Online advertisement putting optimization method and system based on machine learning

The invention discloses an online advertisement putting optimization method and system based on machine learning. The method comprises the steps of advertisement putting data collection, data preprocessing, accurate advertisement putting, repeated advertisement processing and regular evaluation and adjustment. The invention belongs to the technical field of data processing, and particularly relates to an online advertisement putting optimization method and system based on machine learning. According to the scheme, target audiences of advertisement putting are determined, an accurate advertisement putting model is constructed, a hypothesis function of logistic regression is used, and maximum likelihood estimation and a stochastic gradient rising method are used for solving an update vector; calculating the probability that the classifier judges that the parameters are positive examples according to the feature vectors, setting a probability threshold value, screening out target users needing advertisement putt