In this module, you will be able to develop your base for advanced predictive analytics through basic tools like correlation and regression. This module helps you differentiate between these two terms and acquaints you with how correlation measures the degree of association between two variables, whereas regression tells us about the functional relationship among the variables. In this module, you will be learning how to compute correlation coefficient, simple linear regression, and multiple linear regression for a given data set with the help of statistical software for social sciences. Finally, this module will cover the basic assumptions of multiple linear regression and help you test the significance of the correlation coefficient.

In this module, you will be introduced to naïve Bayes classification. One of the most common predictive analytics models is the classification model. This module also introduces you to how these models work by categorizing information based on historical data. This module will help you understand how classification predicts the categorical class (or discrete values), whereas regression and other models predict continuous valued functions.

In this module, you will be continuing with classification modeling. This module will introduce you to the k nearest neighbors. This module will help you apply the k nearest neighbors method to business problems. This module will further explain the working of k nearest neighbors. After going through this module, you will be able to run k nearest neighbors in RStudio.

This assessment is a graded quiz based on the modules covered in this week.

In this module, you will learn about logistic regression. When you are interested in predicting the likelihood of an event, the most widely used classification method is logistic regression. When the classification problem at hand is binary, true or false, and yes or no, then you use logistic regression-based classification.

In this module, you will learn about discriminant analysis. When you know the groups a priori, the classification method used is discriminant analysis. This module will help you run discriminant analysis binomial and multinomial categorical variables.

This assessment is a graded quiz based on the modules covered in this week.

In this module, you will learn about decision trees. When there is non-linear data in hand for classification, the classification method that is used preferably is the decision tree. Their most important feature is the capability of capturing descriptive decision-making knowledge from the supplied data. This module will make you familiar with the concept of information gain and entropy. This module will further help you create the decision tree for business problems.

In this module, you will learn about neural networks. This module gives you an insight into how you can use a neural network when you have so much data with you (and computational power, of course), and accuracy matters the most to you. If it comes to predictive accuracy, then neural network–based classification models are the ones that are preferred.

In this module, you will learn about the important steps of dimension reduction. In data mining, one often encounters situations where there are a large number of variables in the database. Even when the initial number of variables is small, this set quickly expands in the data preparation step, where new derived variables are created, for instance, dummies for categorical variables and new forms of existing variables. In such situations, it is likely that subsets of variables are highly correlated with each other. Including highly correlated variables in a classification or prediction model or including variables that are unrelated to the outcome of interest can lead to overfitting, and accuracy and reliability can suffer.

In this module, you will learn how clustering refers to the grouping of records, observations, or cases into classes of similar objects. You will get insights into how a cluster is a collection of records that are similar to one another and dissimilar to records in other clusters. In this module, you will be able to understand distance measures and how different types of distance measures are used in clustering. You will also be introduced to the quality and an optimal number of clusters, and the various types of clustering methods, such as hierarchical clustering, single-linkage clustering, and complete-linkage clustering. Finally, you will learn about dendrograms, displaying the clustering process and results, and the limitations of hierarchical clustering.

This assessment is a graded quiz based on the modules covered in this week.

In this module, you will be introduced to non-hierarchical clustering: the K-means clustering algorithm, its computation process, and its advantages. You will also learn to determine the correct number of clusters. Finally, you will be able to give the interpretation of clusters and market segmentation using conjoint analysis.

In this module, you will learn how to use rule base machine learning models to analyze and discover interesting connections, patterns, and relationships between different item sets based on large volume transaction data. This module will give you an insight into how association rule mining measures the strength of co-occurrence between one item and another. The objective of this rule base data mining algorithm is not to predict an occurrence of an item, like classification or regression do, but to find usable patterns in the co-occurrences of the items. You will also learn about association rules learning, which is a branch of an unsupervised learning process that discovers hidden patterns in data, in the form of easily recognizable rules.

This assessment is a graded quiz based on the modules covered in this week.

Course Wrap-Up video