A report on

INTERNSHIP

PROCESS MINING VIRTUAL INTERNSHIP

Submitted in partial fulfillment of the requirements

for the award of the degree of

BACHELOR OF TECHNOLOGY
in

Electrical and Electronics Engineering

by

A. Hema Harshitha

214G1A0231

DEPARTMENT OF ELECTRICAL AND ELECTRONICS ENGINEERING

2024-2025
 Department of Electrical and Electronics Engineering

Certificate
This is to certify that the internship report entitled Process Mining Virtual Internship is the
bonafide work carried out by A.HEMA HARSHITHA bearing Roll Number
214G1A0231 in partial fulfilment of the requirements for the award of the degree of Bachelor
of Technology in Electrical and Electronics Engineering for three months from April 2024
to June 2024.

Internship Coordinator Head of the Department

Mr. Y.Satish Kumar M.Tech Dr. G. Meerimatha M.Tech., Ph.D.

Assistant Professor Associate Professor, & HOD

Date: EXTERNAL EXAMINER

Place: Ananthapuramu
 PREFACE

The All India Council for Technical Education (AICTE) is the statutory body and a national
level council for technical education, under the Department of Higher Education, Ministry of
Education, Government of India. AICTE is responsible for proper planning and coordinated
development of the technical education and management education system in India.

EduSkills Foundation is a non-profit organization that enables Industry 4.0 ready digital
workforce in India. EduSkills works closely with students, faculties, educational institutions,
and central/state governments to provide world-class curriculum access, industry exposure,
skill development, and career opportunities.

Purpose: The purpose of AICTE and EduSkills is to improve the quality and relevance of
technical education in India and to create a skilled and employable workforce for the emerging
industries. AICTE and EduSkills have launched several initiatives to provide virtual internship
opportunities for students in technical institutions across the country. The aim of these
initiatives is to bridge the gap between academia and industry by ensuring practical learning
and hands-on experience for the students.

Company’s Mission Statement: To promote quality and innovation in technical

education and research, and to enhance the employability and competitiveness of the graduates.
Providing access to world-class curriculum, skill development, industry exposure, and career
opportunities to students, faculties, and educational institutions across the country.
 ACKNOWLEDGEMENT

The satisfaction and euphoria that accompany the successful completion of any task
would be incomplete without the mention of people who made it possible, whose constant
guidance and encouragement crowned our efforts with success. It is a pleasant aspect that I have
now the opportunity to express my gratitude for all of them.

It is with immense pleasure that I would like to express my indebted gratitude to my

internship coordinator Mr. Y. Satish Kumar, M.Tech Assistant Professor, Department of
Electrical and Electronics Engineering, who has supported me a lot and encouraged me in
every step of the internship work. I thank him/her for the stimulating support, constant
encouragement and constructive criticism which have made possible to bring out this
internship work.

I am very much thankful to Dr. G. Meerimatha, M.Tech., Ph.D. Assiociate Professor,

Head of the Department of Electrical and Electronics Engineering , for his/her kind support
andfor providing necessary facilities to carry out the internship.

I wish to convey my special thanks to Dr. G. Balakrishna, Principal of Srinivasa

Ramanujan Institute of Technology for giving the required information in doing my
internship. Not to forget, I thank all other faculty and non-teaching staff, and my friends who
had directly or indirectly helped and supported me in completing my internship in time.

I also express our sincere thanks to the Management for providing excellent facilities
and support.

Finally, I wish to convey my gratitude to my family who fostered all the requirements
and facilities that I need.
A. Hema Harshitha
214G1A0231
 Contents
Contents Page No
Chapter 1: Introduction 1-2
1.1 Introduction to process Mining 1
1.2 History of Process Mining 2
Chapter 2: Foundations of Process Mining 3
2.1 Features of Process Mining 3-5
2.2 Tools for process mining 5
Chapter 3: Celonis Process Mining: Unveiling Operational Insights 6-13
3.1 Introduction 6
3.2 Celonis Academy 6
3.2.1 Discovery 7
3.2.2 Conformance 7
3.2.3 Enhancement 7
3.3 Registration for Celonis Academy 8
3.4 Level 1: Introduction to Process Mining 9
3.5 Level 2: Process Mining Fundamentals 10
3.6 Level 2: Celonis Rising Star – Technical 12
3.6.1 Write PQL Queries 12
3.6.2 Get data into EMS 13
Chapter 4: Celonis Execution Management System (EMS) 14-23
4.1 Studio 15
4.2 Process Analytics 17
4.3 Process Explorer 18
4.3.1 Basic Configuration 19
4.4 Variant Explorer 19
4.5 Case Explorer 20
 4.6 The Celonis Process Query Language 21
4.6.1 Language Overview 22
Chapter 5: Uses Cases of Process Mining 24
Chapter 6: Applications of Process Mining 25-26
Chapter 7: Learning Outcomes 27
Conclusion 28
Internship certificate 29
References 30
 List of Figures

Fig. No Description Page. No

1.1 Process Mining Model 1
1.2 History of Process Mining 2
2.1 Process Mining features 3
2.2 Variants/Traces associated with the same process 4
2.3 Various Process Mining Tools 5
3.1 Types of process mining 6
3.2 Overview of process mining 7
3.3 Academy Training Platform 8
3.4 Overview of Celonis Rising Stars Program 8
3.5 Module of Use of Charts and Tables KPIs 10
3.6 Celonis PQL Engine 12
4.1 Overview of Celonis EMS 14
4.2 Celonis Studio 15
4.3 Creating New Package 17
4.4 Process Analytics 18
4.5 Example view of Process Explorer 18
4.6 Example of Variant Explorer 19
4.7 Case Explorer Table 20
4.8 Table Columns 21
4.9 Comparing SQL and Celonis PQL by an example
query 22
 LIST OF ABBREVIATIONS

