Advanced Techniques of AI- Boosted Data Imputation Methods for Handling Missing Data in Large Datasets
Main Article Content
Abstract
Addressing missing data in extensive datasets poses a significant challenge in data-driven sectors, where gaps in information can greatly affect the accuracy and dependability of predictive models. While traditional imputation methods have their merits, they often struggle with large and intricate datasets. This paper examines advanced data imputation techniques powered by AI, utilizing machine learning and deep learning algorithms to improve data completeness with enhanced precision and efficiency. Key methods discussed include generative adversarial networks (GANs) for producing realistic estimates, deep neural networks for identifying complex data patterns, and ensemble models that combine various imputation strategies for improved performance. Through experiments conducted on multiple benchmark datasets, the study shows that these AI-enhanced imputation techniques significantly surpass traditional methods in accuracy, speed, and scalability, providing a more dependable solution for managing missing data in large-scale applications.