Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Logistic Regression, Decision Tree and Neural Network in R
Rating: 3.9 out of 5(32 ratings)
3,002 students

Logistic Regression, Decision Tree and Neural Network in R

Logistic Regression, Decision Tree and Neural Network in R
Created byModeste Atsague
Last updated 8/2017
English

What you'll learn

  • At the end of this Course, A student will be able to use Predictive analytics ( Decision tree , neural network or Logistic regression) to predict future outcomes. Some areas of application are the following: Actuarial Science, marketing, financial services, insurance, mobility, pharmaceuticals, healthcare, just to name a few

Course content

1 section • 12 lectures • 1h 0m total length

  • Introduction0:33
  • How to download R2:28

    Learn to download and install R on Mac or Windows by selecting the proper installer, double-clicking to run, and following the continue prompts through the setup.

  • Welcome2:04
  • Description of the data4:03
  • Data transformation2:11

    Transform the response by recoding the sex variable to a binary 0/1 in a data frame using an if statement and the dollar-sign notation, preparing the dataset for analysis.

  • Missing values detection and treatment2:53
  • Data visualisation3:36

    Install and load the R package, then use plot to visualize salary by sex and occupation and interpret the resulting group comparisons.

  • Training and Testing set4:26
  • Decision Tree5:23

    Build and interpret a decision tree in R, train and evaluate the model, visualize splits, and predict sex from attributes using the training data.

  • Logistic regression4:08

    Explore logistic regression in R for binary outcomes, estimate predictive probabilities for sex, use a threshold of 0.5 for class prediction, and assess ~90% accuracy on test data.

  • Neural network26:52
  • Min Max normalization1:51

Requirements

  • The only prerequisite for this class is the willingness to learn and some basic knowledge of R but not necessary

Description

In this course, we cover two analytics techniques: Descriptive statistics and  Predictive analytics. For the predictive analytic, our main focus is the implementation of a logistic regression model a Decision tree and neural network. We well also see how to interpret our result, compute the prediction accuracy rate, then construct a confusion matrix .

By the end of this course , you will be able to effectively summarize your data , visualize your data , detect and eliminate missing values, predict futures outcomes using analytical techniques described above , construct a confusion matrix, import and export a data.

Who this course is for:

  • Anyone seeking a career as data scientist, data analyst , finance analyst, statistician , actuary, just to name few

Report abuse