Banknote distribution prediction method and device based on GBDT algorithm

• Main Authors: YAN XIAOYU, GUO YUJIE, LIU YA, LIU RUIGUO, WEN ZHENZHEN, ZHANG JING, LIU PENGQIANG, LI PENG, MAO FULIN, GUO QIANG, DING PING, CHANG CHENGJUAN, ZHAO CHUANJUN, LAN RUOQIAN
• Format: Patent
• Language: Chinese; English
• Published: 31.12.2019
• 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; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a banknote distribution prediction method and device based on a GBDT algorithm. The banknote distribution prediction method comprises the steps: acquiring data information influencing cash transaction of a to-be-distributed banknote branch; constructing a feature data set according to the data information; and training a banknote distribution amount prediction model established based on a GBDT algorithm by using the feature data set, and predicting the banknote distribution amount of the banknote distribution branch on the next day according to the trained banknote distribution amount prediction model. According to the invention, banknote distribution does not need to be carried out according to the experience of workers, and the deviation between the banknote distribution amount and the actual demand is small, and the labor intensity of the workers is low. 本发明公开了一种基于GBDT算法的配钞预测方法及装置，该方法包括：获取影响待配钞网点现钞交易的数据信息；根据数据信息构建特征数据集；利用特征数据集对基于GBDT算法建立的配钞量预测模型进行训练，根据训练后的配钞量预测模型预测待配钞网点次日的配钞量。本发明无需根