Microsoft released a PDF cheat sheet of which machine learning algorithms can be used on Azure Machine Learning Studio. This Microsoft Azure Machine Learning Algorithm Cheat Sheet helps you choose the right machine learning algorithm for your predictive analytics solutions from the Microsoft Azure Machine Learning library of algorithms. The algorithms have been grouped in 5 different groups. These groups are:
- Regression: For predicting values. For Example when predicting a stocks price.
- Anomaly detection: For finding unusual data points. For example, any highly unusual credit card spending patterns which deviates from the normal credit card spending patterns.
- Clustering: The data points have no labels associated with them. Instead, the goal of an unsupervised learning algorithm is to organize the data in some way or to describe its structure. For example, discovering companies with similar marketing strategies.
- Two-class classification: When there are only two choices, it’s called two-class or binomial classification. For example distinguishing between a Cat or Dog.
- Multi-class classification: For predicting three or more categories. For Example predicting the winner of a Race.
To read the cheat sheet, read the path and algorithm labels on the chart as “For <path label>, use <algorithm>.” For example, “For speed, use two class logistic regression.” Sometimes more than one branch applies. In this case it is better to create scored models with both the algorithm and compare both of their accuracy to decide which algorithm is the better fit.
Even a beginner can easily use the cheat sheet provided to select which algorithm is apt for creating their predictive solution. There are some generalizations and oversimplifications, but it points you in a safe direction. It also means that there are lots of algorithms not listed here but these many algorithms are more than enough to give you a good head start in the ML world.