Research and Application of Grey Principal Component Analysis in Big Data Analytics

Predictive analysis is one of the most important application fields of big data analytics, which can predict uncertain events by combining various advanced analysis functions, especially statistical analysis and other methods. Big data analytics technology is mainly applied in business intelligence, government decision-making, public services and so on. In response to the shortcomings of principal component analysis method in processing data with time series, a new model, namely grey principal component analysis (GPCA), is proposed by combining grey system thinking with classical principal component analysis based on the characteristics of data with time series in grey systems. Time series analysis can not only quantitatively reveal the development and changes of a certain phenomenon, but also dynamically depict the internal quantitative relationships and changes between a certain phenomenon and other phenomena. Through the generation and development of series, the grey system theory devotes itself to the discussion of practical laws, while mathematical statistics devotes itself to the study of statistical historical laws. Combining the advantages of the two methods to solve time series problems, the system was implemented using object-oriented programming methods. The application of this method to the comprehensive evaluation of living environment indicators in Dalian highlights the impact of new time series data on the entire data, and the analysis results can provide valuable decision-making basis for decision-makers. The experimental results indicate that the use of grey principal component analysis is more effective and can accurately reflect the impact of time on the sample data.