AI Artificial Intelligence

CRM Customer Relationship Management

IT Information Technology

KPI Key Performance Indicator

SAP System Application & Product

ROI Return On Investment

BPM Business Process Management

ABPD Automated Business Process Discovery

SCM Supply Chain Management

EMS Execution Management System

OLAP Online Analytical Processing

PQL Process Query Language

P2P Purchase-to-Pay

EPM Educational process mining

ERP Enterprise Resource Planning

MES Mining Execution Systems

 Process mining virtual internship

Chapter 1

Introduction
In the digital tapestry of organizations, every action, decision, and interaction leaves a
trace— a digital footprint that is frequently hidden by complexity. Welcome to the world
of process mining, where the ordinary transforms into a symphony of revelations,
showing the rhythmic pattern of actions that creates our modern-day reality. Processes
silently coordinate the flow of work, resources, and information in the busy corridors
of businesses and institutions. These procedures control effectiveness, quality, and
success in a variety of industries, including
• e-commerce order fulfilment.
• Patient care, allowing hospitals to streamline workflows for better medical
service.
• Supply chain processes, enhancing coordination and reducing delays.

1.1 Introduction to process Mining

Let us start by defining the term process first. A process is a series of actions or
steps repeated in a progression from a defined or recognized 'start' to a defined or
recognized 'finish'. The purpose of a process is to establish and maintain a commonly
understood flow that allows a task to be completed as efficiently and consistently as
possible. Every business process step leaves a digital footprint in your transactional
systems in the form of event log data.

Process Mining is often described as a technique that analyzes and tracks business
processes based on the data available in the information systems of an organization.
Process mining can help to discover, monitor, improve, and optimize the performance
and efficiency of the processes. Process Mining is the combination of two disciplines:
Data Science and Business Process Management. Process Mining essentially uses Data
Science techniques, such as Big Data and AI, to address Process Science problems such
as process improvement and automation

Fig 1.1 Process Mining model

Department of Electrical and Electronics Engineering Page 1

 Process mining virtual internship

1.2 History of process mining:

Process mining was first introduced as a research discipline by Wil van der Aalst and
his colleagues in the early 2000s. The initial focus was on developing techniques to
extract process models from event logs and on discovering patterns and bottlenecks in
process data.
The history of process mining dates back to the early 2000s when researchers began
developing techniques to analyze event data and extract process models from event logs.
Here are some of the key milestones in the history of process mining :

• 1999: The term “Process mining” was first coined in a research proposal written by
the Dutch computer scientist Wil van der Aalst.
• 2002: The first paper on process mining was published by Wil van der Aalst and his
colleagues.
• 2004: The first commercial process mining tool was released by Fluxicon.
• 2011: The IEEE Task Force on Process Mining was established.
• 2012: The first Process Mining Manifesto was published.

Fig 1.2 History of Process Mining

Department of Electrical and Electronics Engineering Page 2

 Process mining virtual internship

Chapter 2

Foundations of Process Mining

 Process mining is a group of methods for learning about and gleaning insights from
processes by examining the event data produced while the process is being carried
out.
 This training programme offers the theoretical as well as the practical foundations
of process mining.
 Process mining reads this data, transforms it into an event log, and then produces
useful analytics and visualisations of the entire process.
 An event log includes each action taken throughout the process (the activity), the
time the event took place (the timestamp), and the instance of the process the activity
occurred for (the case ID).
 Algorithms create a process model from this event log that depicts the process as it
actually is, complete with the timing of each step and its variations.
Process: A series of linked steps taken in order to achieve a particular goal.
Case: An item or object you follow through the process. Activity: Events
that take place during a process.

2.1 Features of Process Mining:

Process mining encompasses a range of features that provide organizations with

valuable insights into their business processes. These features enable organizations to
understand, analyse, and optimize their processes more effectively. Here are some key
features of process mining:

Fig 2.1 Process mining features

Department of Electrical and Electronics Engineering Page 3

 Process mining virtual internship

 Process Discovery Fact-based understanding of your operations by transforming

data to process maps. It helps organizations discover the truth and make better
decisions based on the evidence found in the organization’s systems
 Compliance Process mining enables an unbiased and fact-based process
compliance checking. By discovering and visualizing the actual process and related
details, companies gain full transparency of their processes.
 Performance Analysis Performance is defined by the efficiency, effectiveness, or
success of an event or an entire process. A high number of process variants indicates
that the process is non-linear and often has a negative impact on the overall
performance.
 Bottleneck Analysis A bottleneck describes the scarcity of resources, products or
manufacturing materials. A bottleneck delays the processor affects its performance,
increasing the throughput time, or even bringing the process to a complete halt.
 Time Analysis The duration of the process results from the length of the individual
activities, which constitutes a process. ’It’s one of the factors that go into measuring
overall process effectiveness and efficiency. A shorter or longer duration may have
a positive or negative impact on a process.
 Process Improvement Process Improvement involves identifying, analyzing, and
improving the existing business processes within an organization for optimization
and to meet quality standards.

