ml-specialty video for a governmental dataset contains the following columns: “ID”, “Race” “Gender”, “Age group”, “educational level”, “income”. The dataset
A governmental dataset contains the following columns: “ID”, “Race” “Gender”, “Age group”, “educational level”, “income”. The dataset contains 100,000 entries, each corresponding to information about a person in a specific city. 10,000 educational level data are found missing which resembles 10% of the total data. The data was collected a few months ago and the government has no intention to spend time or budget on requesting the missing data from citizens. The machine learning engineer should search for a solution to complete those missing data without introducing bias. Which action should be taken to overcome this problem? What is the most accurate action to be taken?