Bibliometric Analysis of Missing Value Imputation (MVI) Research Using Python and VOSviewer: Trends and Future Directions

Incomplete data is a pervasive issue in data science, posing significant challenges for statistical analysis and machine learning applications. Missing Value Imputation (MVI) has thus emerged as a critical area of research aimed at mitigating data quality issues and improving decision-making accuracy. This study presents a comprehensive bibliometric analysis of MVI research using Scopus-indexed publications from 2000 to 2024. The analysis was conducted using Python and VOSviewer, with the support of Scopus AI to enhance the identification of research trends and thematic patterns. Our findings reveal a significant rise in publications on MVI in the last decade, driven by the increasing adoption of artificial intelligence and big data technologies. The results indicate that a few prolific research groups and institutions have contributed extensively to the field, particularly in healthcare, finance, and environmental sciences. We employed advanced preprocessing techniques, including keyword normalization and duplicate filtering, to ensure data quality. In addition, statistical validation methods, such as linear regression and Mann-Kendall tests, were applied to confirm trend significance. Visualizations include co-authorship networks, keyword co-occurrence maps, and citation impact distributions. This study highlights promising directions for future research, including real-time imputation for streaming data, applications in underrepresented domains, and comparative studies across bibliographic databases. The findings contribute not only to a deeper understanding of the evolution of MVI research but also offer actionable insights for researchers and practitioners seeking to navigate and advance this domain.