What is the purpose of collecting data, creating information, and acquiring knowledge? Essentially, what makes data so important in data science?
Data, on its own, is useless. However, it can be a stepping stone to achieve a goal or an objective of some kind. In order to achieve our goal, we need to transform data into something that is actionable. We need to transform our data into actionable insight.
We do this through the following process
In data science, we refer to this process as “transforming data into actionable insight”. In the world of business, this is often referred to as “data-driven decision making”. In our daily lives, we simply refer to this process as “intelligence”: the use of knowledge and new information to make rational decisions about actions that will maximize our chances of achieving a goal.
Let’s take a look at a simple example of intelligent data-driven decision making in action.
Imagine that we’re an investor. We’re considering making an investment in apples (the edible kind not the iPod kind). Our goal, obviously, is to make a profit. However, we want to make our investment using a data-driven decision-making process.
First, we learn that the price of apples has been holding steady for the past year at $2 per kilogram (which is about $2 for 6 apples). We create data when we observe and record the current price of apples at $2 per kilogram.
Next, we learn that the price of apples has risen this month from $2 per kilogram to $3 per kilogram. This price increase was caused by a unexpected increase in consumer demand. We create information when we analyze the historical price data and discover the $1 increase in the price of apples this month.
Then, from many years of observation, we’ve learned that when the price of apples goes up by $1 per kilogram, then the price of apple cider will likely rise by $1.50 per liter in the following month. We acquired knowledge when we learned about the relationship between an increase in the price of apples and an increase in the price of apple cider.
Next, based on our existing knowledge and the new information about the price increase, we make a decision. We decide it would be smart to invest in apple cider now before the price of apple cider rises by an extra $1.50 per liter next month.
Then, based on our decision, we take action. We invest in apple cider on the commodities market at it’s current (discounted) price in anticipation of an increase in price and thus an increase in the value of our investment.
Finally, if everything worked out in our favor, and the price of apple cider rises as predicted, we will have achieved our goal of capturing a profit on our investment.
However, achieving our goal is entirely dependent upon having correct data, information, knowledge, decisions, actions and the apple-cider market working in our favor!
While this has been an overly simplified example of how data-driven decision making works, hopefully, it helped to demonstrate to you how we use data to achieve a goal with data science.
To learn more, please see my latest course Intro to Data for Data Science.