Elective 3: 1-4 Report and Quiz 2

Bagging

Involves building multiple decision trees from resampled data and combining their predictions

Input Layer

Hidden Layer

Output Layer

The component of a neural network

True

True or False: In a Naive Bayes algorithm, when an attribute value in the testing record has no example in the training set, then the entire posterior probability is zero

Nearest Neighbor

It is a simple algorithm widely used to cluster data by assigning an item to a cluster by determining what other items are most similar to it

Naïve Bayes

You have a dataset of emails labeled as spam and non-spam, and you want to classify new incoming emails

Conditionally Independent

The consequence between a node and its predecessors while creating Bayesian network

Clustering

Is not a supervised type of machine learning

Answering problematic query

Bayes can be used for this

Not an advantage of Ensemble Modeling

They can be sensitive to the quality and diversity of the data and the base models, as they depend on the assumptions and limitations of the individual models

Deep Learning

This revolves around the use of deep neural networks, characterized by multiple interconnected layers, to automatically learn and represent intricate patterns and features from raw data

Decision Tree

A specific type of flow chart used to visualize the decision-making process by mapping out different courses of action as well as their potential

Support Vectors

These are the points that are closest to the hyperplane. A separating line will be defined with the help of these data points

Boosting

Main goal is to create predictive model by combining multiple simple models

Bayes Theorem

A mathematical formula for determining conditional probabilities

False

True or False: In SVM, the best hyperplane is that the plane that has the minimum distance from both the classes

Stacking

An ensemble technique that combines predictions from a diverse group of strong machine learning models. This intermediate meta classifier evaluates how accurate the primary classifiers have become and serves as the basis for adjustments and corrections

Ensemble Modeling

Is a machine learning technique that combines several base models in order to produce one optimal predictive model

Human Brain

The neural network is inspired by this

Complete description of the domain

Bayesian network provide

Management

Is a process by which organizational goals are achieved by using resources

Decision Making

Selecting the best solution from two or more alternatives

Markets

Consumer Demand

Technology

Societal

Business Environment Factors

Figurehead

Leader

Liaison

The Nature of Managers’ Work Mintzberg's 10 Managerial Roles: Interpersonal

Monitor

Disseminator

Spokesperson

The Nature of Managers’ Work Mintzberg's 10 Managerial Roles: Informational

Entrepreneur

Disturbance handler

Resource allocator

Negotiator

The Nature of Managers’ Work Mintzberg's 10 Managerial Roles: Decisional

Decision Support System

Interactive computer-based systems, which help decision makers utilize data and models to solve unstructured problems

Gorry and Scott-Morton, 1971

Created DSS

Business Intelligence

Helps transform data, to information (and knowledge), to decisions, and finally to action

Business Intelligence

Is an umbrella term that combines architectures, tools, databases, analytical tools, applications, and methodologies

Gartner Group

The term BI was coined in the mid-1990s

Data Warehouse

Business Analytics

Business Performance Management

User Interface

Architecture of BI

Decision Making

Is a process of choosing among two or more alternative courses of action for the purpose of attaining one or more goals

Managerial Decision Making

Is synonymous with the entire management process. Consider the important managerial function of planning

Intelligence

Design

Choice

Implementation

Simon’s Process

Intelligence Phase

Begins with the identification of organizational goals and objectives related to an issue of concern and determination of whether they are being met

Problem Classification

Problem Decomposition

Problem Ownership

Intelligence Phase

Design Phase

Involves finding or developing and analyzing possible courses of action. These include understanding the problem and testing solutions for feasibility. A model of the decision-making problem is constructed, tested, and validated

Model

Is a simplified representation or abstraction of reality

Choice Phase

Is the one in which the actual decision and the commitment to follow a certain course of action are made

Implementation Phase

Involves putting a recommended solution to work, not necessarily implementing a computer system

Operational Control

Management Control

Strategic Planning

Three Types of Control

Structured

Semistructured

Unstructured

Type of Decision

Structured Processes

These are routine problems with established standard solution methods

Semistructured Processes

These fall in between structured and unstructured problems, containing elements of both

Unstructured Processes

These are complex problems without clear-cut solution methods

Operational Control

Concentrates on the efficient and effective execution of specific tasks

Management Control

Focuses on acquiring and efficiently using resources to achieve organizational goals

Strategic Planning

Involves setting long-term goals and policies for allocating resources

Decision Support Matrix

Combines Anthony's (1965) and Simon's (1977) categorizations into a nine-cell matrix

Solving Tough Problems

For Everyone

Solo or Team

Connected Decisions

Decision Roadmap

Custom-Made

User-Friendly

Quality Over Speed

Your Decision Partner

DIY or Teamwork

Try and Test

Handles All Data

Flexible for Everyone

Characteristics and Capabilities of DSS

Data Management

Model Management

User Interface

Knowledge Management

Components of a DSS

Data Management

This part handles all the information you need

Model Management

It uses models to help you make decisions

User Interface

This is how you talk to DSS, usually with visuals and simple language

Knowledge Management

It helps you store and use what you know

DSS Database

Database Management System

Data Directory

Query Facility

Data Management Subsystem

DSS Database

This is like a digital storage room where we keep all the important information we need for making decisions. Think of it as the warehouse of data

