Trang 1

Microsoft Azure Machine Learning: Algorithm Cheat Sheet This cheat sheet helps you choose the best Azure Machine Learning Studioalgorithm for your predictive analytics solution. Your decision is driven by both the nature of your data and the question you’re trying to answer. ANOMALY DETECTION CLUSTERING MULTI-CLASS CLASSIFICATION >100 features, K-means One-class SVM aggressive boundary Fast training, linear model Multiclass logistic regression PCA-based anomaly detection Fast training Accuracy, long training times Multiclass neural network Discovering structure Finding unusual data points Accuracy, fast training Multiclass decision forest Three or REGRESSION more Accuracy, small memory footprint Multiclass decision jungle Ordinal regression Data in rank ordered categories START Predicting categories Depends on the two-class classifier, see notes below One-v-all multiclass Poisson regression Predicting event counts Predicting values Two Fast forest quantile regression Predicting a distribution TWO-CLASS CLASSIFICATION Linear regression Fast training, linear model Accuracy, Two-class decision forest fast training Two-class SVM >100 features, Accuracy, linear model fast training, Bayesian linear regression Linear model, small data sets large memory Two-class boosted decision tree footprint Two-class averaged perceptron Fast training, linear model Accuracy, Neural network regression Accuracy, long training time small memory Two-class decision jungle footprint Two-class logistic regression Fast training, linear model Decision forest regression Accuracy, fast training >100 features Two-class locally deep SVM Two-class Bayes point machine Fast training, Accuracy, fast training, linear model Accuracy, long Boosted decision tree regression Two-class neural network large memory footprint training times © 2015 Microsoft Corporation. All rights reserved. Created by the Azure Machine Learning Team Email: AzurePoster@microsoft.com Download this poster: http://aka.ms/MLCheatSheet