Course: Machine Learning in Finance
Software to be use:
MATLAB
Note: Use the File called Credit decision.xls for data analysis on Matlab and Attach your codes and outputs for each of the following questions below:
Questions:
1. Train a decision tree model on the full data. Use the trained decision tree model to predict the binary rating of each company in the data set. Calculate the confusion matrix.
2. Train a Random Forest model using 500 trees. Use the trained model to compute the probabilities for each class in the data set.
3. Train a Logistic Regression model and calculate the probabilities for each class in the data set.
4. Train a Support vector Machine model and calculate the probabilities for each class.
5. Repeat step 1 to train and predict the "Rating" of the company using a decision tree. This is a multi-class prediction problem.
6. Repeat steps 2 and 3 to compute probabilities for each Rating class in the data set. This is a multi-class prediction problem.
7. Use the classification learner app in Matlab to train and rank all the models we discussed; namely decision trees, random forests, logistic regression and support vector machines. Which model does the best on the accuracy score?
The following content is partner provided