ORA DMA PRELIMS Flashcards
Not really a flashcard
Industrial Evolution Stages:
First: ________
Second: _____
Third: _______
Fourth: ______
Industrial Evolution Stages:
First: Mechanization, Steam Engineering
Second: Assembly Line, Mass Production, Electricity
Third: Computer and Automation
Fourth: Cyberphysical Systems
Rank each types of Analytics (A) from least complex to most complex
Diagnostic A
Predictive A
Descriptive A
Prescriptive A
Descriptive Analytics
Diagnostic Analytics
Predictive Analytics
Prescriptive Analytics
broad field of computer science focused on creating machines capable of performing tasks that typically require human intelligence
Artificial Intelligence
a subset of Al that involves the development of algorithms that can LEARN and make predictions or decisions BASED ON DATE
machine learning (ML)
a subset of ML that uses layered NEURAL NETWORKS to analyze various factors of data; it is inspired by the structure and function of the brain
Deep Learning
(DL)
(more humanize)
Machine learning is when “Machines” learn relationships between a ____________ (Prediction variables) and a ____ (Output) from Historical Datasets
— Set of descriptive features (e.g. Occupation, Age, Loan-Salary Ratio)
— Target Variable
(Default? or Repaid?)
Feature ____ and Feature _____ are essential Processes in Machine Learning
— Feature design
— Feature Selection
Read only??
What are 6 Variety of techniques and approaches in Machine learning?
– GBM
– Naive Bayes
– Decision Tree
– Random Forests
– Support Vector machines
– kNN
– Deep Learning (Transformers, GANs)
4 Paradigms of Learning in ML
– Unsupervised Learning
explores unlabeled data for patterns
– Supervised Learning
uses labeled data for training (inputs are known)
– Semi Supervised Learning
Combination
– Reinforcement Learning
trains agents through trial and error and rewards
Allows Organizations to make data and technology choices, grounded in business objectives, to maximize value from data
Data Strategy
[Definition from google]
_____ Creates new content like text, images, audio, or video, by learning patterns from existing data and then generating new data instances.
Generative Ai
Hindrances of Companies in Implementing their Data strategy
Lack of Understanding
Lack of Resources
Absence of a Data Strategy
Lack of Internal Support
Lack of Data Science Talent
Absence of a Data
Governance Framework
Lack of Data
____ is about minimizing drawbacks and unnecessary risks. Activities include ensuring data security, privacy, quality, compliance, and governance, among others.
Data Defense
____ on the other hand, concentrates on supporting particular business objectives such as increasing revenue, profitability, market share, & even improving customer satisfaction. Regarding core activities, it involves predictive analytics, modeling, & simulations
Data Offense
Why Visualize data
– Draw Attention
– Answer Ques
– Compare values
– Show Changes
– View a value
– Illustrate patterns
Process to examine data set before performing formal modeling
EDA
Exploratory Data Analysis
Read only
The Importance of Context
Essential background information?
Who is the audience or decision-maker?
Do they have biases? Supportive or resistant to message?
Any available data to strengthen the case?
* What are the risks that could weaken the case?
What would a successful outcome look like?
. Can you give to your audience what they need to know in 3-mins? Or a single sentence?
Who is the audience or decision-maker?
Do they have biases? Supportive or resistant to message?
Any available data to strengthen the case?
* What are the risks that could weaken the case?
What would a successful outcome look like?
. Can you give to your audience what they need to know in 3-mins? Or a single sentence?
Effective Visuals
Focuses:
Academic == 3Comprehension, 2 appeal, 2 retention
Marketing == 3Retention and 3Appeal, 1 comprehension
Editorial == 3Appeal, 2Comprehension, 1 retention
ok
5 effective data visualization
– not in order
– see what stands out
– see only few things
– see meaning
– rely on conventions and metaphors
k
Gestalt Principles of Visual Perception
Proximity (as group)
Similarity
Enclosure (within a shape)
Connection
k
Data stories combine____ with ____ flow. It can breach barriers between people and data, engaging the former and delving deeper into the latter
visualisations
narrative
3 essential elements of Data stories
Data (Foundation of story)
Narrative (Storyline to communicate insights)
Visuals (To communicate story effectively)
Dos and Donts of Storytelling
DONTS
Don’t cherry-pick data.
Don’t offer single facts without value.
Don’t make the “Aha!” moment difficult.
Don’t overcomplicate design.
Don’t show a lack of confidence.
DOS
Do ensure data is complete and reliable.
Do provide key takeaways.
Do maintain consistency.
Do explain data stories in stages.
Do present authority.
What makes a great dashboard
ACES
Accurate (Quality Data)
Clear (Fonts, Colors, Context, Layout) SPEED OF INSIGHTS
Empoweiring (Help make decision, Useful)
Succint (Brief and relevant)
4 types of EDA
Multivariate Graphi/NonGraphi
Univariate Graphi/NonGraphi
Steps in EDA
Data Collection:
Data Cleaning:
Data Exploration and Visualization:
Feature Engineering: Enhance dataset for modeling and analysis.
Hypothesis Testing: Validate assumptions.
Communication & Documentation: Share findings and document the process.