Fig 2.2 Variants/Traces associated with the same process

Department of Electrical and Electronics Engineering Page 4

 Process mining virtual internship

2.2 Tools for process mining:

Many organizations and people think that process mining is a tool to model processes.
But the fact is process mining is not a tool it is an analytical method. It is not modelling
something into a process but it can be used to understand the real process. There are
several tools available for process mining, each offering various features and
capabilities to support different aspects of the process mining lifecycle. Here are some
notable process mining tools: ProM, Disco, Celonis, Prometheus, RapidMiner, Minit,
QPR ProcessAnalyzer, Pafnow, ProcessGold, UiPath Process Mining.

Fig 2.3 Various Process Mining Tools

Department of Electrical and Electronics Engineering Page 5

 Process mining virtual internship

Chapter 3
Celonis Process Mining: Unveiling Operational
Insights
3.1 Introduction:

For this virtual internship program, to understand and implement process mining
we have used Celonis software as a platform. Celonis is a powerful and capable process
mining suite that collects and analyses IT data in order to generate actionable insights.
It is used to identify and fix operational flaws, making the overall operation more
effective. Visual reporting is used by Celonis to help find problems in existing
processes. It creates a process flowchart of the company's processes by tracing any IT
supported activities. After that, they will create models for the best solutions and the
various variants that are currently being used. You can view the complete company's
operations in real time, including all active processes.

3.2 Celonis Academy:

Celonis Academy offers training courses on process mining. The courses are designed
to help learners become Celonis experts by providing best-in-class instructor-led
training and goal-based training tracks coupled with hands-on courses. The vast library
of 2,000 hours of online training content is accessible around the clock and free of
charge. The courses cover the fundamentals of process mining in the first week and
advanced concepts of process mining in the second week. The course will provide an
understanding and practice of the three types of Process Mining: Discovery,
Compliance, and Enhancement¹.

Fig 3.1 Types of process mining

Department of Electrical and Electronics Engineering Page 6

 Process mining virtual internship

3.2.1 Discovery:

Process discovery is the initial phase of process mining. Transforming the event log into
a process model is the primary objective of process discovery. Any data storage system
that keeps track of organisational operations and their associated timestamps can
produce an event log. Such an event log must include a case id, an activity description,
and the timestamp at which the action was taken. Typically, a process model that is
representational of the event log is the end result of process discovery. Such a process
model may be found, for instance, by employing methods like the alpha algorithm,
heuristic mining, or inductive mining.

3.2.2 Conformance:

Conformance assists in analysing the differences between an event log and an existing
process model. A discovery algorithm or human construction can both be used to create
such a process model. Conformance checking can be used to evaluate the discovery
techniques, detect deviations, or improve an existing process model. For each option,
the event log is examined to determine whatever data is generally accessible at the time
the decision is taken. Then, traditional data mining techniques are employed to
determine which data items have an impact on the decision. A decision tree is thus
created for each option in the procedure.

3.2.3 Enhancement:

Process enhancement is the strategy that uses the insights from conformance checking
to propel continuous process improvement initiatives, driving efficiency gains and
customer satisfaction. This type of process mining has also been referred to as
extension, organizational mining, or performance mining. In this class of process
mining, additional information is used to improve an existing process model. For
example, the output of conformance checking can assist in identifying bottlenecks
within a process model, allowing managers to optimize an existing process.

Fig 3.2 Overview of process mining

Department of Electrical and Electronics Engineering Page 7

 Process mining virtual internship

3.3 Registration for Celonis Academy:

To access the contents of process mining in celonis, first we have to register in

https://academy.celonis.com/

Fig 3.3 Academy Training Platform

Then to get the Celonis Process Mining Fundamentals certificate, we have to complete
3 levels in the training track namely- Level 1: Introduction to Process Mining Level 2:
Process Mining Fundamentals

Level 3: Celonis Rising Star - Technical

Fig 3.4 Overview of Celonis Rising Stars Program

Department of Electrical and Electronics Engineering Page 8

 Process mining virtual internship

3.4 Level 1: Introduction to Process Mining:

This training track gives us the idea of what process mining is and the basics
of how it works. As per the theoretical foundations of Celonis, Process Mining is the
combination of two disciplines: Data Science and Business Process Management.
Process Mining essentially uses Data Science techniques, such as Big Data and AI, to
address Process Science problems such as process improvement and automation.
Process mining accomplishes this union by reconstructing and visualizing process flows
using the digital footprints left behind by IT systems. From this point, the technology
behind process mining can spot trends and deviations and eventually get rid of
bottlenecks. We will now look more closely at what is needed to reconstruct a process
in this manner.

When it comes to the topic of digital footprint, A digital footprint refers to the trail of
data you leave behind when using the internet. It includes websites you visit, emails
you send, and information you submit online. A digital footprint can be used to track a
person’s online activities and devices. Internet users create their digital footprint either
actively or passively. Whenever you use the internet, you leave behind a trail of
information known as your digital footprint¹.

So, these digital footprints should be retrieved in order to structure them and use them
in the process mining. Here where the event logs play a key role. Event Logs are the
format in which we can retrieve our digital footprints from the underlying IT systems.
They're essentially the log books that IT systems keep to record what events take place
for each Case ID and at what time.