Database Management System

It makes sure data is organized, safe, and easy to access. It's like a librarian who keeps all the books in order so you can find them when needed

Data Directory

This is like a map that shows us where everything is stored in our storage room. It's handy when we need to find specific information quickly

Query Facility

Think of this as a search tool. It helps us ask questions to find the exact data we're looking for, just like typing a question in Google to find information on the internet

Model Base

MBMS (Model Base Management System)

Modeling Language

Model Directory Model Execution, Integration, and Command Processor

Model Management Subsystem Elements

OLAP (Online Analytical Processing)

Software can be employed for data analysis and working with models

Improved Decision-Making

Flexibility

Efficiency

Integration

Benefits of Model Management Subsystem

Explicit Knowledge

Tacit Knowledge

Types of Knowledge

Explicit Knowledge

Is knowledge that can be codified, documented, and easily transferred in the form of data, facts, or information. It is formal, structured, and often written down

Tacit Knowledge

Is the type of knowledge that is not easily expressed in words or formalized. It is highly personal, context-specific, and often rooted in personal experiences, insights, and intuitions

Informed Decision-Making

Knowledge Preservation

Innovation

Collaboration

Benefits of the Knowledge-Based Management Subsystem

Analytics

The process of analyzing data to extract valuable insights, is a crucial aspect of modern business and decision-making

Descriptive

Diagnostic

Predictive

Prescriptive

Types of Analytics

Descriptive

Describes historical data to provide insights into what has happened

Diagnostic

Digs deeper into data to understand why certain events occurred

Predictive

Uses historical data and statistical algorithms to make predictions about future events

Prescriptive

Recommends actions to optimize outcomes based on predictive models

NumPy

Jupyter Notebooks

SQLAlchemy

Statsmodels

TensorFlow and PyTorch

Scikit-Learn

Matplotlib and Seaborn

pandas

Key Python Libraries for Analytics

NumPy

A fundamental library for numerical computations, providing support for multi -dimensional arrays and matrices

Jupyter Notebooks

An interactive environment for code development, data exploration, and documentation, fostering collaboration.

SQLAlchemy

Enables interaction with databases, making it easier to query and analyze data stored in various formats

Statsmodels

A library for estimating and interpreting statistical models, ideal for regression and hypothesis testing

TensorFlow and PyTorch

Deep learning frameworks for implementing neural networks and advanced machine learning algorithms

Scikit-Learn

A machine learning library with a comprehensive collection of tools for building predictive models and performing data analysis

Matplotlib and Seaborn

Powerful libraries for data visualization, facilitating the creation of insightful plots and charts

pandas

An essential data manipulation and analysis library that simplifies data handling with DataFrame structures

Predictive Analytics Process

Analytics process that involves several key steps

Problem Definition

Data Collection

Data Preprocessing

Model Development

Model Evaluation

Model Deployment

Monitoring and Maintenance

Predictive Analytics Process

Healthcare

Retail

Finance

Marketing

Real-World Applications of Analytics

Artificial Intelligence

The study of human thought processes and duplicating them in machines

Reactive AI

Limited memory AI

Theory-of-mind AI

Self-aware AI

4 Types of AI

Reactive AI

Uses algorithms to optimize outputs based on a set of inputs

Limited memory AI

Can adapt to past experience or update itself based on new observations or data

Theory-of-mind AI

Are fully-adaptive and have an extensive ability to learn and retain past experiences

Self-aware AI

As the name suggests, become sentient and aware of their own existence

Machine Learning

Deep Learning

Neural Networks

Cognitive Computing

Basic Concepts of Artificial Intelligence

Machine Learning

The idea that systems can learn from data, identify patterns and make decisions with minimal human intervention

Deep Learning

Rely on neural networks for cascading data processing. The term “deep” refers to the number of layers hidden in neural networks

Neural Networks

Belong to the family of Machine Learning algorithms and are inspired by the functioning of neurons in the human brain. They are based on the fact that, given some parameters, there is a way to combine them to produce a specific result

Cognitive Computing

It consists of systems that take on tasks or make specific decisions as assistants or substitutes for people, as they can handle ambiguity and vagueness, and have a high degree of autonomy within their area of knowledge

Supervised Learning

Unsupervised Learning

Semi-supervised Learning

Reinforcement Learning

4 Types of Machine Learning

Supervised Learning

It learns by receiving a lot of labeled training data that allows generalizing in new cases

Unsupervised Learning

It learns by observing, understanding, and abstracting patterns directly from the information. It is very similar to how we humans think

Semi-supervised Learning

It learns based on both labeled and unlabeled training data, with the proportion of unlabeled data typically being larger