CANDIDATE

GUIDE

DATA SCIENCE COUNCIL OF AMERICA

©2024. DATA SCIENCE COUNCIL OF AMERICA. ALL RIGHTS RESERVED.
Hello!
Welcome to the starting blocks of your ABDA™ journey!

This Candidate Guide seeks to share some of the key structural

features of the ABDA™ program, and also some important
aspects of the responsibilities of data analysts - those that will
help you plan for not only the ABDA™ exam but also for meeting
the larger expectations that the industry has from you as an
ABDA™ credential-holder.

To begin with, it is important to appreciate that the 8 knowledge

areas prescribed by DASCA for Associate Big Data Analysts are
intricately connected to the real-world roles they get to play in
the most complex of organizations. To most ABDA™ applicants,
this fact has been the strongest indicator that probably the best
way to prepare for the ABDA™ exam is to prepare yourself to
excel in the aspects of data analytics and technical expertise that
organizations have from their data analysts. And understand the
policies and processes thoroughly before attending the exam.

2
Skills and Knowledge
Potential…
Earning the ABDA™ is more than qualifying for
the ABDA™ certification exam – it means being
transformational and insightful in your role as a
data analyst. Here are some ways the ABDA™
can help you drive organizational change and
stand out in your workplace as a data analyst…

3
Impact Revenues, Costs & Growth
As an Associate Big Data Analyst, you will be equipped with the
knowledge, skills, and experience required to drive efficient and forward-
looking organizational strategy through data intelligence. Organizations
look to their data analysts for insights to help them accomplish tasks
quicker, earlier, and cost-effectively. ABDA™ credential holders reflect this
acumen to increase growth in their organizations and provide a significant
competitive advantage.

Advanced Skills to Enhance

Efficiencies
ABDA™-certified professionals work in strategic data analytics functions in
many organizations. By leveraging their skillset in improving outcomes and
developing insights through big data, ABDA™ professionals contribute a lot
to their organization’s decision making practices. This skillset includes
analyzing large data sets to identify patterns, using data visualization tools,
developing data storage systems, and creating coherent reports and
presentations to communicate insights.

4
Perspective for Smart Change
High-impact ABDA™ professionals think outside the box and provide a
unique perspective on success metrics, functional scorecards and business
strategies for their organization. As an aspiring ABDA™ credential holder,
you must look at ways that big data can help you create a differentiating
factor for your organization, whether that is through overcoming legacy
disadvantages or identifying historical patterns to deal with difficult
situations.

Vision for Business Intelligence

As an Associate Big Data Analyst, you are expected to deploy data in a
way that generates intelligence for organizations and keeps them at the
forefront of their industry. ABDA™ credential holders enable organizations
to become nimble, agile, and proactive during times when change is quick
and unpredictable. Some key areas of focus must be enhancing the results
of systems and processes through automation, providing insight on
lucrative markets, product segments and unique business opportunities,
and improving customer engagement and reach through internal and
external data.

5
 About ABDA™ exam
The ABDA™ exam carries multiple-choice,
single-answer questions carrying equal marks,
with no penal scoring for wrong answers. A
typical DASCA certification exam carries a mix
of questions that seek to test the accuracy of
knowledge of principles and concepts;
understanding of techniques and processes;
and the skills to apply tools and techniques of
programming and analysis in solving real data
problems. The exam questions are drawn
from 8 knowledge areas prescribed for data
scientists in the DASCA framework. ABDA™
exam has 75 questions and the duration of
the exam is 100 minutes.

6
Exam Coverage

Foundations of Data Science

Understanding the role of the data scientist; tapping the power of Python and R in 15%
making sense of data and deriving information and intelligence for decision-making.

The Mathematics of Data Science

Refreshing important quantitative techniques and tools deployed in data analytics and 20%
model optimization including Statistics, Linear Algebra, Probability and Calculus.

Dealing with Data

Understanding data types, data origination modes, streaming data; learning the 15%
frameworks of analyzing, managing and harnessing massive data using tools and
applications like Python and R.

