Course Description
The course covers topics like data analysis and data visualization. Topics covered in this course include techniques of regression, prediction, categorization of data, and pattern detection in complex data. The course also covers creating and evaluating different types of association rules and provides an overview of ethical considerations of implementing Big Data analytics in an organization.
Audiences
This course is intended for data analytics project managers, data and business analysts, database professionals and forecasting and trend management practitioners.
Curriculum
- 8 Sections
- 49 Lessons
- 10 Weeks
Expand all sectionsCollapse all sections
- Exploratory Data Analysis with R5
- Data Analysis and Data Visualization3
- Working with Unstructured Data4
- Regression and Prediction Techniques8
- 5.1Linear Regression Explained
- 5.2Logistic Regression Explained
- 5.3Modeling relationship output and input variables
- 5.4Interpreting coefficients of continuous data
- 5.5Assessing the ‘goodness of fit’ of Regression Models
- 5.6Regression techniques for Big Data
- 5.7Dealing with Data volume with RHadoop
- 5.8Creating regression modules for RHadoop
- Data Categorizing with Classification Techniques7
- 6.1Automated Labeling of new data items
- 6.2Prediction using Decision Trees
- 6.3Creating a Model from historical data for Predictions
- 6.4Combining tree predictors with random forests in RHadoop
- 6.5Assessing Model Performance
- 6.6Visualizing Model Performance with a ROC curve
- 6.7Confusion Matrices to evaluate Classifiers
- Detecting Patterns in Complex Data8
- 7.1Overview of Clustering and Link Analysis
- 7.2Using K–Means Algorithm for Customer Market Segmentation
- 7.3Defining Similarity using Appropriate Distance Measures
- 7.4Creating Tree–like Clusters with Hierarchical Clustering
- 7.5Clustering Text Documents and Tweets
- 7.6Connections Discovery with Link Analysis
- 7.7Capturing Connections with Social Network Analysis
- 7.8Social Networks Results usage in Marketing
- Creating and Evaluation Different Association Rules8
- 8.1Building and evaluating association rules
- 8.2Capturing true customer preferences in transaction data to enhance customer experience
- 8.3Calculating support, confidence and lift to distinguish “good” rules from “bad” rules
- 8.4Differentiating actionable, trivial and inexplicable rules
- 8.5Meeting the challenge of large data sets when searching for rules with RHadoop
- 8.6Constructing recommendation engines
- 8.7Cross–selling, up–selling and substitution as motivations
- 8.8Leveraging recommendations based on collaborative filtering
- Implementing Analytics in an Organization6
- 9.1Expanding analytic capabilities
- 9.2Breaking down Big Data Analytics into manageable steps
- 9.3Integrating analytics into current business processes
- 9.4Reviewing Spark, MLib and Mahout for machine learning
- 9.5Examining ethical questions of privacy in Big Data
- 9.6Disseminating results to different types of stakeholders