Many different kinds of IT systems, including enterprise resource planning (ERP),

supply chain management (SCM), and customer relationship management (CRM)
systems, can retrieve the Event Log data. These systems frequently produce and archive
Event Log data in real time. In a variety of circumstances and scenarios, from automatic
payment to customer journeys, event log data may also be retrieved.

3.5 Level 2: Process Mining Fundamentals:

This training track provides you with insights into both the theoretical and
applied foundations around Process Mining. The track is structured into three
milestones which consist of multiple courses. Those milestones are:

1. Review and Interpret Analyses

2. Build Analyses

3. Case Study: Pizzeria Mamma Mia

The track contains a good selection of academic reading, software training, and
application examples of where the software is used in real life. It is also accompanied
by quizzes and software exercises to test your knowledge and skills in the software.
Department of Electrical and Electronics Engineering Page 9
 Process mining virtual internship

The Review and Interpret Analyses training track is designed for data
and business analysts, process experts, and process improvement specialists. Keep
in mind, this track is focused mainly on product know-how and less so on business
acumen. If you'd like to complement your own experience in strategically identifying
and prioritizing process inefficiencies, and planning for and implementing
improvement measures, then we recommend you take a look at the Deliver Business
Value with Celonis training track after completing this one.

Here's a sneak peak of what you'll experience in the Review and Interpret Analyses
training track.

Self-paced Reading and Video Demos

Fig 3.5 Module of Use of Charts and Tables KPIs

The Build analyses comes after the completion of Review and Interpret
Analyses. Here, you can configure analytic components using simple clicks and drag
and drop by using the Build Analyses training track. But exactly how? by means of a
combination of: Reading the same material you are currently reading, viewing video
demonstrations, participating in your personal training team's (sandbox) activities, and
of course, responding to exercise questions that call for critical reflection on the
material you have learned.

In Build analyses training track, different concepts are covered including:

• Create a Package and the Analysis Asset.

• Add the Variant and Process Explorers to make the process and all its activities
transparent.

Department of Electrical and Electronics Engineering Page 10

 Process mining virtual internship

• Describe the relationship between data tables and dimensions and KPIs.

• Configure tables and charts with dimensions and KPIs so that users can drill down
into the analysis.

• Configure single KPIs such as the number with a KPI to give users quick snapshots
of the health of the process.

• Add Dropdowns and configure them with dimensions, and add Date Pickers to
allow users to restrict the analysis to their desired time period.

• Use the Visual Editor to customize Standard Process KPIs and even build KPIs
from scratch using the visual formula builder.

• Add the Conformance checker sheet to the analysis and even add custom KPIs to
it.

• Create background filters (layers) at component, sheet, and Analysis-level that the
end user cannot remove

• Add a dropdown to an OLAP table so that the end user can select the Dimension
to display from a list.

A dimension is a category of attributes; for example, the dimension "customer name"

is a category for individual customer names. Other examples of dimensions, depending
on the nature of the process, can include vendor name, sales organization, region, and
material group.
bullet
Key Performance Indicators (KPIs) are used to calculate and add aggregated values;
for example, case count, order value, invoice value, throughput time, and automation
rate.

In the case study part, we are looking at the digitization journey of the Pizzeria Mamma
Mia from the perspective of Giovanni, the owner of the business, and Martin, his Junior
Manager. The Order-to-Cash process (O2C), which is the foundational procedure of the
Munich-based company, will be the subject of attention. The journey begins with the
digitalization of all process steps, continues with the identification of inefficiencies and
bottlenecks, and concludes with recommendations for both immediate improvements
and for maintaining the success of the firm.

After deciphering and understanding the Pizzeria Mamma's ordering procedure, we

should assess how our conclusions will affect the success of the company. What impact
can process optimisation have on the pizzeria's financial performance? First of all, the
removal of bottlenecks can have a favourable impact on the effectiveness, speed, and

Department of Electrical and Electronics Engineering Page 11

 Process mining virtual internship

quality of the process. High-level key performance measures like sales figures, costs,
and customer happiness are then improved as a result of these.

3.6 Level 2: Celonis Rising Star – Technical:

In this level, we have to complete 2 training tracks-

• Write PQL queries

• Get data into EMS

3.6.1 Write PQL Queries:

It is crucial for Process Mining users to formalise their process questions

as executable queries in order to obtain insightful process knowledge. We present the
Celonis Process Query Language (Celonis PQL) for this purpose, which is: a
businessoriented, domain-specific language that is geared towards a specific process
data model. It creates queries from process-related business questions and runs them on
the Celonis PQL Engine, a specially created query engine.

The PQL is a domain-specific language tailored towards a special process data model
and designed for business users. PQL enables the user to translate process-related
business questions into queries, which are then executed by a custom-built query
engine. PQL covers a broad set of operators, ranging from process-specific functions to
aggregations and mathematical operators. Its syntax is inspired by SQL, but specialized
for process-related queries. Even though Celonis PQL is inspired by SQL, there are
major differences between the two query languages.
• Celonis PQL does not support all operators that are available in SQL.
• Second, Celonis PQL is not supported by a data manipulation language (DML).
• Furthermore, Celonis PQL does not provide any data definition language (DDL).
• In contrast to SQL, Celonis PQL is domain-specific and offers a wide range of
Process Mining operators not available in SQL.