Doing Data Analytics

Capturing, processing, sorting, classifying, analyzing, managing and harnessing big data 15%
using the Hadoop ecosystem; understanding the use of combination of tools like R,
Python and MapReduce etc., in big data analytics.

Data Visualization
Understanding the needs, building blocks and basic mechanisms of data visualization; 18%
using popular visualization applications like Tableau to visualize and present
information results.

Big Data in Machine Learning & Ai

Foundational concepts and framework of machine learning and artificial intelligence; 7%
understanding how big data analytics fires machine intelligence; using R and Python in
ML and AI applications.

Enterprise Applications of Data Analytics

Planning, design and implementation framework for big data analytics solutions in 5%
organizations; deploying R and Python in business-level data analytics; going to
production with R.

Implementing Analytics
Understanding of databases and data pipelines deployed in big data analytics; 5%
applications of document-oriented NoSQL database in high volume data storage and
processing using MongoDB; fundamentals of messaging systems; Elasticsearch
enterprise big data search; and big data processing on cloud.

7
Exam Format
The ABDA™ examination aims to check and validate the accuracy and
breadth of the candidate's core knowledge and skills related to advanced
data analytics; data governance; business intelligence infrastructure among
other topics included in the knowledge areas.

Know The Question Format

ABDA™ exam questions may fall within any of the following three
categories:
TYPE A- GENERAL UNDERSTANDING OF DATA SCIENCE
Type A questions directly test the candidates' ability to correctly and
precisely recollect concepts, principles, techniques, and generally accepted
practices in Data Science. The answers to TYPE A questions will reflect
candidates' awareness and comprehension of critical Data Science concepts
elements and issues as enshrined in the DASCA Body of Knowledge. There
is only one correct answer to TYPE A questions, candidates are scored only
if the correct option is selected.

TYPE B- ADVANCED UNDERSTANDING OF DATA SCIENCE

Type B questions test the candidates' understanding of Data Science at an
advanced level of Data Science techniques and practices. TYPE B Questions
would be fact-based with answer options being clear statements – either
clearly correct, or incorrect.

TYPE C- IMPLEMENTATION OF DATA SCIENCE TECHNOLOGIES

Type C questions directly test the candidates' ability to APPLY and DEPLOY
their awareness and understanding of the Data Science technologies in
real-life practice. There is only one correct answer to TYPE C questions,
candidates are scored only if the correct option is selected.

8
Examples
TYPE A - GENERAL UNDERSTANDING OF DATA SCIENCE
Question 1:
The first Fraud Management System was based on
a) CPP b) NPP c) MPP d) RPP
Correct Answer: c) MPP

Question 2:
HBase does not support which of the following?
a) Compaction b) MapReduce jobs c) Hashing d) Secondary indexes
Correct Answer: d) Secondary indexes

TYPE B - ADVANCED UNDERSTANDING OF DATA SCIENCE

Question 1:
What could be the purpose of an online retailer's analytics team using
'Collaborative filtering' algorithm?
a) Recommendation of the product b) Shelf space allocation
c) Shopper navigation control d) Pricing optimization
Correct Answer: (a) Recommendation of the product

Question 2:
An analyst has obtained data from the following sources. Identify the source where
Hive CANNOT be used to analyze the data.
a) Twitter data b) Web logs c) Call data records d) Oracle CRM tables
Correct Answer: d) Oracle CRM tables

TYPE C - APPLIED & PRACTICAL UNDERSTANDING OF DATA SCIENCE

Question 1:
Which of the following commands is usually the best for dropping database, along
with the tables in Hive?
a) DROP DATABASE my_database ALL b) DROP DATABASE my_database FALSE
c) DROP DATABASE my_database TRUE d) DROP DATABASE my_database CASCADE
Correct Answer: d) DROP DATABASE my_database CASCADE

Question 2:
What could be the purpose of an online retailer’s analytics team using ‘Collaborative
filtering’ algorithm?
a) Recommendation of the product b) Shelf space allocation
c) Shopper navigation control d) Pricing optimization
Correct Answer: a) Recommendation of the product

9
Exam-preparation Resources &
Exam Policies
All registered ABDA™ candidates receive print copies of the Big Data
Analyst Handbooks. These handbooks are prescribed for exam preparation.
DASCA practices stringent examination standards to ensure the highest
integrity of the exam content and fairness for all examinees during the
delivery of the examination. It is the responsibility of the candidate to
familiarize themselves with the policies and procedures before they appear
for the examination.

