Online payment fraud:from anomaly detection to risk management

Online banking fraud occurs whenever a criminal can seize accounts and transfer funds from an individual’s online bank account.Successfully preventing this requires the detection of as many fraudsters as possible,without producing too many false alarms.This is a challenge for machine learning owing to the extremely imbalanced data and complexity of fraud.In addition,classical machine learning methods must be extended,minimizing expected financial losses.Finally,fraud can only be combated systematically and economically if the risks and costs in payment channels are known.We define three models that overcome these challenges:machine learning-based fraud detection,economic optimization of machine learning results,and a risk model to predict the risk of fraud while considering countermeasures.The models were tested utilizing real data.Our machine learning model alone reduces the expected and unexpected losses in the three aggregated payment channels by 15%compared to a benchmark consisting of static if-then rules.Optimizing the machine-learning model further reduces the expected losses by 52%.These results hold with a low false positive rate of 0.4%.Thus,the risk framework of the three models is viable from a business and risk perspective.

INTEGRATED RISK ASSESSMENT OF MAJOR METEOROLOGICAL DISASTERS WITH PAPRIKA PEPPER IN HAINAN PROVINCE

Paprika pepper, as one of the main vegetable crops, is originated in the tropics and now widely planted in the world for its dietary therapy and medicinal functions. For its typical physiological properties referring to low tolerances to flood, drought and cold, paprika pepper often suffers from one or several disasters during its growing period,especially under tropical climate. Paprika pepper in Hainan, as a typical region of tropical climate in China, sustains flood, chilling and drought disaster risks induced by varied weather systems. This study was to develop and employ appropriate indices to assess hazard, sensitivity, vulnerability and prevention capability for major disasters during paprika pepper growth period, using long-term meteorological data from 1998 to 2011, actual disasters record from 1999 to 2011, production and socioeconomic statistics from 2002 to 2011 at 18 weather stations. Based on the Analytic Hierarchy Process and Entropy method, the combined weight was given to each disaster factor, thus an integrated disaster risk assessment model was developed and applied at regional level. High flood hazard mainly occurred in eastern Hainan, high chilling hazard in north and central mountain areas, and high drought hazard in the western part of Hainan. Drought and chilling sensitivity had a similar spatial distribution which decreased from central to coastal regions while flood sensitivity was the opposite. High vulnerability of the disasters mainly occurred in central regions,similar to low prevention capability. Eastern Hainan suffered from high integrated damage risk. The predicted damage occurrence showed a good agreement with the occurrence of actual disasters. We concluded that an integrated damage risk assessment model could provide a new tool to assess major meteorological disasters and help farmers and policy makers to alleviate the risks of major meteorological disasters for paprika pepper, which seems also suitable for other crops.

Disaster risk reduction in mountain areas: an initial overview on seeking pathways to global sustainability

As disasters cripple the world’s prospects for sustainable development, protecting the most vulnerable groups exposed to hazards is one of the main challenges facing humanity. Owing to the systemic nature of risk and the interactions and interdependencies between upland and lowland systems, healthy and productive mountain households and livelihoods are essential to global sustainability. This paper argues that, building on existing international frameworks, and integrated knowledge and praxis, the development of a global policy agenda should be established to build sustainable peace, sustainable security, and development.

Disaster risk reduction in mountain areas: a research overview

This paper gives an account of the diverse dimensions of research on disaster risk reduction in mountain regions derived from an open call of the Journal of Mountain Science that brought 21 contributions.This special issue includes topics as diverse as landslide dynamics and mechanisms,landslide inventories and landslide susceptibility models,insights to landslide hazards and disasters and mitigation measures,disaster response and disaster risk reduction.The overall structure of the paper takes the form of three sections.The first part begins by laying out the significance of disaster risk reduction in mountain areas,whereas the second one looks at the research insights on disaster risk reduction in mountains provided by the contributions comprised in the special volume.The final section identifies areas for further research.

Impact of Improving Design Factor over 0.72 on the Safety and Reliability of Gas Pipelines and Feasibility Justification

Many years experience of the operation of high stress (>72% specified minimum yield strength, SMYS) gas pipelines and statistical analysis results of pipeline incidents showed that the operating pipelines at stress levels over 72% SMYS have not presented problems in USA and Canada, and design factor does not control incidents or the safety of pipelines. Enhancing pipeline safety management level is most important for decreasing incident rate. The application history of higher design factors in the U.S and Canada was reviewed. And the effect of higher factors to the critical flaw size, puncture resistance, change of reliability with time, risk level and the arrest toughness requirements of pipeline were analyzed here. The comparison of pipeline failure rates and risk levels between two design factors (0.72 and 0.8) has shown that a change in design factor from 0.72 to 0.8 would bring little effect on failure rates and risk levels. On the basis of the analysis result, the application feasibility of design factor of 0.8 in China was discussed and the related suggestions were proposed. When an operator wishes to apply design factor 0.8 to gas pipeline, the following process is recommended: stress level of line pipe hydro test should be up to 100% SMYS, reliability and risk assessment at the design feasibility or conceptual stage should be conducted, Charpy impact energy should meet the need of pipeline crack arrest; and establish and execute risk based integrity management plan. The technology of pipeline steel metallurgy, line pipe fabrication and pipeline construction, and line pipe quality control level in China achieved tremendous progresses, and line pipe product standards and property indexes have come up to international advanced level. Furthermore, pipeline safety management has improved greatly in China. Consequently, the research for the feasibility of application of design factor of 0.8 in China has fundamental basis.