Fig
3.5 Celonis PQL Engine
Department of Electrical and Electronics Engineering Page 12
 Process mining virtual internship

3.6.2 Get data into EMS:

In this topic we will study about two types they are:

• Set up a data pipeline

• Refine your Data Pipeline

In the set up a data pipeline again divide into sub parts they are-

1. Data Integration basics

2. Connect to Systems

3. Extract Data

4. Transform Data

5. Load a Data Model-

In the Refine your Data Pipeline divide into parts they are-

1.Schedule Data Jobs

2.Monitor and validate your Data pipeline

3.Multiple Process and Systems

4. Boost your EMS SQL Transformations

5.Connect Custom processes

6.Quality Assuring your Data Pipeline

In the next chapter, we will get to know about EMS in detail.

Department of Electrical and Electronics Engineering Page 13

 Process mining virtual internship

Chapter 4

Celonis Execution Management System (EMS)

The Celonis Execution Management System (EMS) enables the team to apply
real-time business intelligence to the data in your systems. Celonis Execution
Management System (EMS) has Process Mining Technology as its base, which supports
the rest of Celonis products, from data gathering to exploring, analyzing, and devising
solutions.

A team in EMS is specific to an organization. It comprises members of an

organization that your team admin invited. Note that the array of licensed products
may differ depending on your team’s license.

The Celonis EMS comprises the following features:

• Studio and PQL: Transparency into how your process runs

• Data Integration: Flexible development platform for data integration projects.
New Celonis Connector Technology
• Marketplace: Instead of weeks of IT setup, install and setup Marketplace Apps
with a couple of clicks

Process Analytics by Celonis EMS provides you with insights into how your process
is. With Process Discovery, process visualizations show you what’s happening in your
processes; so, you can quickly identify opportunities to increase revenue, free capital,
and ensure customer satisfaction.

Fig 4.1 Overview of Celonis EMS

Department of Electrical and Electronics Engineering Page 14

 Process mining virtual internship

4.1 Studio:

The Studio allows you to combine functional expertise with the power of Celonis
Process Mining to create scalable Apps. Celonis Studio is your one-stop development
platform to build, test, and edit Execution Apps and Instruments in a single, low-code
interface.

Benefits of Celonis Studio

• Create or configure an Execution App in days.

• Reuse components from your best deployments.
• Combine analytical and execution capabilities.
• Leverage template views for each business user.

Fig 4.2 Celonis Studio

You can access Studio via the left-hand navigation menu.

Your business users can access your apps by clicking on the left-hand navigation menu
and selecting "Apps".

Core components of an app

The Studio is structured by your Apps, also called Packages. Packages are collections
of Views, Knowledge Models, Skills and Analyses.

Views in a Studio app

Views are the key user experience component for new Apps built on Celonis. They
empower your business users with a unified interface to consume data, create insights
and act on knowledge.
A View is a collection of components and tools to provide business users with focused
access to our business context and engines. Learn how to configure and use Views.
Department of Electrical and Electronics Engineering Page 15
 Process mining virtual internship

Knowledge Models

Knowledge Models act like a centralized place to consistently and reliably define
metrics through configuring Business Knowledge Entities. Business Knowledge
Entities are concrete definitions of KPIs, Benchmarks, Variables, Filters, and many
more. Standardizing the development and definition of these commonly used Business
Knowledge Entities solves a crucial scalability problem, ensures consistency across the
enterprise, and accelerates optimization efforts through the reuse of commonly used
Business Knowledge Entities. Learn how to build and use Knowledge Models.

Skills

A Skill is the integral part of each automation as it defines its procedure by a sequence
of events. It consists of Sensors and Actions. Learn how to make use of automation in
your Execution App.

Analysis

An Analysis helps to identify execution gaps in your process. Within a Package, you
can create Analyses as you might know from Process Analytics. Currently, there are
slight differences between the analysis service offered in Process Analytics and the
analysis service that is offered in the Package. Creating analyses in the studio has the
benefit of versioning and better integration with other services offered by Celonis. It is
now possible to keep multiple analyses with different data models next to each other.

To create an analysis in a package, you need to hover on the package name, click on the
“+” sign, and select the “Analysis” option. You can then define the name of the analysis
and the data model variable to assign the analysis to a data model. The Analysis Key is
used to link other assets such as views to this Analysis.

Folders

Folders can be used inside packages for organizational purposes. Inside a package, you
can create as many folders as you want, and you can directly create new assets inside
the folders or move existing assets inside folders with drag and drop. Furthermore, you
can create folders inside folders, however, you cannot have more than nine levels of
folder hierarchies. This is limited for usability purposes. Also, it is not possible to set
permissions on folders, for this capability, see Studio Spaces or Studio Packages.

Department of Electrical and Electronics Engineering Page 16

 Process mining virtual internship

Working with packages

Creating a package

You can create a new Package within the Studio.

1. Select “New Package” on top of the left-hand navigation panel.

2. Name the Package.
3. When naming a Package, the Package Key will automatically populate. This key
is a unique identifier of the package.
4. Select the Package Type (App, Library or Instrument).
5. Press Create.

Fig 4.3 Creating New Package

Please note that the package name can be changed later, however, the package key as a
unique identifier cannot be changed after being defined.

Also, the package type cannot be changed after creating the package. You can find
information on your package by clicking on the three-dot menu next to the operational
app and then select settings.

4.2 Process Analytics:

Process Analytics is a feature of the Celonis (EMS) that provides insights into
how your process is. With Process Discovery, process visualizations show you what’s
happening in your processes; so you can quickly identify opportunities to increase
revenue, free capital, and ensure customer satisfaction. Process Analytics by Celonis
EMS provides you with insights into how your process is.

