About The Course
Edureka's Advanced Predictive Modeling in R course will cover the Advanced Statistical and Analytical techniques. This course focuses on case study approach for learning various Analytical techniques and there will be a project to be done at the end of the course.
After the completion of Advanced Predictive Modeling in R course at Edureka, you will be able to:
1. Understand the need for Statistical Predictive Modeling
2. Work on Logistic and Linear Regression
3. Do Forecasting with Time series data and decomposition
4. Implement ARIMA models
5. Understand Survival Analysis and Neural Networks
Who should go for this course?
This Advanced Analytics course is a must for anyone who aspires to get into Data Analytics and Decision science. The following professionals can go for this course :
1. Developers who want to step-up as 'Data Scientists'
2. Analytics Consultants
3. R / SAS / SPSS Professionals
4. Data Analysts
5. Information Architects and Data Engineers
Pre-requisites for learning Advanced Predictive Modeling is knowledge on R and exposure to basics of statistics.
The Project will be based on a freely available dataset. The students will be asked to make different models based on the dataset and evaluate them. They will have to explore the data and decide on the right techniques that needs to be implemented. They will have to present the project as a PPT with reasons for their choices.
Why learn Advanced Predictive Modeling in R?
Advanced Predictive Modeling in R will allow one to gain an edge over other Data analysts and present the data in a much better and insightful manner.
This would help the learner to immediately implement these technique and create analysis and support decision making in the most scientific manner.
1. Basic Statistics in R
Learning Objectives - In this module, you will get an introduction to statistics and conduct best test and exploratory analysis.
Topics - Basic Statistics, Hypothesis Analysis, Correlation, Covariance, Matrix, Basic Charts.
2. Ordinary Least Square Regression 1
Learning Objectives - In this module, you will be introduced to basic regression and multiple regression, and will learn how to present the same graphically.
Topics - Exporting Data and Connecting Sheets, Making Basic Visualization in Tableau, Making Sense out of the Visuals and Interpreting the same.
3. Ordinary Least Square Regression 2
Learning Objectives - In this module, you will dive into linear regression and make the model a better fit, make necessary transformation check for over fitting and under fitting and outliers identification and treatment.
Topics - Residual Plots, AV plots, deletion diagnostics, partial correlation, subset selection, influential observations, transformations, Hetroscadasticity, VIFs, Multi co-linearity, auto-correlations, tests, dummy variables, seasonality, DW tests, Box-Cox transformation, interaction variables
4. Logistic Regression
Learning Objectives - In this module, you will be introduced to logistic regression and various uses of the same and also its industry usage.
Topics - Basic Logistic Regression, Uses, Drawbacks of OLS, Tests.
5. Advanced Regression
Learning Objectives - In this module, you will dive into logistic regression, learn about more varied usage of logistic regression on various dataset.
Topics - Poisson Regression, Multinomial, ordinal Regression: Business Case & Zero-inflated regression, Negative binomial, Panel data.
Learning Objectives - In this module, you will learn about addressing missing values and how to impute it using various process.
Topics - Imputations using various methods like regression, mode/mean substitutions.
7. Forecasting 1
Learning Objectives - In this module, you will get an introduction to forecasting and time series data.
Topics - Techniques, Time series data, Decomposition, ARIMA/ ARMA, ACF and PACF plots, Seasonality and Smoothing (exponential).
8. Forecasting 2
Learning Objectives - In this module, you will learn about Seasonality, Trend Analysis and decaying the factors over the time.
Topics - Holt_winter smoothing, Growth Models, binary data, Neural Networks, ARCH / GARCH, trend lines (exponential trend lines).
9. Survival Analysis
Learning Objectives - In this module you will learn about Churn analysis and Regression on time series data with time component.
Topics - Survival Analysis, CoxPH analysis, Plots, tests.
Learning Objectives - In this module, you will work on a dataset of your choice after approval from the trainer. The project needs to cover all concepts discussed in the class. The scope of project should enable you to perform various regressions (including logistic regression), forecasting and survival analysis. You are encouraged to take up a dataset that has missing value and logically impute the same before performing any predictive modeling. You can further develop various models under each section (logistic, forecasting and survival) and then suggest the best one using any technique of his choice. You also need to perform EDA and various aggregation and transformation before jumping into model making and implementing the entire concept on a free dataset
Topics - Project Discussion.