The Philosophy Of DATA ANALYST

12 11
12 11

The philosophy of a data analyst is a funny thing. You may not have ever really thought about it much, but you should. Being a data analyst means finding insights in numbers, and that’s what makes it an art form for sierra tel webmail.

To get good at the craft of analyzing things with numbers, one needs to be able to spot patterns in this world full of numbers and symbols, find their order and meaning in the context, filter out all irrelevant information as if it was white noise and focus on what is important – find what actually matters.


Data analytics philosophy starts with the ability to spot the trend and pattern. The data analysts scan large amounts of data to spot the underlying tendencies and facts, from which conclusions can be drawn.

Data analytics is often associated with big data and advanced analytical tools, but that’s just a tool for a job, like a hammer for a carpenter or an awl for a leather worker. Data analysis itself is an old science passed down by business leaders and renowned statisticians over decades. You just need to learn or unlearn the patterns. If you can’t spot a pattern without all the fancy tools, how will you find it when you need it?

Data tools are worth learning, but they are not the whole story. Logic and common sense is still the best way to figure out what your data means. This is true for any business, from online e-commerce to collecting the data for a market research report.

It won’t just be about what you know and how you use it, but also about where and why to use that knowledge. It is crucial that data analysts figure out what matters as early in their analysis process as possible.


Data analysts are likely to come across many sets of data in every day’s work. They should know that data is like a circle, and the more circles you have on your table, the better your understanding of the whole. The point is to find the patterns and trends in these circles, and then focus on those that can give you insights into what’s really important.

For example, a restaurant chain may collect data on its food costs over time and analyze it in fine details to find out which types of food are contributing high costs most often. Then, their team can focus on the most significant patterns and try to find ways to reduce food costs or just avoid those foods.

To make a better decision, you need to know two things: what is the effect of your action, and what are the potential risks? Data analysts need to figure out how likely it is that they will achieve their goal, and what could potentially go wrong if they fail.


The data analysts should also realize that data points that seem unrelated probably are, at least to some degree. It’s just a matter of identifying the relationships and what can be gained by knowing them. For example, if you have a yearly report on how many people bought your product over the last year, you can use it to find out how much they bought in times when the weather and other factors were similar to when they bought it now.

Some business decisions are based on finding correlations between factors – using weather forecast, Internet trends, and other statistical information to predict sales volume or decide which products to produce next season. This is where data analysis starts making sense.

In a business context, the knowledge gained from analyzing data should not be integrated into the decision process itself, but rather provide supporting information, or even radical new ideas to help others in their decision making process.


Another thing that data analysts need to do is find critical data points that can be used as statistical regularities (i.e. reliable measures) for decisions and derive conclusions from them instead of just looking for correlations and possible trends with other unrelated variables. This is also another important step in case you want to teach others how to use your insights.

With data, you shouldn’t learn to love all the numbers. You should learn to identify outliers and take action upon them. For example, in investment banking, you can use your data analysis skills to find out which assets are produced with too much debt and need to be repriced or which assets are being overvalued because they had been getting investments in a market bubble on that specific day.

These critical points can become regularities that can be used as indicators of upcoming risks and patterns in the future. In other words, it is not a matter of finding all possible correlations with the current set of data, but rather perceiving the general trend they have and acting accordingly.


Please enter your comment!
Please enter your name here