Introduction

The Pareto Analysis is a statistical technique employed in decision-making to identify a limited set of tasks to produce the most significant effect. We base it on the Pareto Principle, which stipulates that 20% of the work on a project generates 80% of the outputs.

The technique is also known as the 80/20 rule, the principle of factor sparsity, and the rule of the vital few and the trivial many.

Pareto Principle

In the 1940s Armenian-American management consultant Joseph Juran developed the Pareto principle. Juran named the principle after Italian economist Vilfredo Pareto, who, in 1906, documented that 80% of income goes to 20% of the population. At first, he noticed it in Italy but later conducted surveys in other countries and observed the same distribution.

We can apply the 80/20 rule in almost any situation:

  • 20% of system defects cause 80% of problems with usage;
  • 20% of the sales force provides 80% of the revenue;
  • 20% of products generate 80% of complaints;
  • 20% of the product portfolio makes 80% of the profit.

After looking into the work of Pareto and Juran, the British NHS Institute for Innovation and Improvement observed the Pareto distribution in the following scenarios:

  • 20% of employees come up with 80% of innovations;
  • 20 of efforts gives 80% of personal success;
  • 20% of provided services account for 80% of customer complaints;
  • 20% of the time in meetings generates 80% of the taken decisions.

The Pareto principle is widely applied in quality control, as it is the base of the Pareto diagram, which is a critical tool in quality control and Six Sigma. The value provided by the Pareto principle is that it reminds project managers to focus on the 20% of things that matter, the 20% that are crucial. Only after that, they should focus on the other 80%.

We need to remember that the 80/20 rule is mostly a rule of thumb, and we should not consider it as something precise. It is roughly presented by the power-law distribution (Pareto distribution) for a set of parameters. In reality, many phenomena exhibit such distribution.

Pareto Analysis

The Pareto Analysis is useful where we have many possible courses of action fighting for attention. The benefit of each activity is estimated, and on this basis, we select several most beneficial steps to deliver the maximum possible outcome.

By employing Pareto analysis, we can identify the top portion of causes that have to addressed to resolve the majority of problems. Then we need to apply other tools to identify the root causes of these problems.

A problem with the Pareto technique is that we may limit the analysis by the exclusion of possibly significant issues that may be small at the beginning, but will grow with time.

Steps of Pareto Analysis

To perform Pareto analysis, we would typically follow the following approach:

  1. Identify the problems;
  2. Identify the causes of those issues;
  3. Rank the issues based on the extent of negative impact on the company;
  4. Organize them in groups;
  5. Develop and implement action steps to solve problems, starting with higher scored ones first.

Following the steps above, we notice that not all problems get a high score and some are not worth going after initially. By focusing on high-impact issues, the company can allocate the proper resources to fix the problems that have the highest negative impact on profits, growth, sales, customer satisfaction, and others.

Pareto analysis proves we can achieve more improvements by concentrating on solutions with the most substantial impact. It is important to remember that the technique does not give the answers to the issues, but only shows which are the fundamental causes of the majority of the company’s problems. The basic premise is that not all inputs have the same or proportional impact on output.

Multi-Level Pareto Analysis

Pareto Analysis helps us in identifying the significant problems the company needs to focus on to get the most benefits. What we can then do is go another step further. By looking into the reasons for a specific problem, we can perform a second-level Pareto analysis of these reasons within a single issue and get a better understanding as to where to focus company resources.

Weighted Variables in Pareto Analysis

It’s common to assign weights to problems to emphasize issues that the company management believes to have a more significant impact on performance. We use the weights to normalize the contribution of the causes. We then base the Pareto Analysis and our Pareto chart on the weighted contributions.

Pareto Chart

The Pareto chart is a type of diagram representing individual values in descending order as bars, and the cumulative total as a line graph. We show the frequency of occurrence alongside the left vertical axis, and the right axis is the aggregate percentage of total occurrences.

We show values in decreasing order, so the cumulative line follows a concave function. The Pareto chart aims to highlight the most critical factors from a usually large set of factors.

The Pareto diagram serves as a visual representation of the vital few against the trivial many.

Example

The best way to understand the benefits of the Pareto Analysis is to illustrate it with a real-life example. As part of our initial user base testing, we ran a survey (fill it here for a free bonus benchmark template).

One of our questions was aiming to figure out the most laborious tasks financial analysts face when analyzing financial data:

After we gathered about a 100 responses to our survey, we can run our preliminary analysis of the collected data. Google Forms gives us the following chart for the answers people checked:

It is easy to see that most people struggle with the collection of the required data. After this we have five options with similar count. To better analyze their importance, let us apply a Pareto Analysis and prepare a Pareto Chart.

First, we need to export the data from Google Forms and prepare it for analysis. We will not be looking into the process of data preparation, as it is not the subject of the article. After a few steps, we get the following Pivot table with the options and the count of how many times they were selected:

Organizing it a bit better and preparing short Chart Handles we can sort by count in descending order, to get the data ready for our Pareto Chart:

We can then calculate the cumulative percentage at each of the options. We can also separate the options to Primary and Secondary based on when the increasing percentage passes the 80% Pareto line. We will also show the Primary Selection of options in a separate column, to facilitate building a better visual representation in our Pareto Chart.

Having this, we can use a Combo Chart to create our Pareto graphical representation. The first five options give us most of the problems (77% to be exact) that users are facing.

Having the Pareto Chart is an easy to read visual representation of the issues we should focus on solving so that we get the maximum effect. We have now identified the major problems we need to address in our product, to provide the most significant benefit to our customers.

It’s obvious here that the 80/20 rule is more like the 80/50 rule, as about half of customer concerns are causing 80% of complaints. It is important to remember that the Pareto Principle is more of a rule of thumb, and we should not be looking for the same distribution whenever we perform Pareto Analysis.

From the perspective of Magnimetrics, we can see that in this case, the Pareto Chart is a helpful way to identify the features we need to develop first so that we can provide a product that adds actual value to our customers’ businesses.

Conclusion

In summary, Pareto analysis is a technique used for decision-making based on the 80/20 rule. We separate a limited number of input factors as having the most impact on outcomes, either favorable or unfavorable.

It is important to remember that the Pareto analysis only applies to historical data; it is as good as the data we input, and will not help us in forecast analysis. It is also a great tool to use when we need to allocate limited resources to tackling many problems within our organization.

Don’t forget to download the Excel model file below:

Dobromir Dikov

FCCA, FMVA, Co-founder of Magnimetrics

Hi! I am a finance professional with 10+ years of experience in audit, controlling, reporting, financial analysis and modeling. I am excited to delve deep into specifics of various industries, where I can identify the best solutions for clients I work with.

In my spare time, I am into skiing, hiking and running. I am also active on Instagram and YouTube, where I try different ways to express my creative side.

Subscribe to our monthly newsletter and never miss on Magnimetrics!

The information and views set out in this publication are those of the author(s) and do not necessarily reflect the official opinion of Magnimetrics. Neither Magnimetrics nor any person acting on their behalf may be held responsible for the use which may be made of the information contained herein. The information in this article is for educational purposes only and should not be treated as professional advice. Magnimetrics accepts no responsibility for any damages or losses sustained in the result of using the information presented in the publication.