DASCA official exam-preparation

resources
ABDA™ candidates get a pair of Big Data Analyst handbooks exclusively
prepared in accordance with the DASCA knowledge framework. In addition
to serving as a base of learning and exam preparation, these handbooks
double up as useful reference resources for candidates even after they have
earned their ABDA™ credential. Big Data Analyst Handbook 1 contains 23
chapters and Big Data Analyst Handbook 2 contains 17 chapters.

The content in the two handbooks aims to develop in learners a strong

generic and platform-based understanding of the concepts, tools, and
technologies of handling, managing, processing, and visualizing large
volumes of streaming data.

In addition, DASCA
partners provide online
resources including
videos for supplemental
learning.

10
System Requirements
Below are the minimum system requirements to appear for the DASCA
exams:

System Essentials Requirements

Please note: Candidates need to ensure that to run the exam smoothly, their internet
speed must be at least 1 MBPS. In the event their exam interrupts and they cannot
complete it because of bandwidth reasons at their end, candidates can reschedule it for
another slot from their myDASCA dashboard after paying a nominal fee.

Should have admin rights on your laptop/computer if you are taking the exam
from your office premises.

11
Identification Policy
While scheduling the ABDA™ exam, you will be required to submit details of
two valid, nonexpired Government-issued identification documents. The IDs
must be valid and current (not expired) on the exam day. One of the IDs
must be a photo ID with your legal name and signature. Your legal name on
the ID must exactly match the first and last name on your
myDASCA account.

Both IDs must be issued by the country in which the candidate is testing. If
the candidate does not have a qualifying primary ID issued from the country
they are testing in, an International Travel Passport from their country of
citizenship is required, along with a secondary ID.

List of acceptable IDs -

Ÿ Government-issued driver's license
Ÿ Passport
Ÿ Military ID
Ÿ State/country ID card
Ÿ Employee/school ID

You will be required to present your ID on the screen to the remote proctor
on exam day. If there is any discrepancy in the ID presented or the ID does
not fulfill one or more requirements from above, the remote proctor has the
right to refuse entry into the exam zone on the platform.

It is also recommended that you ensure the exam room is well-lit and your
webcam has a good resolution to ensure a smooth verification process.

12
Scheduling, Rescheduling, and
Cancellation Policy

Exam Scheduling
Once you complete your registration, you have a period of 180 days to
study, prepare for and give your exam. It is the responsibility of the
candidate to schedule the exam in time to ensure they get access to
preferable exam windows. It is recommended you schedule your
examination at least 30 days before the expiry of 180 days period. Any
requests for exam scheduling within 20-30 days of the expiry of the 180
days validity period will not be accommodated. To schedule your exam after
the expiry of 180 days, you can do so after paying a nominal fee on your
myDASCA dashboard.

In the event you do not show up for your exam as scheduled, you will be
marked ‘No-show’. If you miss your scheduled examination due to an
emergency, please contact DASCA within 48-96 hours to report the matter.
Visit the policy section here to read more about Appeals.

Exam Rescheduling
To reschedule your exam, you must log in to your myDASCA dashboard 72
hours prior to your scheduled examination. Rescheduling in less than 72
hours prior to your scheduled exam will require you to pay USD 50 from
your myDASCA dashboard.

Cancellation Policy
If you wish to cancel your exam, you should log in to your myDASCA
dashboard 72 hours prior to your scheduled examination. To reschedule the
exam after voluntary cancellation, you can immediately reapply from your
myDASCA dashboard by paying a nominal fee of USD 50.

