Learn about cluster analysis.
- Think about your closet at home. Do you keep certain types of clothing like T-shirts or dress shirts, jeans and slacks, organized into groups or is it a mishmash? How about a sock drawer, do you have one of those? Whether you keep things organized in groups or not is your own personal preference, and this is certainly not intended to be a critique on your own personal organizational habits. To each their own as they say, but the idea of a sock drawer, the concept of all things in their place as they say. Those sorts of organizational devices help things in general to stay organized, to stay efficient.
Need a pair of socks? Well if you have a sock drawer, you know where to go. Now, we do this kind of thing all the time, right? We sort similar things into groups, so we can make sense of them. This is what cluster analysis is all about. Sorting your data into groups. Now, this is actually a very powerful concept when applied to marketing. In the marketing world, we talk about market segments, and competitive sets, and business units, or brand extensions. All these ways in which we refer to our marketing strategy are organized into groups.
Each of the different types of cluster analysis algorithms group data based on certain variables. In other words they create and organize your data into different buckets. This can be used for consumer segmentation, or to identify which types of ad units are driving the greatest conversion or brand lift. It could help you to identify what people are responding to. Our cluster analysis case study comes from the world of consumer packaged goods, CPG. You might imagine the client is a popular beverage brand, or a challenger brand in the personal care space.
They have come to us seeking our guidance on their segmentation strategy. Now, take off your marketing hat for a moment. How many times in your lifetime as a consumer have you experienced an ad that was irrelevant to either your taste or your needs? It happens a lot, and it can be annoying on a personal level, and it can be a real waste of marketing dollars on a business level. Now, put your marketing hat back on. One of the great things about technological advancements in the marketing space is the ability to target your message to those that it will find the most resonance with.
Marketing can be extremely valuable to the right customer, and providing that value can in turn drive revenue, and that's what we want. So, how do we go about doing this? Well, we have to determine where our marketing will provide value. Where it will be welcomed and be useful. We need the right message being delivered at the right time to the right person. So we have to understand which groups, what are known as consumer cohorts, represent which portion of the market so that we can evaluate and prioritize. This approach can also inform our messaging and our creative with consumer insights.
So, the way we go about doing this is with cluster analysis. For example, imagine our CPG client leverages email marketing as one of their channels. Analysis has shown that the right kind of personalization in email messaging can dramatically improve performance. We might have a large group in our database with families, and their needs will likely be different from other groups. Safety and wellbeing for example might resonate most with this group. That same database might have a large group of recent college graduates, and value might resonate most with them. So you see, I'm talking a lot about groups.
Our client may have millions of customer records in their database, and if we can organize that information into the right groups, we can do marketing personalization at scale.
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