Big Data Analysis and MiningBayesClassifier2015 Fall9/22/2026
9/22/2026 1 Big Data Analysis and Mining 2015 Fall Bayes Classifier
Things We'd Like to Do SpamClassificationGiven an email, predict whether it is spam or notIMedicalDiagnosisGiven a list of symptoms, predict whether a patienthas disease X or notWeatherBased on temperature, humidity, etc... predict if it willraintomorrow
Things We’d Like to Do ◼ Spam Classification ◆ Given an email, predict whether it is spam or not ◼ Medical Diagnosis ◆ Given a list of symptoms, predict whether a patient has disease X or not ◼ Weather ◆ Based on temperature, humidity, etc. predict if it will rain tomorrow
ApplicationDigitRecognitionClassifierX,...,X E (0,1) (Black vs. White pixels)Y e {5,6) (predictwhetheradigitis a5 ora 6)
Application ◼ Digit Recognition ◼ X1 ,.,Xn {0,1} (Black vs. White pixels) ◼ Y {5,6} (predict whether a digit is a 5 or a 6) Classifier
Classification problemI Training data: examples of the form (d,h(a))where d are the data objects to classify (inputs)and h(d) are the correct class info for d, h(d)e{1,...K) Goal: given dnew, provide h(dnew)Training Info: Desired (target) OutputOutputsInputsSupervisedLearningError=(targetoutput-actualoutput)
Classification problem
Bayesian Classification A statistical classifier: performs probabilisticprediction, i.e., predicts class membershipprobabilitiesIFoundation:Based on Bayes'Theorem.Performance: A simple Bayesian classifier, naiveBayesianclassifier,hascomparableperformance with decision tree and selectedneuralnetworkclassifiers
Bayesian Classification ◼ A statistical classifier: performs probabilistic prediction, i.e., predicts class membership probabilities ◼ Foundation: Based on Bayes’ Theorem. ◼ Performance: A simple Bayesian classifier, naïve Bayesian classifier, has comparable performance with decision tree and selected neural network classifiers