Performance assessment of ensemble learning systems in financial data classification

Financial data classification plays an important role in investment and banking industry with the purpose to control default risk, improve cash and select the best customers. Ensemble learning and classification systems are becoming gradually more applied to classify financial data where outputs from different classification systems are combined. The objective of this research is to assess the relative performance of existing state‐of‐the‐art ensemble learning and classification systems with applications to corporate bankruptcy prediction and credit scoring. The considered ensemble systems include AdaBoost, LogitBoost, RUSBoost, subspace, and bagging ensemble system. The experimental results from three datasets: one is composed of quantitative attributes, one encompasses qualitative data, and another one combines both quantitative and qualitative attributes. By using ten‐fold cross‐validation method, the experimental results show that AdaBoost is effective in terms of low classification error, limited complexity, and short time processing of the data. In addition, the experimental results show that ensemble classification systems outperform existing models that were recently validated on the same databases. Therefore, ensemble classification system can be employed to increase the reliability and consistency of financial data classification task.     

基于SVM的房地产财务决策风险预测及敏感性分析

本文以房地产上市公司的财务数据为参考依据,结合相关性分析,筛选并建立影响财务风险的指标体系;利用支持向量机建立财务风险分析预测模型;并使用灰色关联理论对指标进行敏感性分析,从而得到影响财务风险最敏感的指标。     

对江苏省电力负荷进行回归预测

本文主要根据2001-2011年江苏省用电量样本数据,建立了江苏省电力负荷与人均GDP、工业化以及人口数之间的多元回归预测方程,并预测了江苏省2014-2020年总用电量数据,在此基础上提出了相应的建议。     

Noisy signaling in discrete time

This paper characterizes the equilibrium set of a dynamic noisy-signaling model in discrete time. A seller privately knows the quality of her asset. She can exert a costly effort to generate stochastic returns. Buyers stochastically arrive over time and, after observing the history of returns, they make price offers. In our model, the equilibrium behavior of the buyers is discontinuous: they only make acceptable (high) offers if the posterior about the quality is above a given threshold. As a result, the recursive nature of the model replicates the discontinuity, giving the equilibrium continuation payoff a complex self-replicating structure that may take the form of a devil’s staircase.     

单车场无时间窗甩挂运输车辆调度的启发式算法

考虑了牵引车空驶、带空挂车行驶和带重挂车行驶所引起的成本差异，定义了牵引车运行成本的概念，将总运行成本最小作为调度方案优劣的判别指标，并同时考虑牵引车数量最少。将牵引任务分为四种类型，定义了任务链、虚拟任务、链内交叉和链间交叉的概念，提出了一种求解该类单车场甩挂运输车辆调度无时间窗约束的启发式算法，包括初始调运方案、链内优化、空车调运交叉、牵引车数量优化和链间交叉。最后给出了仿真算例，算法优化后的最终方案与初始方案相比，牵引车数量减少，总运行成本降低，验证了算法的有效性和可行性。     

Post encroachment time threshold identification for right-turn related crashes at unsignalized intersections on intercity highways under mixed traffic

Abstract

Unsignalized intersections in developing countries experience many serious conflicts between cross-traffic due to indiscipline traffic manoeuvrability. Historically, Post Encroachment Time (PET) has gained attention as a proximal indicator to analyze crossing conflicts. However, identifying an appropriate PET threshold to classify critical conflicts for highly heterogeneous traffic scenario is still an unexplored area. Consequently, this study proposes a novel approach of PET threshold identification with proof of application by collecting data from ten intersections located on four-lane intercity highways in the National Capital Region (NCR), India. Both crossing conflicts and right-turn related crash data (for the left-hand drive) are collected. Their correlations are thoroughly studied for each PET threshold using a quantitative technique considering all and individual vehicle categories. Finally, a qualitative analysis is done by ranking the sites based on cumulative PET and related crashes to verify the proposed quantitative technique. A PET threshold of 1?s is obtained from both the techniques which can be used to identify critical conflicts for unsignalized intersections located on four-lane intercity highways. The proposed methodology will serve as an alternative, faster and effective tool to evaluate the hazardousness of unsignalized intersections located on intercity highways under highly heterogeneous traffic condition.     

Minimising emergency response time of ambulances through pre-positioning in Dhaka city,Bangladesh

This study conducted a large-scale survey in Dhaka, Bangladesh; the survey involved 95 major hospitals, more than 3000 emergency room patients, and 2 of the largest ambulance operators. Currently, most ambulances are parked within the vicinity of hospitals and are either dispatched or fetched by the acquaintances of the patient on demand, resulting in lengthy round trips. Reducing the response time of ambulances would certainly improve the emergency service, and pre-positioning of the ambulances could be a solution to reducing the response time. This study used two approaches to address the problem. First, the location-allocation problem was solved to find the optimal number of ambulance locations by maximising the demand coverage. Second, separate location-allocation for the peak and off-peaks, using K-means clustering, was applied to systematically optimise the ambulance positioning in small clusters near demand points. These approaches could substantially improve the existing emergency response time. Distributing ambulances near demand points yielded greater improvements in response time than when the ambulances are stationed near hospitals.     

Light fuel demand and public policies in Brazil, 2003–2013

The main objective of this article is to evaluate determinants of demand for light fuels in Brazil between 2003 and 2013. Through a vector autoregression analysis, an effort was made to identify and quantify the impact of different economic variables and public policy measures adopted during this period on the surprising increase in energy consumption by Brazil’s light-vehicle fleet. The results suggest that demand for energy by the light-vehicle fleet was influenced by an increase in income, by a decrease in fuel prices associated with a policy designed to prevent increases in the price of gasoline from pushing the inflation rate up, by a higher availability of credit for buying vehicles, and by a drop in the real price of those goods, with emphasis on countercyclical measures to waive the tax on industrialized products levied on new vehicles during economic downturns in the automotive industry.     

论历史逻辑

历史逻辑是以历史时间的历时性和共时性统一为基础的概念推论，研究关于叙述史中基本概念之间的意义关系和推论规则。过去、现在和未来是历史逻辑的基本范畴，“过去-现在-未来”三段式是历史逻辑的基本公式，它是概念逻辑推论三段式“正题-反题-合题”在历史逻辑中的具体形式。历史逻辑研究的目的，是根据特定历史时段的特殊性，建构以不同时段概念为逻辑变项的历史逻辑，预见未来的发展，规划现在的实践。     

模糊层次分析法优化BP神经网络的交通冲突预测模型

本文通过全面剖析影响交通冲突的原因,以交通流量、道路几何设计和道路环境三方面的因素建立指标层次结构体系。提出基于模糊层次分析(FAHP)法优化BP神经网络(BPNN)的预测模型,应用于交通冲突预测。