Predictive analytics for data driven decision making : tools and techniques for solving real world problems / L. Ashok Kumar, R. Sujatha and B. Uma Maheswari.

Format:

Book

Author/Creator:

Kumar, L. Ashok, author.

Sujatha, R. (Computer science professor), author.

Maheswari, B. Uma, author.

Series:

Research Methodology and Data Analysis

Language:

English

Subjects (All):

Decision making--Statistical methods.

Decision making.

Management--Statistical methods.

Management.

Predictive analytics.

Physical Description:

1 online resource (430 pages)

Edition:

1st ed.

Place of Publication:

New York, New York : Nova Science Publishers, Incorporated, [2022]

Summary:

"Predictive analytics is an evolving field and has applications across all domains and sectors. This book will introduce to the reader the concept of predictive analytics and cover in detail the predictive analytic models, tools and techniques involved. The book will also cover the applications of predictive analytics in various domains including health care, banking, agriculture, retailing, sports and industries using smart grid and industrial drivers with real world scenarios. This book covers performance improvement and enhancement techniques with the aid of intelligent predictive analytical algorithms to predict future patterns. This would be a handy guide covering all steps from identification of the problem, preparing the data, model building and recommending solutions. Hence, the readers can experience the various types of performance improvement techniques and implement them in their specific domain"-- Provided by publisher.

Contents:

Intro

Contents

Preface

Acknowledgments

Chapter 1

Introduction to Predictive Analytics

Learning Outcomes

Abstract

1.1. Introduction

1.2. Predictive Analytics

1.3. Need for Predictive Analytics

1.3.1. Enhance Marketing Productivity

1.3.2. Obtain a Competitive Edge

1.3.3. Better Understand the Customers

1.3.4. Identify Attrition Points

1.3.5. Identifying New Revenue Sources

1.3.6. Detecting Fraudulent Activities

1.3.7. Optimizing Marketing Campaigns

1.3.8. Improving Operations

1.3.9. Reducing Risk

1.4. Working of Predictive Analytics

1.4.1. Understanding the Business Problem

1.4.2. Extract and Load Data

1.4.3. Pre-Process the Data

1.4.4. Create a Predictive Model

1.4.5. Model Evaluation

1.4.6. Deploy the Model

1.5. Big Data, Text Analytics and Predictive Analytics

1.5.1. Big Data

1.5.2. Text Analytics

1.5.3. Text Analytics Process Flow

1.5.4. The Relationship between Big Data, Text Analytics and Predictive Analytics

1.6. Applications of Predictive Analytics

1.6.1. Customer Relationship Management

1.6.2. Healthcare

1.6.3. Insurance

1.6.4. Pharmaceutical Industry

1.6.5. Manufacturing

1.6.6. Wind Farms

1.6.7. Stock Markets

1.7. Career in Predictive Analytics

1.7.1. Data Analytics Manager

1.7.1.1. Roles and Responsibilities

1.7.1.2. Requirements

1.7.2. Data Processing Analyst

1.7.2.1. Roles and Responsibilities

1.7.2.2. Requirements

1.7.3. Data Analyst

1.7.3.1. Roles and Responsibilities

1.7.3.2. Requirements

1.7.4. Risk Analyst

1.7.4.1. Roles and Responsibilities

1.7.4.2. Requirements

1.7.5. Data Scientist

1.7.5.1. Roles and Responsibilities

1.7.5.2. Requirements

1.7.6. Visual Business Intelligence Developer

1.7.6.1. Roles and Responsibilities

1.7.6.2. Requirements.

1.7.7. Data Analyst

1.7.7.1. Roles and Responsibilities

1.7.7.2. Requirements

1.7.8. Data Science Consultant

1.7.8.1. Roles and Responsibilities

1.7.8.2. Requirements

1.7.9. Machine Learning Engineer

1.7.9.1. Roles and Responsibilities

1.7.9.2. Requirements

1.7.10. Decision Scientist

1.7.10.1. Roles and Responsibilities

1.7.10.2. Requirements

1.7.11. Artificial Intelligence Engineer

1.7.11.1. Roles and Responsibilities

1.7.11.2. Requirements

1.7.12. Business Intelligence Engineer

1.7.12.1. Roles and Responsibilities

1.7.12.2. Requirements

1.7.13. Machine Learning Research Engineer

1.7.13.1. Roles and Responsibilities

1.7.13.2. Requirements

1.7.14. Business Analyst (Visualization)

1.7.14.1. Roles and Responsibilities

1.7.14.2. Requirements

1.7.15. Data Engineer

1.7.15.1. Roles and Responsibilities

1.7.15.2. Requirements

1.7.16. Product Analyst

1.7.16.1. Roles and Responsibilities

1.7.17. Data Engineer

1.7.17.1. Roles and Responsibilities

1.7.17.2. Requirements

1.7.18. Business Reporting Analyst

1.7.18.1. Roles and Responsibilities

1.7.18.2. Requirements

1.7.19. Data Processing Analyst

1.7.19.1. Roles and Responsibilities

1.7.19.2. Requirements

1.7.20. Data Wrangler

1.7.20.1. Roles and Responsibilities

1.7.20.2. Requirements

1.7.21. Engagement Manager

1.7.21.1. Roles and Responsibilities

1.7.21.2. Requirements

Conclusion

References

Chapter 2

Predictive Analytics Modelling

2.1. Introduction

2.2. Predictive Modelling Process

2.2.1. Step 1: Feasibility Analysis

2.2.2. Step 2: Data Collection

2.2.3. Step 3: Data Preparation

2.2.4. Step 4: Data Splitting

2.2.5. Step 5: Model Building

2.2.6. Step 6: Deploying the Model.

2.2.7. Step 7: Monitoring of Predictive Models

2.3. Types of Predictive Modelling

2.3.1. Classification Model

2.3.2. Clustering Model

2.3.3. Forecast Model

2.3.4. Outliers Model

2.3.5. Time Series Model

2.4. The Generic Predictive Algorithms

2.4.1. Association Rule Mining

2.4.2. K-Means Clustering

2.4.3. Hierarchical Clustering

2.4.4. Linear Regression

2.4.5. Logistic Regression

2.4.6. Linear Discriminant Analysis

2.4.7. Naïve Bayes Algorithm

2.4.8. K-Nearest Neighbours

2.4.9. Random Forest

2.4.10. Support Vector Machines

2.4.11. Time Series Models

2.4.12. Artificial Neural Networks

2.4.13. Deep Learning Algorithms

2.4.14. Ensemble Methods

2.4.14.1. Bias Variance Tradeoff

2.4.14.2. Bagging

2.4.14.3. Boosting

2.5. How to Choose Feasible Predictive Modelling?

2.5.1. Types of Predictive Models &amp

Evaluation Metrics

2.5.2. Cross Validation

2.5.2.1. K-Fold Cross Validation

