Browsing by Author "Ma R"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    A label noise filtering and label missing supplement framework based on game theory
    (Elsevier B.V. on behalf of KeAi Communications Co Ltd for the Chongqing University of Posts and Telecommunications, 2023-08-31) Liu Y; Yao R; Jia S; Wang F; Wang R; Ma R; Qi L
    Labeled data is widely used in various classification tasks. However, there is a huge challenge that labels are often added artificially. Wrong labels added by malicious users will affect the training effect of the model. The unreliability of labeled data has hindered the research. In order to solve the above problems, we propose a framework of Label Noise Filtering and Missing Label Supplement (LNFS). And we take location labels in Location-Based Social Networks (LBSN) as an example to implement our framework. For the problem of label noise filtering, we first use FastText to transform the restaurant's labels into vectors, and then based on the assumption that the label most similar to all other labels in the location is most representative. We use cosine similarity to judge and select the most representative label. For the problem of label missing, we use simple common word similarity to judge the similarity of users' comments, and then use the label of the similar restaurant to supplement the missing labels. To optimize the performance of the model, we introduce game theory into our model to simulate the game between the malicious users and the model to improve the reliability of the model. Finally, a case study is given to illustrate the effectiveness and reliability of LNFS.
  • Thumbnail Image
    Item
    Estimating Long-Term Expected Returns
    (Taylor and Francis Group, 2024-07-01) Ma R; Marshall BR; Nguyen NH; Visaltanachoti N
    Estimating long-term expected returns as accurately as possible is of critical importance. Researchers typically base their estimates on yield and growth, valuation, or a combined yield, growth, and valuation (“three-component”) framework. We run a horse race of the abilities of different frameworks and input proxies within each framework to estimate 10- and 20-year out-of-sample returns. The three-component model based on the TRCAPE valuation proxy outperforms estimates based on historical mean benchmark returns, with mean square error improvements exceeding 30%. Using this approach in asset allocation decisions results in an improvement in Sharpe ratios of more than 50%.
  • Thumbnail Image
    Item
    Insider trading and climate disasters
    (Elsevier Inc, 2024-09) Ma R; Marshall BR; Nguyen HT; Nguyen NH; Visaltanachoti N
    Climate disasters are increasing in frequency and severity. While a large body of research has shown that extreme climate affects various economic decisions, how climate events influence investment decisions remains largely under-investigated. This paper examines whether, and to what extent, climate disasters influence insider transactions, which are important investment decisions that attract increasing attention from both corporate management and policymakers. We find that the monthly value of insider trades increases markedly in firms headquartered in counties with a climate disaster. Climate-induced insider trading holds in general but is stronger when investors are distracted and less prevalent when insiders face higher litigation risk. Climate disasters trigger uncertainty about short-term firm fundamentals, and insiders benefit by selling prior to this being priced. Insiders living in disaster counties do not trade more than those in unaffected counties, which does not support a personal liquidity motivation. Our paper documents a new way through which climate impacts investor behavior and financial markets.
  • Thumbnail Image
    Item
    The impact of alcohol pricing policies on public health in Hong Kong, China: A modelling study.
    (Elsevier B.V., 2022-06-24) Ng CS; Au M; Ma R; Leung JYY; Quan J
    Background Contrary to most developed economies, Hong Kong has reduced and eliminated taxes on beer and wine over the last 15 years and observed increasing alcohol consumption. Methods We applied econometric epidemiological modelling to assess the impact of reverting ad valorem taxation to pre-2008 levels (20% on wine and 40% on beer) on consumption and health outcomes. We used 15 years of industry sales and pricing data (2004-2018) to derive 25 own-price and cross-price elasticity estimates. We applied risk functions from the World Health Organization 2018 Global Status Report to assess the impact on 25 alcohol-attributable conditions. Findings An estimated 616 deaths (91.3% in men) were attributable to alcohol in 2018. Raising taxes to pre-2008 levels is estimated to reduce consumption of pure alcohol consumption by 8.0%, 15.9%, and 31.1%; and reduce alcohol-attributable deaths by 11.6%, 21.8%, and 40.2% assuming 25%, 50% and 100% pass through rates of taxes to consumers. The largest projected decreases in alcohol-attributable mortality in absolute numbers are alcohol abuse, alcohol dependence, and alcoholic psychoses (wholly alcohol-attributable disorders). The largest absolute number of new alcohol-attributable cases in 2018 were hypertension, alcohol dependence and alcohol abuse; which are estimated to be reduced by 31.3%, 34.2%, and 34.3% respectively by raising taxes to pre-2008 levels. The alcohol-attributable health burden and absolute reductions in health harms are far greater in men. Interpretation Reversing the 2008 alcohol tax reductions is potentially effective in averting the alcohol-attributable health burden and thus mitigate against the avoidable harms of alcohol-related disease. Funding Health and Medical Research Fund, Food and Health Bureau of the Hong Kong SAR, China [03170067].