Many marketing professionals are drawn to their field because they consider themselves more right-brained (creative) than left-brained (analytical). It’s true that success in marketing often requires imagination, creativity, and an emotional appeal to the target audience. In fact, many college students choose marketing as their major due to the perception that it is a less rigorous discipline than fields like finance, physics, or engineering. In the workplace, marketing has been seen as a profession driven more by intuition and creative flair than analytics and data. However, with the rise of digital tools and the increased prominence of data-driven strategies, intuition and creativity alone are insufficient for marketing pros.

Today, marketing has evolved into a field where analytics and data management are just as important as creativity and imagination. Marketers, once stereotyped as being “soft on data,” must become proficient in data analysis. In fact, many marketing campaigns now rely heavily on the insights provided by data analytics to optimize performance and improve outcomes.

While marketing professionals don’t necessarily need advanced degrees in data science or statistical theory, they must have a basic understanding of statistics and data analysis. A solid foundation in these areas will allow marketers to create more effective campaigns, reduce waste, and enhance customer service and satisfaction.

Data’s role in customer service and quality management

Let’s consider a customer service example to illustrate the importance of integrating data and quality management principles into marketing and customer service. Business owners commonly use metrics such as net promoter score (NPS), churn rate, and customer satisfaction ratings to assess their effectiveness. However, incorporating techniques from quality management and statistical process control can provide a deeper understanding of these metrics and lead to significant improvements.

Take the case of R2 Delivery Services. Luke owns the business and has been tracking the number of low-star ratings (three or fewer stars) received through the company’s customer feedback system. Luke believes that if a customer provides a rating of less than four stars it indicates dissatisfaction, and he has been tracking these complaints over the past six months. The company reports an average of six negative ratings per day, which, given the company’s 300 deliveries per day, Luke interprets as an approximately 98% satisfaction rate.

However, Trent, a recent intern at R2 Delivery Services (and a data analytics student), suggests applying a statistical process control (SPC) method to understand better whether the number of complaints falls within an acceptable range. Specifically, he recommends using a c-chart, a control chart used in quality management that helps track the number of defects (in this case, complaints) over time.

The first thing to decide is whether there is enough data to make a clear decision. When applying statistical methods like SPC, it’s important to consider the sample size—the number of data points collected over time. Many companies end up with misleading conclusions because of a small sample size; fluctuations in daily complaints might not represent broader trends. Larger sample sizes, on the other hand, help provide more accurate, reliable insights and allow for more confident decision-making.

The key is finding a balance: enough data to ensure your results are statistically significant, but not so much that information becomes unnecessarily time-consuming or expensive to collect. With 300 deliveries over 180 days (six months), there are more than 54,000 observations, providing a large enough sample to make meaningful decisions.

Next, Trent determines an upper and lower control limit around the average number of complaints using a Z-value of 2.33 to match the desired 98% confidence level. He quickly calculates the following:
• Average complaints (c̅) = 6
• Z-value = 2.33
• Upper control limit (UCL) = 6 + 2.33 * √6 = 8.45
• Lower control limit (LCL) = 6 - 2.33 * √6 = 3.55

This means that, based on the current process, R2 Delivery Services can expect anywhere from three to nine complaints per day. Although Luke felt that an average of six negative ratings per day equated to a satisfactory 98% customer satisfaction rate, the statistical analysis suggests that this rate of complaints is more variable than he assumed. The lower control limit (3.55 complaints) indicates that it’s statistically acceptable for the company to experience as few as three complaints per day, and the upper control limit (8.45 complaints) allows for up to nine complaints per day without signaling a failure in the service process.

Reevaluating customer service standards

Upon reviewing the results, Luke realizes that accepting three to four complaints per day (the lower control limit) isn’t ideal, especially when striving for a higher level of service. He decides to reduce the average number of low-star ratings by half, ideally bringing the lower control limit closer to zero.

Several strategies could be implemented to achieve this goal. For instance, Luke could analyze the feedback data from the last six months to identify any recurring patterns that might be influencing the average rating. He could also look for outliers that could skew the data, or investigate whether certain delivery personnel consistently receive lower ratings.

By incorporating quality management techniques such as root cause analysis and statistical process control, Luke can develop targeted strategies to reduce complaints and improve customer satisfaction. These tools allow him to make data-driven decisions that would have been difficult, if not impossible, to identify through anecdotal observations alone.

Integrating quality management into marketing and customer service makes sense

Integrating quality management principles and data analytics into marketing and customer service doesn’t have to be complicated and time-consuming. By adopting tools from other disciplines, such as SPC, businesses can gain a deeper understanding of their performance and identify areas for improvement. This leads to better customer service and helps optimize marketing efforts by identifying key factors that affect customer satisfaction.

In today’s data-driven world, marketing professionals no longer have the luxury of relying solely on intuition or creative instincts. Understanding how to collect, analyze, and interpret data has become a core competency for marketers. Whether you’re in B2B or B2C marketing, integrating statistical tools and quality management practices into your strategy can lead to more effective campaigns, higher customer satisfaction, and, ultimately, better business outcomes.

Many tools are available for marketers to analyze their campaigns. There’s no need to reinvent the wheel. Data analysis should be an integral part of the marketing and customer service process, enabling businesses to create better customer experiences while continuously improving their services.