Examination Reappear Policy

In the event you fail your first attempt to pass the examination, you can
apply to reappear after your result is published on your myDASCA
dashboard. You will be required to pay a nominal fee of USD 50 and then
schedule the exam for a later date.

13
Recommendations
The fast-paced evolution of the industry is a key issue too; little written
content about data science stays relevant for too long. The following
resources and publications can help you stay up to date with the latest data
science developments:

Ÿ International Journal of Data Ÿ Intelligent Data Analysis

Science and Analytics
Ÿ Predictive Analytics World
Ÿ Big Data
Ÿ Towards Data Science
Ÿ Big Data Research
Ÿ Inside BIG DATA
Ÿ Journal of Big Data
Ÿ Data Science Central
Ÿ International Journal of
Business Intelligence and Data Ÿ Information Week
Mining Ÿ Gartner
Ÿ Computational Statistics & Ÿ Datafloq
Data Analysis
Ÿ Forrester
Ÿ Sigkdd Explorations
Ÿ Kdnuggets
Ÿ Artificial Intelligence
Ÿ Dataconomy
Ÿ Foundations and Trends® in
Machine Learning Ÿ TechCrunch

Ÿ Social Network Analysis and Ÿ CIO Magazine

Mining
Ÿ DataRobot
Ÿ Advances in Data Analysis and
Ÿ Forbes
Classification

14
Exam Conduct
All examinees must comply with DASCA’s policies and procedures to ensure
a fair and secure examination process. DASCA has a zero-tolerance policy
for any misconduct or adoption of unfair means in its ecosystem. All
decisions taken by the remote proctor during the exam session will be
final and binding including termination of the examination due to non-
compliance or any activity that is deemed suspicious or not in compliance
with the code of conduct. Examinees cannot appeal the final decision
regarding an exam policy violation.

It is recommended that you are at your desk atleast 30-50 minutes prior to
your exam start time. This gives you ample time to check your internet
connectivity, and system compatibility, give the mock exam and ensure you
have read through and familiarized yourself with all the terms, conditions,
and policies well in advance. We encourage you to review the guidelines
below to gain perspective and understanding of an examinee’s conduct
during the examination. If you have any specific questions,
please contact us to get more clarity before you appear for your
examination. No personal belongings are allowed in the exam room
including mobile phones, digital assistants, reading material including the
DASCA handbooks, tablets, e-readers, digital watches, and any other
electronic device except the computer/ laptop you will be appearing for the
exam on. You are only allowed to have a webcam and an external mouse
connected to your device.

No breaks are allowed during the examination. You should be visible at all
times on the exam screen. If you are partially visible on the exam screen at
any time during the exam, your exam may be terminated. Trying to relocate
during the examination is disallowed as well.

Make sure your browser tabs and applications are closed/ signed out
during the exam, especially if you are using a work laptop/ computer. Any
notification pop-ups of email and chat will lead to the immediate
termination of the exam session.

Exam Integrity
The examination and all connected materials are the intellectual property of
the Data Science Council of America. Examinees should not try to copy the
exam questions or take a screenshot or record during the examination
through any means. After the exam has been administered, the examinees
are prohibited to publish or share the examination content in any format.
Any such act of reproducing or distributing content or any material, that
violates the copyright laws, may invite stringent penal action. Any action, or
activity by the examinee including any misconduct, intentional or otherwise,
during or after the administration of the exam, will be deemed as a
violation of DASCA’s policies and procedures.

15
 www.dasca.org I Contact Us

©2024. Data Science Council of America. All Rights Reserved.

Data Science Council of America (DASCA) is an independent data science credentialing body that
DSEG0224

researches, designs, and builds platform-independent data science knowledge framework, standers,
and credentials. ABDA™, ABDE™, SBDA™, SBDE™, SDS™, PDS™, and EKF™ are the trademarks owned
by the Data Science Council of America. DASCA credentials, approaches, initiatives, and programs work
toward developing high-quality professionals to address squarely the challenging expectations of Data
Science stakeholders internationally.