In recent years, the need for rational processing of large amounts of diverse data has increased, making data science increasingly important. There are two types of data science education: passive, where knowledge and analytical methods are learned through classroom lectures, and active, where students learn problem solving and task achievement through practical exercises. To date, passive education has been the main approach, and has already produced satisfactory results. However, active education is seen as a future challenge, and there is a strong demand for the development of approaches to achieve it.
In practical settings, the PDCA cycle approach (Plan, Do, Check, Act) has been used for many years to solve problems and accomplish tasks, and has produced many successful results. Its essence is to collect facts in the form of data, analyze them, come up with a hypothesis based on the conclusion reached, put this into practice, and then collect the results as data to verify the hypothesis, which is essentially active data science.
Over the years, the authors have developed educational programs that use both coin shooting materials and the PDCA cycle, implemented them in lectures and workshops, and presented the contents of the programs many times in various forums (papers, academic conference presentations, lectures, etc.). In this presentation, we systematically organize these and report on active data science education.