Department of Electrical and Electronics Engineering Page 17

 Process mining virtual internship

Fig 4.4 Process Analytics

To check, look for the Process Analytics icon in the navigation bar.

4.3 Process Explorer:

The Process Explorer is an analysis tool to use when taking an exploratory approach. It
starts with showing the most frequent activities and connections. You can add further
additional activities to the graph and analyze their impact on the process. Any number
of Event Logs can be visualized together to understand the relationships between
multiple processes.

Similar to the Variant Explorer, the Process Explorer allows you to filter on activities
and relationships. Although the Activity and Connection panels are not a part of Process
Explorer, activities and connections can still be used to filter on cases. The experience
of filtering will be comparable to that of the Variant Explorer.

Fig 4.5 Example view of Process Explorer

Department of Electrical and Electronics Engineering Page 18

 Process mining virtual internship

There are two main configuration options for the process explorer:

• Basic Configuration
• Advanced Configurations

But we use only Basic Configuration.

4.3.1 Basic Configuration:

To configure a basic process explorer, you must define the event logs you wish to
visualize in the component. Ensure that prior to creating a process explorer component
you have the event logs defined in the eventLogsMetadata section of the Knowledge
Mode.

4.4 Variant Explorer:

With the aid of the Celonis EMS Analysis tool Variant Explorer, you can
investigate the movement of a particular process inside your company. Each process
variant would represent a potential path if we imagined a process to be a road trip. Each
step in a process may be compared to a waypoint on a route, and the connections
between steps could be compared to the roads that link the stops. Each journey a person
takes along a specific path would also constitute a case.

Using Variant Explorer, you can see the individual activities within each process
variant and the frequency of each variant. You can also compare variants to each other
and see metrics for individual variants, such as Activity Frequency .

In short, Variant Explorer gives you a quick way to see whether most process cases
follow an acceptable flow of activities or not and helps you develop your first analysis
questions.

Fig 4.6 Example of Variant Explorer

Department of Electrical and Electronics Engineering Page 19

 Process mining virtual internship

4.5 Case Explorer:

The Case Explorer is one of the default analysis screens of Celonis Execution
Management System (Celonis EMS). The Case Explorer displays the data tables
connected to the Celonis engine and is an intuitive tool for examining cases and their
respective activities.

Case Explorer Table

Fig 4.7 Case Explorer Table

The data provided by the data sets are organized by the Case Explorer and presented as
a table.

1. Column sort: each column represents one of the imported columns from
the data set. When clicking in a column, it is possible to sort the entire
table according to the column content in ascending or descending order.

2. Table Column editor: opens up the table columns panel.

3. Case selector: each row of the Case Explorer table refers to a specific
case. The case details panel opens when clicking on a row.

4. Activity table divisor: line determining the division between the core
elements of the activity table (case ID, activity, and timestamp) located to
the left and the accessory elements from the activity table or other linked
tables, to the right.

Department of Electrical and Electronics Engineering Page 20

 Process mining virtual internship

Fig 4.8 Table Columns

The Table Columns tab allows you to select which columns will be displayed on the
Case Explorer table.

1. Column search: search for a column by its name.

2. Database: database from which the columns were extracted. Click on it

to list the column options.

3. Column selector: each name on the list refers to a column on the case
explorer table. If one or more columns are selected, the Case Explorer
table will display only display these together with the core activity table
columns (case ID, activity, and timestamp).

4. Reset: resets the column selection and reverts to the default view.

4.6 The Celonis Process Query Language:

The intention of Celonis PQL is to provide a query language for performing process
mining tasks on large amounts of event data. As described in Section 2.2, it is based on
a relational data model. The event and business data as well as all results (including the
mined process models) are represented as relational data. Currently, the supported data
types comprise STRING, INT, FLOAT, and DATE. Boolean values are not directly
supported, but can be represented as integers. Each data type can hold NULL values. In
general, Celonis PQL treats NULL values as non-existing and ignores them in
aggregations. Also, row-wise operations like adding the values of two columns will
return NULL if one of its inputs is NULL.

Operators usually create and return a single column that is either added to an existing
table (e.g. the case or activity table) or to a new, temporary result table. Only a few
operators (e.g. for computing a process graph) create and return one or more tables with
multiple columns. However, these operators are only used internally by GUI
components and are not exposed to the end-user. Currently, Celonis PQL provides more
than 150 different operators to process the event data. Due to space limitations, we
cannot sketch the full language. However, we can offer a brief overview of the major

Department of Electrical and Electronics Engineering Page 21

 Process mining virtual internship

language features before we present selected examples to showcase the expressiveness

of the language. Comprehensive documentation of the Celonis PQL operators can be
accessed via the free process mining platform Celonis Snap1.

4.6.1 Language Overview:

Even though Celonis PQL is inspired by SQL, there are major differences between the
two query languages. Figure 6 shows these differences by comparing how to query the
cases and the number of involved departments for all orders with a value of more than
1000 euros in both languages. Furthermore, it also illustrates the key concepts of
Celonis PQL.

Fig 4.8 Comparing SQL and Celonis PQL by an example query

Similar to SQL, Celonis PQL enables the user to specify the data columns to
retrieve from the data model. This can either be an aggregation, which we call a KPI,
or an unaggregated column, which we call a dimension. While the data columns are part
of the SELECT statement in SQL, Celonis PQL requires them to be wrapped in the
TABLE operator, which combines the specified columns into a common table.

