Ke Da, Fan Xianhua, Asif Muhammad
School of Management, Huazhong University of Science and Technology, Wuhan, Hubei, China.
School of Economics and Management, China University of Geosciences, Wuhan, Hubei, China.
PeerJ Comput Sci. 2024 Nov 7;10:e2412. doi: 10.7717/peerj-cs.2412. eCollection 2024.
This article addresses the problem of interval pricing for auction items by constructing an auction item price prediction model based on an adaptive learning algorithm. Firstly, considering the confusing class characteristics of auction item prices, a dynamic inter-class distance adaptive learning model is developed to identify confusing classes by calculating the differences in prediction values across multiple classifiers for target domain samples. The difference in the predicted values of the target domain samples on multiple classifiers is used to calculate the classification distance, distinguish the confusing classes, and make the similar samples in the target domain more clustered. Secondly, a deep clustering algorithm is constructed, which integrates the temporal characteristics and numerical differences of auction item prices, using DTW-K-medoids based dynamic time warping (DTW) and fuzzy C-means (FCM) algorithms for fine clustering. Finally, the KF-LSTM auction item interval price prediction model is constructed using long short-term memory (LSTM) and dual clustering. Experimental results show that the proposed KF-LSTM model significantly improves the prediction accuracy of auction item prices during fluctuation periods, with an average accuracy rate of 90.23% and an average MAPE of only 5.41%. Additionally, under confidence levels of 80%, 85%, and 90%, the KF-LSTM model achieves an interval coverage rate of over 85% for actual auction item prices, significantly enhancing the accuracy of auction item price predictions. This experiment demonstrates the stability and accuracy of the proposed model when applied to different sets of auction items, providing a valuable reference for research in the auction item price prediction field.
本文通过构建基于自适应学习算法的拍卖物品价格预测模型，解决了拍卖物品的区间定价问题。首先，考虑到拍卖物品价格的混淆类特征，开发了一种动态类间距离自适应学习模型，通过计算目标域样本在多个分类器上预测值的差异来识别混淆类。利用目标域样本在多个分类器上预测值的差异来计算分类距离，区分混淆类，并使目标域中的相似样本更聚集。其次，构建了一种深度聚类算法，该算法整合了拍卖物品价格的时间特征和数值差异，使用基于动态时间规整（DTW）的DTW-K-中心点算法和模糊C均值（FCM）算法进行精细聚类。最后，使用长短期记忆（LSTM）和双重聚类构建了KF-LSTM拍卖物品区间价格预测模型。实验结果表明，所提出的KF-LSTM模型在波动期显著提高了拍卖物品价格的预测准确率，平均准确率为90.23%，平均平均绝对百分比误差（MAPE）仅为5.41%。此外，在80%、85%和90%的置信水平下，KF-LSTM模型对实际拍卖物品价格的区间覆盖率超过85%，显著提高了拍卖物品价格预测的准确性。该实验证明了所提出的模型在应用于不同拍卖物品集时的稳定性和准确性，为拍卖物品价格预测领域的研究提供了有价值的参考。
