PeopleCert Data Science Foundation Flashcards

These vocabulary flashcards cover key terminology from the PeopleCert Data Science Foundation syllabus, including Big Data, Programming, Data Governance, Statistics, Machine Learning, and Artificial Intelligence.

Data Science

A cross-disciplinary field that combines the scientific method, math and statistics, specialized programming, advanced analytics, AI, and storytelling to uncover and explain business insights buried in data.

Big Data

A 21st-century phenomenon characterized by the exponential growth of business data and the challenges of holistic collection, storage, management, and analysis.

Volume

One of the 5 Vs of Big Data referring to the size of data sets that need to be analyzed and processed, such as all credit card transactions in Europe in a day.

Velocity

One of the 5 Vs of Big Data referring to the speed with which data is generated from sources like machines, social media, and mobile phones.

Variety

One of the 5 Vs of Big Data referring to the different types of data, including structured, semi-structured, and unstructured data like CCTV audio and video files.

Veracity

One of the 5 Vs of Big Data referring to the quality, trustworthiness, and authenticity of the data being analyzed.

Value

One of the 5 Vs of Big Data referring to the insights gained from data that can be turned into useful information to improve profit or operations.

Online Transaction Processing (OLTP)

A system that captures, stores, and processes data from transactions in real-time within operational applications.

Online Analytical Processing (OLAP)

A system that uses complex queries to analyze aggregated historical data from OLTP systems, typically seen in a data warehouse environment.

Extract, Transform, Load (ETL)

The process of ingesting data from one or more OLTP databases into OLAP systems by copying it into a destination system that represents the data differently.

MapReduce

A programming model introduced by Google in 2004 for simplified data processing on large scale clusters.

Hadoop

An open-source ecosystem (including Hive, Hbase, and Pig) that started in 2006 for decentralized storage and processing, with Version 2.0 released in 2012.

Data Lake

A repository used to store raw, semi-structured, or unstructured data in its original form until it is needed.

Data Swamp

A Data Lake that has become difficult to navigate or use because data was saved without proper structure, information, or value.

Data Analytics

A discipline focused on extracting insights from data comprising processes, tools, and techniques for collection, organization, and storage.

Descriptive Analytics

A type of analytics that asks "What has happened and what is happening right now?" using historical and current data to identify trends.

Diagnostic Analytics

A type of analytics that asks "Why is it happening?" to discover the factors or reasons for past performance.

Predictive Analytics

Advanced analytics that uses statistical modeling and machine learning to ask "What is likely to happen in the future?"

Prescriptive Analytics

Advanced analytics that uses testing and algorithms to recommend specific solutions by asking "What do we need to do?"

Digital Transformation

A company-wide effort involving digital strategy, customer journey mapping, enterprise architecture, and a transformation roadmap.

CRISP-DM

The Cross-Industry Standard Process for Data Mining, consisting of six phases: Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment.

Nominal Scale

A scale used to label variables that have no quantitative values or natural order.

Ordinal Scale

A scale used to label variables with a naturally occurring order but no quantifiable difference between values.

Interval Scale

A scale used for variables with a natural order and quantifiable difference but no "true zero," such as Celsius temperature.

Ratio Scale

A scale for variables with a natural order, quantifiable difference, and a "true zero" value.

Quantitative Analytics

Analysis of numerical data that can be counted or measured to confirm or test theories.

Qualitative Analytics

Analysis of descriptive data to understand concepts, thoughts, or experiences through rich, in-depth insights.

SAS (Statistical Analysis System)

A proprietary, closed-source suite of tools designed for statistical operations and modeling used primarily in large industries.

Apache Spark

A distributed computing framework designed for high-speed in-memory batch and stream processing of large-scale data.

D3.js

A JavaScript library used for creating interactive, animated data visualizations in web browsers.

MATLAB

A multi-paradigm numerical computing environment used for mathematical information, neural networks, and deep learning algorithms.

Matplotlib

A popular plotting and visualization library for Python used to generate complex graphs with simple code.

ggplot2

An advanced data visualization package for the R programming language that is part of the tidyverse.

TensorFlow

An open-source toolkit developed by Google Brain used as a standard for advanced machine learning and deep learning.

Jupyter Notebooks

An open-source web application used for writing live code, visualizations, and storytelling across multiple languages like Julia, Python, and R.

Software

The part of a computer system consisting of encoded information or computer instructions, including programs and libraries.

Algorithm

A self-contained, step-by-step procedure or formula for solving a problem or performing a well-defined task.

Graphics Processing Unit (GPU)

Hardware that streamlines processes with faster compute time for parallel processing tasks like image recognition and chatbots.

Machine Language

The "native" language of a computer, consisting of binary ($1$s and $0$s) or hexadecimal instructions executed directly by the CPU.

Compiled Language

A programming language converted directly into machine code for efficiency, requiring a "build" step (e.g., C++, Rust, Go).

Interpreted Language

A language where the source code is read and executed line-by-line by a separate program called an interpreter (e.g., Python, Ruby).

Python

An interpreted, high-level, general-purpose programming language released in 1991 by Guido van Rossum.

Variable

A reserved memory location used to store values, identified by a name that refers to those values.

Modulus Operator ($\%$)

An arithmetic operator in Python that returns the remainder of a division (e.g., $x \% y$).

Floor Division ($//$)

An arithmetic operator in Python that performs division and returns the largest possible integer result.

range() Function

A Python function that yields a sequence of numbers, accepting start, stop, and step parameters.

Data Mining

Also known as Exploratory Data Analysis (EDA), it is the systematic process of identifying hidden patterns and information in a dataset.

