Many newcomers do not understand the meaning of data. Facing the report, it would only be the same as the repeater, saying: "100 sales yesterday, 120 sales today, an increase of 20..." Talking about these things that anyone who is not blind can see. Because of this, what should I do? ! Today we will explain the system.
Understanding the first stage: Ming indicators
Give a number: 180, can you see the meaning?
Can't!
Because this is a lone number with no meaning at all. To understand the data, at least it has to be a clear data indicator. Contains the indicator name, usage scenario, and calculation caliber. The same is 180, we replace it with: adult female, height 180cm. Is it clearer at once?
Reading the second stage: setting standards
And many people may already have an instinctive judgment: this girl is tall. This judgment may be based on statistics. According to the 2015 "Report on Nutrition and Chronic Disease Status of Chinese Residents", the report shows that the average height of adult men is 167.1cm and that of women is 155.8cm, which means that 180cm has exceeded the height of many men. Can be defined as high. Such a judgment may also be based on customary habits. For example, it is customary for girls to be taller than 170, and 180 is even bigger. It must be considered high.
Both judgments are not wrong, in fact, they are both methods to further understand the data: statistical law and customary law. The statistical method is based on the difference in data statistics to divide high, middle and low. Customary law is to quantify people's customary habits.
From "adult female, height 180cm" to "adult female, very tall" is an important transition in reading data. Because 180cm is an objective value, it cannot directly affect our decision-making. But "high" is a judgment result, and this judgment will affect our decision-making. Do not believe it, continue to look down.
Understand the third stage: the scene
Scene 1: Xiao Ming is 175 in height, and his second aunt enthusiastically introduced a 180 girl to him for a blind date.
Scenario 2: Xiao Ming is organizing an exhibition and needs 5 models. HR linda introduced 1 180 girls to him.
How does Xiao Ming feel in the two scenarios?
Some girls will dislike boys who are shorter than themselves. Unfortunately, Xiao Ming is a pretty boy who has been deeply disliked. Therefore, Xiaoming probably scolded his mother directly when he encountered scene 1: "I said that I shouldn't look for someone taller than me. Are you sincerely embarrassing me!"-This is the result of ignoring other people's requirements.
Scene 2 estimates that Xiao Ming will be very happy. The model at the exhibition is to have a tall and handsome appearance, so that it can be good enough. Of course, the appearance fee is a lot more expensive. At this time, if the picture is cheap, just find a few short girls, it is estimated that the leader will scold when he sees the height-give you the fee, don't use it to paste the facade, use it to wipe the butt!
So if you want to understand the data in depth, you must combine specific scenarios. There are two approaches here:
1. Deduction based on business logic
2. Summary based on past experience
Both methods require an in-depth understanding of business scenarios (as shown below):
Understanding the fourth stage: observing the situation
After the first three stages, the information we know is:
1. Adult female 180cm belongs to: tall
2. Need a model to find a model: tall
3. tall + handsome appearance = expensive
On these foundations, looking at the data again, there will be new interpretations.
For example, if you are responsible for planning an exhibition, the height of the live model recommended by the advertising company below you is as follows:
After reading it, you may immediately read: These grandsons want to hack my expenses again! Secretly exchanged a batch of cheap models for me! Yes, this interpretation goes even further than "Oh, the height has shrunk so much". This is the fourth stage of interpretation.
The same data, if you didn't read this out, you sent it directly to the leader. After reading it, the leader might immediately interpret: This newcomer doesn't understand business, so how can he do such a shabby job.
The same data, if the leader did not deal with it, really found a group of random people to the exhibition. After your dealers read it, they can immediately understand: Hey, is there a problem with the brand's strength this year? You see the booth area has shrunk, the new product launch conference is not enthusiastic, and the models are all made up. .
All of these are based on a height data. The so-called seeing the micro-knowledge is actually a logical reasoning behind it (as shown below)
The difference between reading and reading
Of course, there is a limit to interpreting data. Excessive interpretation or random guessing will lead to misunderstanding. such as:
Guess casually: you see that the models are all beautiful women, so their boss must be lustful.
Over-interpretation: You see nine beautiful models were invited this time, and nine products must be released
The biggest difference between reading and guessing is the amount of evidence. For example, the dealers above questioned the strength of the brand, not just watching the height changes of models alone, but also watching the booth and new product launches. There are many evidences to support it, and the interpretation is naturally close to reality. Random guessing is often unfounded (what about lustful evidence?) Over-interpretation, and often solitary evidence is not established (apart from nine models, is there any other evidence?).
Of course, it does not rule out that after we have obtained more evidence, there will be a new interpretation. Logic + amount of evidence is the only criterion for judging data interpretation. As long as there is sufficient evidence + reasonable logic, we have reason to accept the conclusion.
Why is it difficult to interpret data in a company
Why is it easy to interpret the data in the example, but difficult in actual work? Answer: Because of the examples of height, blind date, and exhibition model, the business meaning is very simple, clear and easy to understand. However, in actual work, data analysts often divorce from the business and know nothing about specific sales, operations, products, after-sales, etc., and can only make simple guesses through several figures such as sales, gross profit, activity rate, and conversion rate. .
Common problems, such as:
1. I don’t understand the meaning of business: why do blind dates pay attention to height? Didn’t you feel it?
2. I don’t understand the business situation: Why doesn’t Xiaoming like tall girls? Tall people are pretty girls!
3. I don’t understand business logic: Why must we find tall models at the show? Can't you just go to a few people?
As a result, it is impossible to judge the data. So it can only flow from: yesterday the sales volume was 120, today is 140, an increase of 20, an increase of 16.7%, this meaningless running account. The key is that these judgments are likely to be common sense from the perspective of the business, so there is an embarrassing scene in the communication: the business is too lazy to talk, and the data does not know how to ask. When the data analyst finally blamed him, he was still pitiful: I haven't dated on a blind date, and I haven't been to an exhibition, oh oh oh
Therefore, if you want to interpret in-depth and specific, you have to be close to the business, learn to abstract the meaning of data from specific operations, and quantify the business side’s judgments. If you are interested, we will share a specific data interpretation scenario in the next article, so stay tuned. Teacher Chen is angry.
Author: Chen grounded gas, micro-channel public number: down to earth school. A data analyst with ten years of experience and CRM experience in multiple industries.