Analyzing the Data Analyst

Analytics, business intelligence, data scientists, database managers, forecasting, big data. There’s a good chance you’ve heard of most or all of these terms before, but do you really know what each of them means and how they’re interconnected? If we’re honest with ourselves, most of us cannot make such a claim. Just like melting an iceberg with a hairdryer might seem like an impossible task, distinguishing each of these terms from each other and understanding their individual nuances is daunting at first. Bearing that in mind, let’s start by chipping away at the iceberg and trying to get a better grip on analytics and what exactly a data analyst does.

According to BusinessDictionary.com, analytics can be defined as “the field of studying past historical data to research potential trends, to analyze the effects of certain decisions or events, or to evaluate the performance of a given tool or scenario.” Basically, analytics is the practice of using known data to evaluate some event (or decision, prediction, et cetera) and quantify results. Data analysts look at and evaluate (i.e. analyze) data they receive and try to make useful sense of it. Analytics and data analysts are important to businesses because data analysts analyze data to improve business tactics and decisions and implement changes if necessary. The decisions resulting from data analysts’ work increase functionality and profitability of a business. In short, analytics is vital to business’ success.

Let’s apply the process of using analytics to something ordinary to make sense of what a data analyst does. Whether you know it or not, you use analytics in your everyday life; you simply don’t think to label yourself as a data analyst. For example, take the scenario of filling up your car with gasoline. Five days a week you drive from your house to work and stop at a coffee shop somewhere in between. Between your house, the coffee shop and work, you drive approximately 15 miles and pass six gas stations. Today you notice your gas tank is almost empty, so you decide to stop at one of these six gas stations on your way to work. In theory, it shouldn’t matter which gas station you visit because all six gas stations have the oil-based fuel your car needs. You, however, are a money-savvy driver and hate overpaying for gas, so naturally you want to spend the least amount of money possible while not having to go out of your way. You remember that the two stations closest to work are always more expensive because they’re right off of a highway exit, so you plan to stop at one of the first four stations. You have also noticed that the gas stations on the left side of the road tend to sell gas for a few pennies less than the stations on the right side of the road (which also happen to be located next to your favorite coffee shop). Since this trip is about you spending the least amount of money possible, you decide to stop at the first station on the left because you’re convinced it will have the cheapest gas. You fill up, grab some coffee from the gas station kitchen and continue your daily routine.

But where were the analytics in that situation? You didn’t sit in front of a database and compare gas prices, time wasted by going to the station on the left instead of the right, or the difference in coffee prices at the gas station versus your regular shop (although someone’s probably developed an app for all of those things). You did, however, make your gas station decision based on these metrics, even if it was subconsciously. Since you drive the same way to work every day, you notice certain trends and your memory keeps a record of them. That’s why you knew gas would be more expensive closer to work and on the right side of the road. Your brain also decided the tradeoff between spending more time by turning left into a gas station was worth the money you’d be saving by getting cheaper gas than at a station on the more convenient right-side of the road. Data analysts do this exact same thing, except they look at data compiled from businesses stored in a database. Instead of making a decision about buying gas and simply buying it, they prepare reports showing functional data trends (e.g. data versus fiscal year, season or geographical location). Businesses can then use these reports to make decisions and see how well their current business model is working. If the data indicate that business is doing well, then no change needs to be made. If the data analysts’ results show room for improvement, though, changes in the business’ decisions then have concrete justification backing those decisions. Using the same logic, you’d know whether or not your “business decision” of choosing the first gas station on the left was a good one as you see the other stations’ prices when you drive by them. If you did indeed get the best price, then you successfully used data analytics. If you actually chose the most expensive gas based on your decision-making tree, then perhaps you should reconsider the “business model” your brain employed.

Rebecca Seasholtz

Rebecca is a senior Materials Science and Engineering major at Georgia Tech. She specializes in soft materials (i.e. plastics and textiles) and has also worked extensively with functional materials for electrical applications. Rebecca is originally from Grayson, GA and likes to spend her free time running, cycling, drinking coffee, or hanging around the campus house of a ministry she attends at Georgia Tech. Contact Rebecca at [email protected]