DATA SCIENCE: PENDEKATAN DAN LANGKAH PRAKTIS DENGAN EXCEL

Abstract

The steps in conducting data science activities consist of several stages, namely problem identification, understanding the current business, data collection, data processing, and making decisions based on insights. Researchers who engage in data science activities are often referred to as data scientists. In their process, data scientists use applications to facilitate their data science activities. One application that can be used by data scientists is Excel. Excel has features that can handle a certain amount of data. However, for the initial steps towards becoming a data scientist, Excel is a good application with features that make it easier for researchers to conduct data science activities. Data that can be managed by Excel is not more than 1 million rows, as Excel only has a maximum of 1,048,576 rows and 16,384 columns. Nevertheless, the features in Excel are already powerful, such as error detection, removing duplicate data, correcting error values, detecting outliers, handling missing data, and validating data. This study discusses the functions of these features in an effort to promote data science for beginner data scientists.