Database Management System (DBMS)

Software that allows users to interact with one or more databases and provides functions for entry, storage, and retrieval.

Relational Database (RDBMS)

A digital database based on the relational model proposed by E. F. Codd in 1970, where data is organized into tables with columns and rows.

Structured Query Language (SQL)

The standard ANSI/ISO language for managing and manipulating data within relational databases.

NoSQL

A non-relational database category designed for faster speed and processing of unstructured or semi-structured data at scale.

Self-driving Database

A cloud-based database that uses machine learning to automatically upgrade, patch, and tune itself while running.

Data Governance

A system defining authority and control over data assets, encompassing people, processes, and technologies.

Data Stewardship

A functional role in data management responsible for ensuring that data policies and standards are turned into practice.

Data Quality

A measure of data condition based on accuracy, completeness, consistency, reliability, and timeliness.

Master Data Management (MDM)

A discipline to ensure the uniformity, accuracy, and accountability of an enterprise's official shared master data assets.

General Data Protection Regulation (GDPR)

A European Union law enacted on May 25, 2018, providing individuals control over their personal data.

Personally Identifiable Information (PII)

Any data relating to an identified or identifiable natural person, such as name, age, or IP address.

Sensitive Personal Data

PII revealing racial origin, political opinions, health data, genetic data, or sexual orientation.

Data Protection Officer (DPO)

A role responsible for informing and advising organizations on GDPR compliance and serving as a contact point for supervisory authorities.

Right to be Forgotten

The right of a data subject to request the erasure of their personal data from a controller.

Privacy by Design

A GDPR principle requiring controllers to implement appropriate technical measures, like pseudonymization, to protect data.

Anonymization

The process of eliminating PII so that data subjects can no longer be identified; the resulting data is no longer considered personal data.

Pseudonymization

Replacing PII with non-identifying keys; the data is still considered personal data under GDPR because it can be reversed with the key.

Conflict of Interest

A situation that has the potential to prevent impartiality or create bias due to a clash between self-interest and professional interest.

Data Integrity

A measure of data quality referring to the consistency, accuracy, and correctness of data stored in a database.

Data Warehouse (DWH)

A central repository that extracts data from operational systems and external sources for analysis and reporting.

Business Intelligence (BI)

A continuous process that turns data into actionable business insights to improve organizational performance.

Data-Ink Ratio

A visualization principle advocating for the removal of extraneous elements to ensure the ink used represents actual data information.

Statistics

The science concerns with the collection, organization, analysis, interpretation, and presentation of data.

Population

In statistics, a universe or set of similar items which is of interest for an experiment.

Sample

A set of individuals or objects selected from a statistical population by a defined procedure.

Arithmetic Mean

A measure of central tendency calculated as the sum of all numbers divided by the count of the numbers.

Median

The middle measurement in an ordered set of data.

Mode

The most frequently occurring measurement in a set of data.

Standard Deviation ($\sigma$)

A measure of variability that represents the average distance of measurements from the mean.

Variance ($\sigma^2$)

The squared average distance of data points from the mean value.

Probability Theory

The branch of mathematics that measures how likely an event is to occur, fundamental to the reliability of statistical conclusions.

Sample Space

The set of all possible outcomes associated with a random experiment.

Intersection ($\cap$)

The collection of all outcomes that are elements of both sets A and B, corresponding to the word "and."

Union ($\cup$)

The collection of all outcomes that are elements of either set A or B, corresponding to the word "or."

Conditional Probability

The probability of one event ($A$) occurring given that another event ($B$) has already occurred, denoted as $P(A|B)$.

Histogram

A bar graph used to plot a frequency distribution of continuous data that has been discretized.

Normal Distribution

Also called the Gaussian distribution, it is a density curve characterized by mean ($\mu$) and standard deviation ($\sigma$) where data clusters around the center.

Machine Learning (ML)

A subset of AI that provides systems the ability to automatically learn and improve from experience without being explicitly programmed.

Supervised Learning

Algorithms that learn from labeled training data to predict future events or classify new entries.

Unsupervised Learning

Algorithms used to find undetected patterns or clusters in datasets that have no pre-existing labels or human supervision.

Reinforcement Learning

Algorithms that learn the ideal behavior within a context by producing actions and receiving simple reward feedback signals.

Classification

A supervised learning task concerned with building models that separate data into distinct, pre-labeled classes.

Regression

A supervised learning task focused on predicting a continuous outcome variable ($y$) based on predictor variables ($x$).

Linear Regression Equation

The mathematical formula $y = a + b \times x + e$, where $a$ is the intercept and $b$ is the coefficient.

Anomaly Detection

The identification of rare items or events (outliers) that differ significantly from the majority of the data.

ML Pipeline

An automated workflow consisting of a sequence of components used to manipulate and send data through computational stages.

Model Deployment

The method of integrating a trained machine learning model into a production environment to make practical business decisions.

Artificial Intelligence (AI)

The science and engineering of making intelligent machines or computer programs capable of tasks usually requiring human intelligence.

Computer Vision

A subset of AI that deals with making computers visually enabled so they can analyze and understand digital images.

Convolutional Neural Network (CNN)

A deep learning algorithm that assigns learnable weights and biases to various aspects of an image to differentiate objects.

Natural Language Processing (NLP)

A subfield of AI dealing with how computers process and analyze large amounts of human language data to understand meaning.

Sentiment Analysis

The process of interpreting and classifying emotions within text data to identify customer sentiment (positive, negative, or neutral).

Inference

In machine learning, the process of using a trained algorithm to make a prediction on new data.