Learn about exploratory analysis and the steps to performing such an analysis.
- You can think of exploratory analysis as that moment in a data analysis project similar to beginning a hike. So, this is where you're just setting out on the trail head. It's where the problem, the data, and the tools, they all converge. Now, you might have a sense of what lies ahead, but you're not entirely certain and so you start to experience that trail. Most often, exploratory analysis is all about visualizing the data you have on hand. It's about summarizing certain characteristics. This really helps you to get comfortable with what you're working with.
It helps you to get familiar with that data and sometimes this approach can help you to see what narrative the analysis might divulge prior to statistical modeling. For this chapter on exploratory analysis, imagine the following. You're working as a consultant for a marketing team for one of the airlines. The particular airline is positioned as a low-cost carrier with a dynamic brand full of personality. Assessing market dynamics over the past few years, you and the team have decided to invest heavily in search engine marketing, so it's important to keep your finger on the pulse of those search engine campaigns and how well they're performing.
Here's a sample from our data set for this chapter's exercise files. Take a look. What would you look at to decide performance? What kind of questions would you ask? A highly effective concept for marketing campaigns of this sort is to look at leading and lagging indicators. So you want to look at paid search impressions. This is a great leading indicator that will help us to know how many users are finding our brand and our promotions via certain keywords. Next, we need to assess CTR, which stands for click-through rate, which will help us to understand how effectively our ads are at addressing what customers are really looking for.
And we also need to assess CPA, which stands for cost per acquisition, so that we can truly understand our return on investment and our conversion. So we just talked through a number of our TMTMTMs, or what I call, our metrics that matter the most. And again, leading and lagging indicators that help our marketing campaigns to ladder up to business impact. You can think of the customer journey here almost like one of those board games you played as a kid. Each roll of the dice, each move you make should move you forward along the path, should move your customer and your market forward along that path.
If we move our CTR rate forward, chances are we've made some informed decisions now here that will also have a positive impact on our cost per acquisition, so on and so forth. So in the following videos we are first going to assess what you call the shape of our data. This is to say, we're going to visualize what the data looks like so that we can see if there are any patterns. Those patterns can help us to create a narrative and can help us to create an intuition for what deeper analysis and specific models might reveal. Then, in each video with each of our analysis platforms, we'll model a matrix so we can see relative performance at a high level.
This is a data visualization that is indispensable to assessing marketing's impact. Remember, we're about to start a journey, and the next few videos are a great start.
In this course, discover how to gain valuable insights from large data sets using specific languages and tools. Follow Chris DallaVilla as he walks through how to use R, Python, and Tableau to perform data modeling and assess performance. As Chris dives into these concepts, he shares specific case studies that come directly from his own work with clients. Plus, he shares three essential—and practical—best practices for data-driven marketing that you can use to bolster your organization's marketing performance.
- Installing R, Python, and Tableau
- Navigating the UI for R, Python, and Tableau
- Using R, Python, and Tableau
- Exploratory analysis
- Performing regression analysis
- Performing a cluster analysis
- Performing a conjoint assessment
- Stakeholder alignment