In contrast to SQL, Celonis PQL does not require the user to define how to join
the different tables within the query. Instead, it implicitly joins the tables according to
their foreign key relationships which have to be defined only once in the data model.
Also, the grouping clause is not needed in. A Query Language for Process Mining
Celonis PQL as each selected column which is not aggregated (i.e. a dimension) is
implicitly used as a grouper. According to the design goals, implicit joins and groupings
significantly reduce the size and complexity of the queries and make it much simpler to
formulate them.

Both languages offer the possibility to filter rows. While SQL requires the user
to formulate the filter condition in the WHERE clause of the query, Celonis PQL offers
the FILTER statements which are separated from the TABLE statements but executed

Department of Electrical and Electronics Engineering Page 22

 Process mining virtual internship

together. Splitting the data selection and the filters into different statements enables the
user to define multiple filter statements in different locations inside an application,
which then can be combined into the table statement to query the data. Beyond this
simple structure, Celonis PQL provides a wide range of different operators which can
be combined to answer complex business questions. The following list gives an
overview of the most important classes of operators.

Aggregations.

Celonis PQL offers a wide range of aggregation functions, from simple standard
functions like count and average, to more advanced aggregations like standard deviation
and quantiles. Most of the aggregation functions are also available as window-based
functions computing the aggregation not over all values but over a user-defined sliding
element window.

Data functions.

These are operators like REMAP_VALUES and CASE WHEN which allow for
conditional changes of values.

Date and time functions.

These functions enable the user to modify, project or round a date or time value, e.g.
add a day to a date or extract the month from a timestamp. There are also functions to
compute date and time difference (e.g. between timestamps of events).

Index functions.

Index functions create indices based on columns. The function

INDEX_ACTIVITY_LOOP, for example, returns for each activity how many times it
has occurred in direct succession in a case. This is useful, e.g., for identifying selfloops
and computing their cycle lengths.

Machine learning functions.

There are various machine learning functions available, e.g., to cluster data using the
kmeans algorithm or learn decision trees.

Math functions.

Celonis PQL offers a wide range of mathematical functions, e.g., for arithmetic
computations, rounding float numbers, and computing logarithms.

Department of Electrical and Electronics Engineering Page 23

 Process mining virtual internship

Chapter 5
Use cases of Process Mining
1. Process Discovery: Process mining helps visualize and understand real-world
processes based on event logs. This aids in identifying bottlenecks,
inefficiencies, and variations in the processes.

2. Conformance Checking: By comparing actual process executions with the

intended process model, organizations can detect deviations, compliance issues,
and potential areas of improvement.

3. Performance Analysis: Process mining allows organizations to analyze process

efficiency, cycle times, resource utilization, and other performance metrics. This
data helps optimize workflows and enhance overall productivity.

4. Root Cause Analysis: Process mining enables the identification of root causes
behind bottlenecks, delays, or errors within processes. This information is
crucial for making targeted improvements.

5. Predictive Analytics: Utilizing historical process data, predictive analytics can

forecast future process behavior and outcomes. This assists in making informed
decisions, resource allocation, and planning.

6. Process Enhancement: Process mining facilitates the iterative improvement of

processes by pinpointing areas that could benefit from automation, optimization,
or streamlining.

7. Risk Management: By analyzing process data, process mining helps detect

potential risks and compliance violations. This proactive approach ensures
adherence to regulations and minimizes potential issues.

8. Customer Journey Analysis: Process mining sheds light on customer

interactions and experiences within processes. This insight helps organizations
enhance customer satisfaction by addressing pain points.

9. Supply Chain Optimization: Process mining is applied to analyze end-to-end

supply chain processes. By identifying inefficiencies and opportunities for
improvement, organizations can optimize their supply chain operations.

10. Healthcare Process Improvement: In the healthcare sector, process mining is

used to optimize patient care pathways, allocate resources efficiently, and
enhance overall hospital operations. This ultimately leads to better healthcare
outcomes.
Department of Electrical and Electronics Engineering Page 24
 Process mining virtual internship

Chapter 6
Applications of Process Mining
Process mining has a wide range of use cases across various industries and
sectors, showcasing its versatility in uncovering insights and optimizing business
processes. Here are some notable use cases of process mining:

1. Accounts Payable Optimization:

Process mining can analyze the end-to-end accounts payable process,

identifying bottlenecks and inefficiencies in invoice processing, approval workflows,
and payment cycles. Insights gained can lead to streamlined invoice handling, reduced
payment delays, and improved vendor relationships.

2. Order-to-Cash Analysis:

By examining the order-to-cash process, process mining can uncover delays,

errors, and opportunities for optimization in order processing, fulfillment, and cash
collection. Improved order processing can lead to enhanced customer satisfaction and
reduced lead times.

3. Supply Chain Visibility:

Process mining can provide end-to-end visibility into supply chain processes,
helping organizations identify delays, stockouts, and inefficiencies in procurement,
production, and distribution.Enhanced supply chain management can lead to reduced
costs, improved inventory control, and optimized resource allocation.

4. Manufacturing Process Analysis:

Process mining can analyze manufacturing processes to identify production

bottlenecks, optimize resource allocation, and reduce cycle times. Insights gained can
lead to increased manufacturing efficiency and improved product quality.

