A feature extraction method based on airline ticket booking behavior data

Abstract

The invention discloses a feature extraction method based on airline ticket booking behavior data, which comprises the following concrete steps: 1, retrieving original data from airline database and carrying out data preprocessing; 2, analyzing that preprocessed data by a feature extraction system to obtain the discrimination information of a normal user and an abnormal user; Step 3, extracting features based on the discrimination information of the normal user and the abnormal user, wherein the features include temporal features, quantitative features and location features. The invention extracts features from time series, location information and IP information, and predicts and intercepts malicious orders with high efficiency and accuracy, so as to obtain higher prediction accuracy.

Description

technical field [0001] The invention relates to the field of feature extraction, in particular to a feature extraction method based on airline booking behavior data. Background technique [0002] At present, there are some malicious booking behaviors on the ticketing websites. These bookings are generated by "broiler" accounts controlled by certain organizations, creating a monopoly situation for some popular routes, and then selling them to users at high prices, which seriously affects the interests of passengers. And make airlines suffer losses, ticket sales market order has also been seriously affected. How to identify malicious orders has important practical significance for improving airline service quality, improving user experience and maintaining market stability. However, the effective prediction of malicious booking behavior is still a problem to be solved. In the prior art, the black and white list method and the order credibility evaluation method are commonly u...

AI Technical Summary

Problems solved by technology

[0005] However, at present, malicious reservations and malicious inquiries in the field of airline ticketing are serious, which affects the normal operation of the airline ticketing market. They are all relatively simple, and the accuracy rate is not ideal enough, and it is impossible to identify malicious orders in real time and efficiently.

Images