Chang Liu

Southwestern University of Finance & Economics

Firm's green practices and sustainable development strategies are considered to have controversial impacts on its economic performance. Exploring the precise relationship between them can provide a theoretical dimension to the long-term development of firms and the achievement of national sustainable development goals (SDGs). In this study, the aut...

Although machine learning (ML) algorithms have been widely used in forecasting the trend of stock market indices, they failed to consider the following crucial aspects for market forecasting: (1) that investors’ emotions and attitudes toward future market trends have material impacts on market trend forecasting (2) the length of past market data sh...

Traditional credit risk measurement models, requiring fair amounts of default debts, have trouble in measuring the true default probability of Government financing vehicle (GFVs) loans in China. In this study, an analytic hierarchical mixing model (AHMM) was proposed to estimate the real states of Chinese GFVs with little default observations. AHMM...

Using interdisciplinary technologies of Web 2.0, Artificial Intelligence, Operational Research, and Integrated Automatic Manufacturing, this model generates a plausible solution for online taking of laundry orders placed by hotels, accessing path planning through Baidu® external port for scheduling under integrated automatic manufacturing and sched...

A company’s operational uncertainty resulting from economic activity could be measured by its contingent liabilities. When the contingent liabilities are forecasted by the analysts, the dispersed analysts’ forecasts might constitute another source of uncertainty. In this study, the Uncertainty (contingent liabilities) of Uncertainty (dispersed anal...

As the financial market in China persistently develops, the market risk of commercial banks' trading account and its risk management have become a heated topic for both financial institutions and regulatory authority. Based on the fixed‐income securities trading's daily practices of commercial banks, this paper develops a framework of market risk m...

The real estate market has been booming in China for the past 10 years. Highly leveraged on banks' credit, it has aroused regulators' attention because of the potential catastrophic consequence, and it may produce on the whole financial system if the housing price boom bursts and massive defaults on mortgages occur. In this article, reverse stress...

Liquidity and order flows have been found to be major causes of extreme price movements (EPMs) in previous studies. However, few studies have clarified whether the impacts of these factors to EPMs are transient or permanent. In this paper, we represent the fluctuation of liquidity as a time series of price. The measurement of permanent price impact...

In the retail market, gathering marketing data is essential at different stages of advertisement and promotion; currently, this is achieved via online crowdsourcing. The jobs involving such tasks must be reasonably priced to attract part-time employees depending on the retail budget. Herein, a new approach is presented to enhance the task repricing...

In this paper, a new evaluation method for under-graduate education quality is proposed based on Artificial Intelligence Neural Network Back-Propagation (BP) algorithm and stress testing. Using this method, a publically available indicator pool is constructed, consisting of 19 variables in 4 dimensions such as Teaching Attitude, Teaching Content, T...

The authors propose an innovative Internet of Things (IoT) based E-commerce business model Cloud Laundry for mass scale laundry services. The model utilises big data analytics, intelligent logistics management, and machine learning techniques. Using GPS and real-time update of big data, it calculates the best transportation path and update and re-r...

This paper used the composite construction method proposed by Haugen (1999) and its application by Zhao and Wang (2010) for the Chinese stock market. Utilizing the Shanghai A-share market stocks data, this paper first selected the shares listed on the Shanghai Stock Exchange during January 1, 1997 to December 31, 2017. A portfolio was then built ac...

In this study, Big Data Analytics has been applied to implement smart manufacturing services performed by local commercial laundry Small and Medium Sized Enterprises (SMEs), which, to be specific, is called Smart Laundry Services (SLSs). This laundry service first uses traffic big data inputs from the City Traffic monitoring Server and abstract pat...

The traditional loans pricing methods are usually based on risk measures of individual loan’s characteristics without considering the correlation between the defaults of different loans and the contribution of individual loans to the entire loan portfolio. In this study, using account-level loans data of 2010-2016 abstracted from 2 databases kindly...

This research presents the technique architectures concepts and business model analyses for an innovative intelligent production model of facial masks, which consists of three modules: in-shop service, intelligent logistics, and smart manufacturing. The in-shop service module uses artificial intelligence to provide customers with quality experience...

Non-tariff measures (NTMs) such as technical barriers to trade (TBT) and sanitary and phytosanitary measures (SPMs) have become new trade barriers, which is contrary to these measures’ original intention to correct market failure and adverse selection of free markets and to protect the people, animals, plants and the environment in importing countr...

In this study, empirical evidence is presented to explain the momentum reversal phenomenon in the Chinese stock market in terms of the manipulation of institutional information. On the institutional “sell” side, we demonstrate that institutional traders send manipulated information to the market using a large volume of buy orders in order to boost...

One big problem with stress testing used by banks, regulators, and international financial organization is that the test does not predict occurrence probabilities of certain pre-specified stress scenarios and their consequent loss to be expected, which is, however, the real purpose of stress testing in the first place. As a result, institutes lack...

This study evaluates housing price control policies in China between 2006 and 2016. A panel regression is employed to diagnose the explicit effects of these policies on housing supply and demand, followed by a nonstationary Markov model and t-copula to assess the policy sensitivity of the real-estate sector and the banking sector. This paper presen...

In this study, a non-stationary Markov chain model and a vector autoregressive moving average with exogenous variables coupled with a logistic function (VARMAX-L) are used to analyze and predict the stability of a retail mortgage portfolio, based on the stress test framework. The method introduced in this paper can be used to forecast the transitio...

The relationship between government deficit spending and the growth domestic product is of extreme importance for economic policy making, especially in times of economic downturns as has been experienced in the US and around the world in recent years. The literature is mixed on this issue. There are studies arguing that deficit spending has an adve...

Regional banks usually issue financial credit products such as mortgages and creditcards to the same group of local residents. As a result, the health correlation analysis for thosedifferent credit products is necessary both for more accurate default prediction and credit policyestablishment. The goal of this study is to present a high-order multiv...

The health index of a mortgage loan portfolio may be viewed as a measure of the performance associated with that portfolio. Models to measure and predict the behavior of the health index of a mortgage portfolio over time are useful for the management of a bank in its decision making. In a previous study by the authors, a Markov chain model was used...

In this study, real-life retail mortgage loan data from a Chinese national commercial bank is used to generate the projected distribution over a set of predefined mortgage states or categories. Non-stationary Markov chain transition probabilities between these states are calculated using loan data from 57 consecutive months. In order to validate th...

This paper provides an indexing procedure for a mortgage loan health status by means of a finite Markov chain approach, which converts the loan health abstract idea into a workable number system. This method could be easily extended to other banking products as well. A regression method is used to analyze the local macroeconomic factors' effect on...

In this study, a discrete time Markov chain model is developed for modeling the duration of retail loans with prepayment, past due, and default states. Prepayment and past due states describe the payment status of a loan. The default state is defined as charge-off on the loan due to bankruptcy, death, or other causes..A bank could use this model to...