Modeling method and device for predicting order cancellation, computer equipment and computer readable storage medium

• Main Authors: WANG DEJIAN, ZHOU YOURONG, SHI YUAN
• Format: Patent
• Language: Chinese; English
• Published: 12.03.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The embodiment of the invention discloses a modeling method and device for predicting order cancellation, computer equipment and a computer readable storage medium. The method comprises the steps of:selecting transaction data of historical orders as training samples, and selecting positive samples and negative samples from the training samples, wherein the positive samples are order data which isnot completed but canceled, and the negative samples are completed orders; preprocessing the associated data; training, evaluating and updating a machine learning model for the preprocessed data; anddeploying the model after offline training to an online environment. In the online service link, for each order, N surrounding drivers are acquired, the model is used to predict the probability thatthe N drivers are forced to cancel due to inappropriate matching with the order, the driver with the higher cancel probability is filtered out, and the order is pushed to the remaining drivers, so that the driver with better ser