Predicting credit card delinquencies: An application of deep neural networks

The objective of this paper is twofold. First, it develops a prediction system to help the credit card issuer model the credit card delinquency risk. Second, it seeks to explore the potential of deep learning (also called a deep neural network), an emerging artificial intelligence technology, in the credit risk domain. With real-life credit card data linked to 711,397 credit card holders from a large bank in Brazil, this study develops a deep neural network to evaluate the risk of credit card delinquency based on the client's personal characteristics and the spending behaviours. Compared with machine-learning algorithms of logistic regression, naive Bayes, traditional artificial neural networks, and decision trees, deep neural networks have a better overall predictive performance with the highest F scores and area under the receiver operating characteristic curve. The successful application of deep learning implies that artificial intelligence has great potential to support and automate credit risk assessment for financial institutions and credit bureaus.     

Using machine learning and big data for efficient forecasting of hotel booking cancellations

Cancellations are a key aspect of hotel revenue management because of their impact on room reservation systems. In fact, very little is known about the reasons that lead customers to cancel, or how it can be avoided. The aim of this paper is to propose a means of enabling the forecasting of hotel booking cancellations using only 13 independent variables, a reduced number in comparison with related research in the area, which in addition coincide with those that are most often requested by customers when they place a reservation. For this matter, machine-learning techniques, among other artificial neural networks optimised with genetic algorithms were applied achieving a cancellation rate of up to 98%. The proposed methodology allows us not only to know about cancellation rates, but also to identify which customer is likely to cancel. This approach would mean organisations could strengthen their action protocols regarding tourist arrivals.     

Determinants in the forecast of the gross national income of China and India from 1952 to 2015

In 2015, China and India's population represented approximately 35.74% of the total number of people living in the world. Due to the historical context and behavior of the most relevant indicators, this study proposes to utilize a wide variety of demographic, economic, and production indicators from 1952 to 2015 to assess their impact on the GNI in China and India. A comprehensive and new fangled modeling process with stepwise, regularization and distributed lag regression approaches is presented. Accordingly, theoretical results were corroborated through extensive diagnostic tests and an empirical check of the models' predictive capacity. The findings show that GNI in China is most influenced by variables such as reserves in foreign currency and the dependency ratio; whereas, variables of energy production and birth rate were generated for India. Therefore, it's the timing for China to relax the universal two-child policy. Due to the current value below the substitution rate, a gloomy outlook for China's future population and economy is predicted. Conversely, a positive outlook is forecasted for India, given the low price in the future of oil- India's primary raw material.     

Selection of influential variables in ordinal data with preponderance of zeros

Presence of excess zero in ordinal data is pervasive in areas like medical and social sciences. Unfortunately, analysis of such kind of data has so far hardly been looked into, perhaps for the reason that the underlying model that fits such data, is not a generalized linear model. Obviously some methodological developments and intensive computations are required. The current investigation is concerned with the selection of variables in such models. In many occasions where the number of predictors is quite large and some of them are not useful, the maximum likelihood approach is not the automatic choice. As, apart from the messy calculations involved, this approach fails to provide efficient estimates of the underlying parameters. The proposed penalized approach includes ?₁ penalty (LASSO) and the mixture of ?₁ and ?₂ penalties (elastic net). We propose a coordinate descent algorithm to fit a wide class of ordinal regression models and select useful variables appearing in both the ordinal regression and the logistic regression based mixing component. A rigorous discussion on the selection of predictors has been made through a simulation study. The proposed method is illustrated by analyzing the severity of driver injury from Michigan upper peninsula road accidents.     

基于神经网络的建筑业碳排放强度预测——以京津冀为例

通过统计分析得出影响建筑业碳排放强度的13个影响因素,基于收集的京津冀相关数据,运用逐步回归分析找出其中6个关键因素.借鉴五折交叉验证解决数据稀缺问题,采用神经网络对京津冀建筑业碳排放强度进行预测.利用敏感性分析简化模型,筛选出4个核心因素.结果表明,此模型预测精度高达99％,同时根据挖掘出的核心因素和关键因素,提出建筑业节能减排的建议.     

