Optimisation of outlier data mining algorithm for large datasets based on unit

This article aims to study the cell-based outlier data mining algorithm for large datasets, and to further improve the profit group data mining algorithm. This experiment first uses mathematical statistical analysis methods to study the optimisation of large data sets based on the unit-based outlier data mining algorithm and the proportion of data mining in various categories of the internet of things; then uses data statistics methods to classify and analyse large data sets, and test normal data mining optimisation algorithms. Finally, the experimental data shows that data mining has been significantly improved in terms of speed, intelligent internet of things, intelligent transportation, big data, genetic algorithms, etc. Experimental data testing shows that the algorithm can quickly and efficiently mine outliers in the dataset, and increase the detection speed of outliers by about 32%, which has guiding significance for outlier data mining in large datasets.