Customer Satisfaction

The business problem

  • Problem: we don't know if our customers are happy with our products and services.
  • Goals:
    • We want to know if customers are loyal to our brand
    • We want to know if the customers are satisfied with our services and products.
    • We want to segment customers in three groups: promoters, passive and detractors
  • Why? Perform specific actions to improve our services and products

Technique to solve the business problem

Customer Satisfaction is a complex problem. Discovering the real factors requires time and the combination of several techniques. As a starting point, we will introduce NPS (Net Promoter Score).

Main Concepts

What is Customer Satisfaction

We need a definition

We define customer satisfaction as the number of clients (or the percentage of the total) whose experience with the products or services of the organization exceed a specific goal of satisfaction.

This concept is often used in marketing and is closely linked to expectations that a customer has for the brand.

Understanding Customer Satisfaction requires to discover the factors that influence satisfaction. Most of the times, we used surveys to discover the factors. Likert scale is used to evaluate the characteristics of a product or service.

The Likert scale is a psychometric scale that specifies the level of agreement or disagreement with a statement.

What is NPS

  • Net Promoter Score® (NPS) is a method created by Freid Reichheld (Bain/SatMetrix) in 2004.
  • This metric measures the customer loyalty and allows to discover if they would recommend the services/products of a company
  • According to Satmetrix, NPS is not just a customer satisfaction survey
  • It is a measure that identifies the extent to which a company is increasing customer loyalty and why
  • Types: Competitive benchmark, Customer Experience, Customer Relationship

Promoters, Passive and Detractors

NPS allows to segment the customer in three groups:

  • Promoters: Those who respond with a score of 9 or 10 are called Promoters, and are considered likely to exhibit value-creating behaviors, such as buying more, remaining customers for longer, and making more positive referrals to other potential customers. They are happy and loyal customers. They "represent" 80% of revenue.
  • Passive: Responses of 7 and 8 are labeled Passives, and their behavior falls in the middle of Promoters and Detractors. They are neither happy neither unhappy customers.
  • Detractors: Those who respond with a score of 0 to 6 are labeled as Detractors, and they are believed to be less likely to exhibit the value-creating behaviors. They are unhappy customers. They can impact on branding, employee morale and customer acquisition/retention.

Pros & Cons

Pros

  • Easy to calculate
  • Easy to compare and explain
  • Easy to use as benchmarking for companies and industries

Cons

  • We lose information by definition
  • His interpretation is not unique
  • It is very sensitive to small variations
  • It is just a diagnostic metric
  • It is based on an attitude, intention to recommend, so it depends on personal factors.
  • The criteria for selecting the cutoffs between segments (Promoters, Neutrals and Detractors) is diffuse
  • The emotional component of a recommendation is not measured

Implementation Process

NPS is based on one question:

What is the likelihood that you would recommend Company X to a friend or colleague?

Let's imagine that we have 200 answers:

  • 120 promoters = 60% will recommend
  • 50 passive = they don't care
  • 30 detractors = 15% won't recommend and probably will critizice
  • NPS = 60 – 15 = 45

Procedure

  • [BU/DU] Determine products/services/department to analyze
  • [DP] Prepare and validate questions and execute survey
  • [M] Calculate Promoters, Passive and Detractors
  • [M] Every product/service/department will have a NPS*
  • [E] Analyze results
  • [D] Present and explain the results

Benefits

This technique provides the following benefits:

  • Create actions linked to groups
  • Understand loyalty and satisfaction
  • Discover what products/services should be reviewed
  • Investigate the causes of low loyalty
  • It can help but must be combined with other metrics

Use cases

This technique is used in different use cases:

  • Retention rate: Promoters usually drop out at lower rates than other customers, which means they have longer and more profitable relationships with a company.
  • Annual Expenditure and participation in the portfolio: Promoters increase their purchases faster than detractors, as they tend to consolidate their purchases with their preferred provider. They are more interested in new offerings and brand extensions than detractors.
  • Pricing: The promoters are usually less price sensitive than other customers, particularly detractors.
  • Cost efficiency: Promoters often require less expenses in sales, marketing and advertising than other customers. In addition, the average size of orders is typically larger, leading to lower transaction costs per unit of revenue. Generally they have fewer complaints and represent less credit losses. Their positive attitudes have an effect difficult to quantify, but important in raising morale and employee productivity.
  • Word of mouth: Promoters generate 80 percent to 90 percent of referrals. Quantify (by survey if necessary) the proportion of new customers who selected their company or product because of the reputation or referral. Conversely, detractors represent more negative word of mouth.

Alternatives

Customer satisfaction score (CSAT) is a management tool used to measure a customer’s satisfaction for the service received.

  • Question: How would you rate your over all satisfaction with the service/product you received?

$$ \frac{\hbox{Number of satisfied customers}}{\hbox{Number of total responses}} = \% \hbox{Happy customers}

$$

Customer Effort Score (CES) tries to access how much effort the customer had to put into a particular interaction with the company.

  • Question: How much effort did you personally have to put forth to handle your request?
  • Likert Scale: from 1 (very low effort) to 5 (very high effort).

How to implement this algorithm using R

# Load the library
library(NPS)

# Generate a data set
x <- sample(0:10, prob=c(0.02, 0.01, 0.01, 0.01, 0.01, 0.03, 0.03, 0.09, 0.22, 0.22, 0.35), 1000, replace=TRUE)

# Data Exploration
summary(x)

# Frequency Table
prop.table(table(x))

# Let's draw the histogram
hist(x, breaks=-1:10, col=c(rep("red",7), rep("yellow",2), rep("green", 2)))

# We can use the basic graph library
barplot(prop.table(table(x)),col=c(rep("red",7), rep("yellow",2), rep("green", 2)))

# NPS Calculation
nps(x) # equivalente nps(x, breaks = list(0:6, 7:8, 9:10))

# Standard Error
nps.se(x)

# Variance
nps.var(x)

References

results matching ""

    No results matching ""