基于人工神经网络的互联网公司估值方法研究

资本市场认为互联网公司市值的驱动因素应包括盈利因子、运营因子、流量因子和协同因子。将协同效应指标考虑到公司估值体系中,意图构造互联网公司优化估值模型。使用美股上市的互联网企业数据建立了评价指标体系,通过因子分析实现了二级指标降维,通过实证分析确认了四个因子与公司市值的相关关系,最后构建了基于人工神经网络BP算法的互联网公司估值模型,通过预测数据的检验发现模型的准确度较高。随着2018年互联网公司美股上市潮的持续,该模型能有效为资本市场估值提供参考。     

基于深度学习的跳频信号识别

针对跳频信号分选存在人工提取参数特征具有复杂性的问题，提出了一种基于深度学习的识别方法。首先对跳频信号进行短时傅里叶变换，得到二维的时频矩阵；接着提取信号的轮廓特征，构造三维矩阵作等高线图，并对等高线图进行预处理；最后把预处理后的等高线图输入到卷积神经网络中进行训练、测试，进而实现分类识别。仿真结果表明，在不需要复杂的人工提取参数特征的基础上，在分选率为100〖WT《Times New Roman》〗%〖WTBZ〗时，所提方法经裁剪处理下的信噪比为-15 dB，比支持向量机和传统K-Means聚类算法都低10 dB。实测数据的算法验证表明，所提方法能够将大疆精灵4Pro、hm无人机、司马航模X8HW以及大疆悟2这四类无人机正确分类。     

一种基于孪生神经网络的深度异构网络嵌入算法

针对现有异构网络嵌入方法导致的捕获关系冗余和模糊的问题，提出了一种基于孪生神经网络的深度异构网络嵌入模型。首先，基于面向关系的深度嵌入(Relation-Oriented Deep Embedding，RODE)框架构建了异构网络嵌入模型，以区分同型节点和异型节点之间的关系；其次，将同型节点与异类节点之间的相似性近似到低维空间，通过构建多任务的孪生神经网络来实现节点之间结构和语义关系的深度嵌入；最后，选取四个数据集执行典型网络挖掘任务，并与其他六种算法进行实验对比分析。实验结果表明，保持相同类型节点之间的相似性有助于提高节点分类效率，且损失函数在提高异构网络嵌入质量方面具有良好的优越性；RODE模型能够有效提高稀疏网络的嵌入质量，且具有良好的稳定性和鲁棒性。     

基于BP人工神经网络中国光伏产业贸易摩擦预警研究

建立有效的贸易摩擦预警系统有利于中国新兴产业的健康发展,有利于中国实施制造强国战略。将警兆信号法与人工神经网络相结合,从宏观经济形势、产业供给能力、双边贸易状况、市场需求水平等四个维度切入,构建了中国光伏产品出口贸易摩擦预警系统模型。预警分析表明,模型的预警效果与现实拟合较好,具有可行性。从模型的预警结果来看,2019年~2020年中国输美光伏产品贸易摩擦警情均低于轻警级别,仍面临一定的贸易摩擦风险。     

一种基于微波雷达回波信号的车型分类方法

车辆类型识别方法是智能交通系统的关键技术之一。利用深度学习的高维特征泛化学习能力，将改进的LeNet-5卷积神经网络用于基于交通微波雷达的大小车型分类识别。首先，以雷达触发前的N帧信号为基础，对雷达的回波信号进行分析并构建数据集；然后，分析LeNet-5卷积神经网络的特点；最后提出一种改进的LeNet-5卷积神经网络。实验结果表明，与传统的支持向量机方法相比，所提方法能够智能学习大小车的雷达时频信号特征，大小车型识别准确率达到97%以上，可为交通场景下的车型识别研究提供新的技术途径。