills to find a meaningful pattern in these data. From everyday transactions to consumer interactions and social network data, decision makers should be able to extract valuable information from such vast and rapidly evolving data. This huge volume of data is very complex and unclean which makes it difficult to analyze and extract meaningful information. The main problem for machine learning algorithms is this unbalanced and disorganized data. Our goal is to conduct a comprehensive analysis of various tools, methods, and machine learning classification algorithms for big data, evaluating them on the basis of cleanliness and big data complexity reduction. In addition, it examines recent developments and suggests a methodology to improve algorithmic efficiency and data preprocessing to address the complexities of real-world datasets.
Keywords: Big data, Machine Learning, Imbalance data, Data mining
How to Cite?: Rajesh Pandey, Dr. Mamta Bansal, Yogesh Awasthi, "A Review on Several Machine Learning Algorithms Used to Handle Big Data Classification Problem", Volume 15 Issue 4, April 2026, International Journal of Science and Research (IJSR), Pages: 1137-1144, https://www.ijsr.net/getabstract.php?paperid=SR251125140830, DOI: https://dx.dx.doi.org/10.21275/SR251125140830