But as a result, students often come away with the impression that most of what data scientists do is work with statistical models. This is usually done for good reasons – the instructors design these exercises in a way that focuses student attention on the skills that they are trying to develop (like model selection or model interpretation). These types of projects are excellent opportunities for learning, but it is usually the case that – unbeknownst to the student – these projects have been carefully tailored to have clearly defined goals, and they come with data sets that have been cleaned and filter to provide only relevant variables. If you don’t have a lot of professional data science experience, it may not be obvious why this is an important skill, or even why I call it a “skill.” That’s because most data science students’ experience with project development comes from classroom exercises or sites like kaggle. Backwards Design is a way of developing an efficient strategy for completing a new data science project, and in my view it is one of the most important skills of a professional data scientist.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |