Business Analytics Syllabus @ Vigor Council

 

Business Analytics Syllabus

 

Learning Objectives

n  Familiarize students with basics of predictive and prescriptive analytics in order to solve some business problems using different types of data

n  Students should be able to solve business problems, analyze datasets using various relevant statistical software packages, and interpret and effectively communicate the results

Learning Outcomes

n  Understand fundamental concepts of machine learning

n  Build basic models Statistical Softwares

n  Interpret results

n  Compare results of different models to select the best fit

n  Drive business decisions using model output

Unit 1

1.       Introduction to Business Analytics and Prescriptive Analytics

1.1.    Introduction to Business Analytics

1.2.    Role of Analytics for Data Driven Decision Making

1.3.    Types of Business Analytics

1.3.1. Descriptive Analytics

1.3.2. Predictive Analytics

1.3.3. Prescriptive Analytics

1.4.    Introduction to Big Data Analytics

1.4.1. Understanding 5Vs

1.4.2. Key components of Big Data Analytics

1.4.3. Application areas of Big Data Analytic

1.5.    Web and Social Media Analytics

1.6.    Overview of Machine Learning Algorithms

1.7.    Introduction to relevant statistical software packages and carrying out descriptive analysis through it

Unit 2

2.       Predictive Analytics 1

2.1.    Simple Linear Regression

2.1.1. Estimation of Parameters

2.1.2. Validation of simple linear regression model

2.1.3. Coefficient of determination

2.1.4. Significant Tests

2.1.5. Residual Analysis

2.1.6. Confident and Predication Intervals

2.2.    Multiple Linear Regression

2.2.1. Interpretation of Partial regression coefficients

2.2.2. Working with categorical variables

2.2.3. Multi-collinearity and VIF

2.2.4. Outlier Analysis

2.2.5. Auto-correlation

2.2.6. Transformation of variables

2.2.7. Variable Selection in Regression Model Building

Unit 3

3.       Predictive Analytics 2

3.1.    Logistic and Multinomial Regression

3.1.1. Logistic Function

3.1.2. Estimation of probability using logistic regression

3.1.3. Omnibus Test

3.1.4. Wald Test

3.1.5. Hosmer Lemshow Test

3.1.6. Pseudo R Square

3.2.    Model Performance

3.2.1. Classification Table

3.2.1.1.              Sensitivity

3.2.1.2.              Specificity

3.2.1.3.              Accuracy Paradox

3.2.1.4.              Precision

3.2.1.5.              F Score

3.2.2. Gini Coefficient

3.2.3. ROC

3.2.4. AUC

3.2.5. Model for determining the optimal cutoff probability

Unit 4

4.       Machine Learning Models

4.1.    Decision Trees

4.1.1. Introduction

4.1.2. Chi-Square Automatic Interaction Detection

4.1.3. Bonferroni Correction

4.1.4.  Classification and Regression Tree

4.1.5. Gini Impurity Index

4.1.6. Entropy

4.1.7. Cost based splitting criteria

4.1.8. Ensemble Methods

4.1.9. Random Forest

4.2.    Clustering

4.2.1. Introduction

4.2.2. Distance and Dissimilarity measures used in clustering

4.2.3. Quality and Optimal Number of clusters

4.2.4. Clustering Algorithms

4.2.5. K-means clustering

4.2.6. Hierarchical Clustering

 

Comments