最新刊期

      “在信用卡风险管控领域，专家构建了基于SMOTEENN-XGBoost的预测模型，准确率达91.8%，为银行甄别客户信用风险提供重要价值。”

      TIAN Yuan, GUO Honglie, JI Qian

      DOI：10.11907/rjdk.231548
      摘要：To achieve risk management for credit cards and reduce economic losses caused by credit card defaults， it is particularly important to develop an effective credit card risk prediction model. In response to the issue of imbalanced credit card data distribution， the ENN algorithm was used to improve the classical SMOTE algorithm， resulting in the construction of a credit card risk prediction model based on SMOTEENN-XGBoost. Empirical evidence reveals that this model achieves a prediction accuracy of 91.8% and an AUPRC value of 0.903， which is significantly better than classical models such as SVC， GBDT， and AdaBoost. It holds significant value in predicting high-risk credit card users and aiding banks in accurately identifying customer credit risks.  
      关键词：credit card risk prediction;data balancing;SMOTEENN;XGBoost   
      126
      |
      174
      |
      0
      <HTML>
      <L-PDF><WORD><Enhanced-PDF><Meta-XML>
      <引用本文> <批量引用> 50615055 false
      更新时间：2024-03-21
      “智能手机变身乐器，通过内置传感器感知动作生成旋律，实现音乐启蒙教育。”

      LIN Qiaomin, TAO Hai, LIN Zecheng

      DOI：10.11907/rjdk.231678
      摘要：Inspired by the Internet of Things allowing objects to speak， let the smartphone's built-in sensors sense the phone's status and generate music melodies without the need for additional hardware devices. After experimenting with sensors embedded in smartphones， the main idea is to imagine a sensor based spatial coordinate system in front of a handheld smartphone， and swing the smartphone along the+x， - x，+y，++y， - y， - y，+z， and - z axes to obtain perceptual data. Based on the data， octave notes are mapped to different hand movements， driving the speaker to play the corresponding notes. Experiments on applications developed on the Android platform have shown that simple melodies such as "Little Stars" can be played based on the mapping of actions and notes， turning smartphones into musical instruments suitable for young people and other groups to engage in music enlightenment education based on their own interaction， achieving the goal of teaching through music.  
      关键词：smartphone;sensor;embodied interaction;music generation   
      83
      |
      84
      |
      0
      <HTML>
      <L-PDF><WORD><Meta-XML>
      <引用本文> <批量引用> 48404648 false
      更新时间：2024-02-21
    0