5. Healthcare Process Optimization:

In healthcare, process mining can analyze patient pathways, identifying delays

and bottlenecks in patient care processes. Improved patient flow can lead to reduced
waiting times, enhanced patient experiences, and better resource utilization.

6. Customer Journey Analysis:

Department of Electrical and Electronics Engineering Page 25

 Process mining virtual internship

Process mining can map the customer journey across various touchpoints,
helping organizations understand customer interactions and behaviors. Insights can
drive personalized marketing strategies and improvements in customer service.

7. IT Incident Management:

In IT service management, process mining can analyse incident response

processes, identifying delays in issue resolution and areas for improvement. Optimized
incident management can lead to reduced downtime and improved IT service quality.

8. Loan Application Processing:

Process mining can analyse loan application processes in banking, identifying

bottlenecks in approval workflows and credit assessments. Streamlined processes can
lead to faster loan approvals and enhanced customer experiences.

9. Energy Consumption Analysis:

Process mining can analyse energy consumption patterns in industrial settings,

identifying energy-intensive processes and opportunities for energy conservation.
Insights can lead to reduced energy costs and improved sustainability.

10. Public Sector Process Optimization:

Process mining can analyse government processes, such as permit approvals or

license renewals, to identify bottlenecks and streamline citizen interactions. Optimized
processes can lead to improved public service delivery and reduced administrative
burden.

11. Retail Inventory Management:

Process mining can analyse inventory management processes, helping retailers

optimize stock levels, reduce stockouts, and improve demand forecasting. Insights can
lead to improved inventory turnover and cost savings.

12. Digital transformation:

Digital transformation is a must for any organization wanting to thrive in its

current market. Process mining provides leaders and change managers with end-to-end
visibility of their processes, making it easy to identify areas in need of improvement.

These use cases highlight the diverse ways in which process mining can be applied to
uncover insights, optimize processes, and drive operational excellence across industries.

Department of Electrical and Electronics Engineering Page 26

 Process mining virtual internship

Chapter 7

Learning Outcomes
After completing this course, you ought to be able to:

• Recognize what process mining is and the fundamental principles underlying

its operation.
• Recognizing the benefits of process mining in the business environment.
• Explain the basics of an event log and why we need one for processing.
• Determine the business applications of process mining.
• Learn where to go for training classes to begin going.
• An understanding of data-driven approaches for finding, analysing, and
improving business processes.
• You'll discover how to analyse event logs for insights, spot bottlenecks,
inefficiencies, and optimization possibilities.
• Additionally, you will learn how to extract data from processes to build visual
representations of them to support decision-making and process improvement
initiatives.
• It is important to comprehend how process mining can be used to find
inefficiencies and inadequate process approaches.
• To find process inefficiencies, interpret process visualizations and make use of
analysis.
• Consider the actions and cases involved in your process.
• Export visualizations, analyse data, and save an analysis selection for later use
and team collaboration.
• Carry out the fundamental duties required to construct Celonis analysis.
• Get to know Analysis Settings and Permissions.
• Post analyses utilizing version control best practices.
• Put your understanding of the theoretical underpinnings of process mining to
use.

Department of Electrical and Electronics Engineering Page 27

 Process mining virtual internship

Conclusion
In conclusion, process mining is a strong and adaptable technique that delivers useful
insights into the inner workings of organizational processes. Process mining reveals
hidden patterns, reveals inefficiencies, and offers practical suggestions for process
optimization by examining event data produced during the execution of processes. A
number of different sectors, including manufacturing, healthcare, banking, logistics,
and customer service, could benefit from this technology.

Process mining techniques are anticipated to become even more advanced and
integrated with other data-driven methodologies as technology develops, thereby
enhancing their capacity to promote process excellence. However, a thorough grasp of
both the technology and the underlying business processes is necessary for the
successful deployment of process mining. By utilizing the potential of data-driven
insights to continuously improve their operations and reach higher levels of efficiency
and effectiveness, businesses that adopt process mining stand to earn a competitive
edge.

Department of Electrical and Electronics Engineering Page 28

 Process mining virtual internship

Internship Certificate

Department of Electrical and Electronics Engineering Page 29

 Process mining virtual internship

References
1. Badakhshan, P., Geyer-Klingeberg, J., El-Halaby, M., Lutzeyer, T. and Affonseca,
G.V.L., 2020, September. Celonis Process Repository: A Bridge between Business
Process Management and Process Mining. In BPM (PhD/Demos) (pp. 67-71).
2. Vogelgesang, T., Ambrosy, J., Becher, D., Seilbeck, R., Geyer-Klingeberg, J. and
Klenk, M., 2021. Celonis PQL: A query language for process mining. In Process
Querying Methods (pp. 377-408). Cham: Springer International Publishing.
3. Van Der Aalst, W., 2012. Process mining: Overview and opportunities. ACM
Transactions on Management Information Systems (TMIS), 3(2), pp.1-17.
4. Reinkemeyer, L., 2020. Process mining in action. Process Mining in Action
Principles, Use Cases and Outloook.
5. Turner, C.J., Tiwari, A., Olaiya, R. and Xu, Y., 2012. Process mining: from theory
to practice. Business Process Management Journal, 18(3), pp.493-512.
6. https://en.wikipedia.org/wiki/Process_mining
7. https://docs.celonis.com/en/celonis-documentation.html

Department of Electrical and Electronics Engineering Page 30