When you start data analysis work, you will find that in the eyes of people who understand data and those who don't, the role of data analysis is completely different.
For those who understand data, it seems that data analysis S has the largest component. Data collection, data cleaning, and data warehouse design are all dirty work. Only hard work is required to have reliable data available.
From the perspective of business parties who don’t understand phone number list data, the data analysis component A is the largest. These people say: "underlying thinking", "core link", "internal strength and mental method", and then run the train with their mouths full, but even the most basic data from Where it came from, it doesn't matter if it's possible or not.
In the eyes of newcomers who don’t understand data, data analysis K is the most important component, and always feels that there is a book with the answers already written and waiting for him to copy. When faced with a problem, I always ask "What is the normal, standard, thong-ah's practice?"
This difference has led to a special difficulty in data analysis work: what the business department directly asks for is not a simple, isolated number, or a fantastic model that can be effective immediately and has boundless mana. If the data analyst is caught in running one or two isolated numbers every day and cannot extricate himself, he will not be able to do in-depth analysis, and phone number list the final result will not be recognized; It is difficult to land, it cannot be effective, and it is still the fault.
Therefore, if you want to do a good job, you must dismantle specific problems in depth, balance the expectations of the business side and the quality of data construction, and clearly distinguish how many K will be used in this project, and what are the performance requirements for S, Finally, use A to deal with and coordinate all kinds of messy problems to ensure the success of the project (as shown in the figure below).