Don’t Say No to Data Analytics if You Want to Be a Successful Marketer !

If you are a Marketer and have not thought about collecting data about your customers, it is time to do it now ! Go create a customer satisfaction survey and consider your client’s feedback to identify the flows and make your business more appealing. Always engage in research about your customers and make it as one of your biggest priorities as it is key to success. In fact, Survey Monkey which is a platform where you can create your surveys for your company investigated the importance of creating customer’s satisfaction surveys.

According to this organization, “businesses who measure customer satisfaction are 33% more likely to describe themselves as successful than those who don’t” (Survey Monkey, 2021). You might want to ask what is the link between customer satisfaction and data analytics. Well, your customer satisfaction survey will allow you to gather data that you should analyze and draw conclusions from to be able to come up with the best strategies for your company.

As a marketer, you should always look for opportunities to collect data especially about your customers. It is crucial nowadays for any type of business regardless the industry to have a clear understanding of data analytics as it can increase the chance of success. Indeed, Doctor Miyazaki defines data distribution as the way data are spread-out. He mentions how important it is to analyze the trends of those numbers to make the right marketing decisions (Miyazaki, 2020).

Customer satisfaction is the most common measure that marketers evaluate to figure out how to make their business more attractive. For instance, one way to collect data is to create surveys aiming at asking customers about their perception of the service provided by the company. Most often, those questions will ask customers to rate different aspects of the customer service. Then, the role of marketers is to analyze the scores that were given by the customers to look at the tendency. When you have enough respondents to your survey, you are able to analyze the answer’s trends. According to the general rule of thumb, at least 100 responses should be collected to be considered acceptable in terms of accuracy, but again it depends on the size of the company (GreatBrook, 2018).

According to Kandane, Enticotts, and Phillips (2013), below are the metrics and statistical terms that you should understand to run your data analysis. Indeed, those measures can help give you a clear overview of the situation based on how the data are distributed.

Central Tendency Data :

Mean : It is the statistical term for average. It is simply the sum of the different values divided by the actual number of observations.

Median : It is the value that is located in the middle after the values were ranked from the smallest to the largest. Indeed, 50% of the values fall above the median and the other 50% below the median.

Mode : It is the value that repeats itself the most in the data sets (Kandane-Rathnayake, Enticotts & Phillips, 2013).

Data Distribution :

Normal Distribution :

It is important to note that when the mean, median and mode are close to each other, you can assume normal distribution and your data will be shaped as a bell curve as the data are symmetric around the mean. Data are normally distributed when most values are clustered around the mean (McLeod, 2019). Normal distribution happens when the values close to the mean occurs more frequently than the ones away from the mean (Chen, 2020). Analysts are able to make better conclusions when data are normally distributed as the results are not influenced by extreme values.

Skewness :

There are cases when most of the values are toward one direction, and this is known as skewness. Indeed, the values can either be right or left skewed. When data are skewed, the median is a better measure of the central tendency (United States Department of Agriculture, 2021).

5-Number Summary :

According to Doctor San Luis, the 5-Number Summary is also important to consider when analyzing your data :

Minimum : It is the smallest number in the data set.

First Quartile : It is also called Q1 or 25th Percentile. 25% of the values are located below or are equal to the first quartile.

Second Quartile : It is also called Q2 or 50th Percentile and known as median as defined previously.

Third Quartile : It is also called Q3 or 75th Percentile. 75% of the values are located below or are equal to the third quartile.

Maximum : It is the largest value in the data collected (San Luis, 2021).

The 5 Number Summary are usually illustrated as a boxplot as shown below :

Now, do not hesitate to impress your supervisors with these terminologies when running your next data analysis with your customer service surveys !