2.5.2.2. Stratified Cross-Validation

2.5.2.3. Leave One out Cross Validation

2.5.3. Metrics for Regression Algorithms

2.5.4. Metrics for Classification Algorithms

2.5.4.1. Confusion Matrix

2.5.4.2. ROC Curve (Receiver Operating Characteristic)

2.5.4.3. Area Under the Curve (AUC)

2.5.4.4. Gini Coefficient

2.6. Applications of Predictive Modelling

Chapter 3

Predictive Analytics Tools and Techniques

3.1. Introduction

3.2. Statistical Prediction Software

3.2.1. Statistical Prediction Software - SPSS Statistics

3.2.2. Statistical Prediction Software - SAS/STAT

3.2.2.1. Advantages

3.2.3. Statistical Prediction Software - STATA, Minitab

3.2.3.1. Stata

3.2.3.2. MiniTab

3.3. Predictive Analytic Software

3.3.1. Uses of SAP

3.3.2. Qlik Sense Predictive Analytic Software.

3.3.3. RapidMiner Predictive Analytic Software

3.4. Predictive Analytics Tools for Excel

3.5. Other Analytical Tools

Chapter 4

Big Data and Internet of Things

4.1. Introduction

4.2. How Are Internet of Things and Big Data Interrelated?

4.3. What does Real-Time Data Processing mean for IoT Applications?

4.4. Types of IoT Analytics

4.4.1. Descriptive Analytics on IoT Data

4.4.2. Diagnostic Analytics on IoT Data

4.4.3. Predictive Analytics on IoT Data

4.4.4. Prescriptive Analytics on IoT Data

4.5. Use Cases of IoT Analytics

4.5.1. Optimizing Marketing and Sales

4.5.2. Real-Time Data Analysis for Manufacturing

4.5.3. Monitoring of Healthcare Devices and Patients

4.5.4. Predictive Maintenance

4.6. IoT Analytics Challenges

4.6.1. Too Much Data

4.6.2. Security

4.6.3. Misbehaving Devices

4.7. Data Infrastructure for IoT

4.7.1. IoT Analytics Storage

4.7.1.1. Data Storage Technologies

4.7.2. Stream Processing Software

4.7.2.1. Streaming Data

4.7.2.2. Analyzing Data

4.7.2.3. Distributed Analytics

4.7.2.4. Real-Time Analytics

4.7.2.5. Edge Analytics

4.7.2.6. Machine Learning

4.7.3. Analytics Engine

4.7.3.1. AWS IoT Analytics

4.7.3.2. Azure IoT Analytics

4.8. IoT and Big Data Applications

4.8.1. Experfy

4.8.2. Signalframe

4.8.3. The Climate Corporation

4.8.4. Aker Technologies

4.8.5. Uplift Data Partners

4.8.6. Cisco Jasper

4.8.7. Altizon

4.9. Related Work Done

Chapter 5

Predictive Analytics in Smart Grid

5.1. Introduction

5.1.1. Smart Metering Has the Following Features

5.2. Applications of Smart Metering

5.2.1. State Estimation of Power Distribution Networks.

5.2.2. Load Analysis, Modelling and Forecasting

5.2.2.1. Ancillary Services such as Frequency Controlled Reserve, Voltage and Reactive Power Control

5.2.2.2. End-Use Energy Management

5.2.3. Energy Saving

5.2.4. Preventive Maintenance and Analysis of Failures

5.2.5. Safety, Security, Telemedicine, Social Alarm Services

5.2.5.1. Safety

5.2.5.2. Security

5.2.5.3. Telemedicine

5.2.5.4. Social Alarms

5.3. Meter Management

5.4. Smart Metering System Benefits

5.4.1. Smart Metering Value Proposition for the utilities

5.4.2. Consumer Value Proposition for Smart Metering

5.4.3. Value Proposition for Smart Metering for Governments

5.5. Smart Meter Technologies

5.6. Types of Smart Metering

5.6.1. GISM Single-Phase (230 V)

5.6.2. GIST Three-Phase (3*230/400 V) Inverter

5.6.3. GISS Meter Installed for Heavy Consumers

5.7. Smart Grid

5.7.1. Definition

5.7.2. Structure of Smart Grids

5.7.3. Smart Grid Technologies

5.7.4. Smart Grid Events and Achievements - An Overview

5.7.5. Smart Grid Predominant Components

5.7.5.1. Demand Response

5.7.5.2. Reliability of Demand Response

5.7.6. Energy Storage Technologies

5.7.7. IoT in the Generation Level

5.7.8. Communication Techniques for Smart Grid

5.7.8.1. ZigBee

5.7.8.2. Wireless Mesh

5.7.8.3. GSM

5.7.8.4. Cellular Network Communication

5.7.8.5. Data Mining Techniques for Smart Grid

5.7.8.6. Expert System Techniques

5.7.8.7. The Regression Technique

5.7.8.8. Support Vector Machines

5.7.8.9. The Time Series Technique

5.7.8.10. Fuzzy Logic Techniques

5.7.9. Evolution of Smart Grid

5.7.9.1. Role of Electricity Market and Importance of Their Rules and Policies

5.7.10. Applications of Smart Grid

5.7.11. Smart Grid Investment and Operating Cost Estimation.

5.7.12. Smart Grid Objectives towards Installation At 2050.

Notes:

Includes bibliographical references and index.

Description based on print version record.

ISBN:

1-68507-770-6