English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 3h 03m | 522 MB
Data Science at your fingertips: build statistical predictive models to make predictions based on data
Predicting future trends can be the difference between profit and loss for competitive enterprises. Most businesses state that poor data quality leads to bad decision-making. Further, the predictive analytics market is expected to grow by 22% by 2020. As this technology hits the mainstream, now is the time to consider which predictive modeling techniques will produce the best results for your organization.
Hands-On Statistical Predictive Modeling gives you everything you need to bring the power of statistical predictive models into your statistical or data mining work. However, without the right predictive modeling techniques, analytics projects are unlikely to provide actionable insights. This course will show you how these core algorithms underpin the accuracy and relevance of statistical results and drive competitive differentiation. You will be able to anticipate customer behavior, take steps to cultivate customer loyalty, and capture a greater share of the market. You will be aware of the data science forces shaping your future economy and will have mastered how best to use and seize these coming opportunities.
By the end of this course, you will be able to elevate your company’s analytics know-how to enhance its decision-making skills, cost efficiency, and profitability. You will also be able to put these skills to use in your upcoming statistical and data mining projects.
This is an application-oriented course and the approach is practical. It discusses situations in which you would use each statistical predictive modeling technique, the assumptions made by the method, how to set up the analysis, and how to interpret the results. No proofs will be derived, but rather the focus will be on the practical aspects of data analysis for the purpose of improving predictive models.
What You Will Learn
- Differentiate between various types of predictive models
- Master linear regression
- Explore the results of logistic regression
- Understand when to use discriminant analysis
- Understand the inner workings of your models
- Maximize your productivity by analyzing your models and interpreting their accuracy in a well-organized manner
Table of Contents
Getting Started with Predictive Modeling
The Course Overview
Predictive Modeling – Purpose, Examples, and Types
Characteristics and Real-World Examples of Statistical Predictive Models
Making Predictions with Linear Regression
Understanding Linear Regression Theory
Using Simple Linear Regression to Predict Salary
Using Multiple Linear Regression to Predict Salary
Using Stepwise Linear Regression to Predict Waste
Testing Linear Regression’s Assumptions
Incorporating Categorical Variables (Dummy Variables)
Determining Likelihoods Using Logistic Regression
Understanding Logistic Regression Theory
Using Binary Logistic Regression to Predict Birth Weight
Using Multinomial Logistic Regression to Predict Credit Risk
Testing Logistic Regression’s Assumptions
Classifying Cases with Discriminant Analysis
Understanding Discriminant Analysis Theory
Using Two-Group Discriminant Analysis to Predict Likelihood of Purchase
Using Multi-Group Discriminant Analysis to Predict Risky Behavior
Testing Discriminant Analysis Assumptions
Comparing Logistic Regression and Discriminant Analysis
Resolve the captcha to access the links!