Integrated Disaster Risk Management(IDRM):Elements to Advance Its Study and Assessment

This study analyzed the international key literature on integrated disaster risk management(IDRM),considering it a dynamic sociocultural process subjected to the historical process of social formation,offering a closer look at the concept while exploring conceptual elements and ideas to advance IDRM in both national and international contexts.Methodologically,the study adopted a literature review strategy,following the Preferred Reporting Items for Systematic Reviews and MetaAnalyses(PRISMA)approach,combined with qualitative content analysis.This article examines the history of IDRM,discusses current challenges for implementation,looks at some experiences,and proposes avenues for further research.Some findings point out the lack of an overarching IDRM approach,which is characterized by a rather disperse set of ideas and experiences concerning what IDRM is and how it should be operationalized,thereby revealing the need for a more comprehensive theory and methodologies to further advance it.Other findings highlight that IDRM encompasses different kinds and levels of"integrations"that go from internal(that is,disaster risk reduction and management domains)to external(that is,all societal processes such as sustainable development),including temporal and spatial integrations.Hence,we are talking about a multidimensional integration of disaster risk management.In this regard,the article proposes four dimensions for integration:sectoral,spatial/hierarchical,temporal,and externally with other cross-cutting societal challenges,especially climate change and sustainable development.These dimensions cover 29 ideas for indicators or"proto-indicators"to guide the discussion,exploration,and analysis of IDRM in specific contexts.

Health and Risks:Integrating Health into Disaster Risk Reduction,Risk Communication,and Building Resilient Communities

In recent years,‘‘health’’has been recognized explicitly as both a determinant and an outcome of the human dimension of disaster risk reduction(DRR).Every disaster creates significant public health needs that can exceed local capacity to respond,resulting in excess mortality and morbidity.The European Union report on Science

Beyond the Expected-Residual Risk and Cases of Overload in the Context of Managing Alpine Natural Hazards

Structural protection measures are designed to protect the population and infrastructure against natural hazards up to a specific predefined protection goal.Extreme events with intensities that exceed the capacity of these protection structures are called“cases of overload”and are associated with“residual risks”that remain after the implementation of protection measures.In order to address residual risks and to reduce the damages from overload events,a combination of structural protection measures with additional,nonstructural measures is required.Based on data collected through a literature review,a questionnaire survey,expert interviews,and an expert workshop we highlight the status quo as well as key challenges of dealing with residual risks and cases of overload in Alpine countries in the context of geohydrological hazards and gravitational mass movements.We present a holistic conceptual framework that describes the relationships of residual risks,cases of overload,and protection goals in the context of both risk governance and integrated risk management.This framework is valuable for decision makers aiming at an improved management of natural hazards that takes adequate account of residual risk and cases of overload in Alpine countries and mountain areas worldwide.

Multi-Sectoral Reflections and Efforts in Strengthening Partnerships to Reduce Disaster Risk in Mexico:The First MuSe-IDRiM Conference

Notwithstanding the high societal impact of disasters in Mexico,there is a lack of integrated efforts to establish a sound policy for reducing disaster risk to counterbalance the existing concentrated endeavors in disaster management.In the face of such segmentation,the science and technology community has advocated for a change of perspective,from civil protection to integrated disaster risk managemcnt.The first Multi-Sectoral Conference towards Integrated Disaster Risk Management in Mexico:Building a National Public Policy(MuSe-IDRiM Conference)was held in Mexico City at National Autonomous University of Mexico,21-24 October 2019.In support of the implementation of the Sendai Framework for Disaster Risk Reduction 2015-2030,the conference aimed at enhancing the dialogue between the scienee and technology community,citizens,civil society organizations,private and public sectors,and the federtil,state,and municipal governments to foster the process of transforming the current National Civil Protection System into a national public policy oriented towards integrated disaster risk management(DRM).Barriers and challenges to the implementation of integrated DRM were identified.Implementation of integrated DRM challenges current socioeconomic structures and encourages all releva nt stakeholders to think,decide,and act from a different perspective and within and across spatial,temporal,jurisdictional,and institutional scales.Understanding disaster risk from an integrated approach,learning skills that authorities have not learned or used,and hence,strengthening disaster risk governance are prerequisites to effectively manage disaster risk.

Interaction between pollution and climate change augments ecological risk to a coastal ecosystem

Pollution and climate change are among the most challenging issues for countries with developing economies,but we know little about the ecological risks that result when these pressures occur together.We explored direct effects of,and interactions between,environmental pollution and climate change on ecosystem health in the Bohai Sea region of Northern China.We developed an integrated approach to assess ecological risks to this region under four scenarios of climate change.Although ecological risks to the system from pollution alone have been declining,interactions between pollution and climate change have enhanced ecological risks to this coastal/marine ecosystem.Our results suggest that current policies focused strictly on pollution control alone should be changed to take into account the interactive effects of climate change so as to better forecast and manage potential ecological risks.

Green Development and Integrated Risk Governance

The‘‘International Symposium on Integrated Governance of Large-scale Disaster and Economic Risks’’was held in Qianhai,Shenzhen,China on 13–14 May 2017.The Academy of Disaster Reduction and Emergency Management of Ministry of Civil Affairs and Ministry of Educa-

Deep Reinforcement Learning Based Decision‑Making Strategy of Autonomous Vehicle in Highway Uncertain Driving Environments

Uncertain environment on multi-lane highway,e.g.,the stochastic lane-change maneuver of surrounding vehicles,is a big challenge for achieving safe automated highway driving.To improve the driving safety,a heuristic reinforcement learning decision-making framework with integrated risk assessment is proposed.First,the framework includes a long short-term memory model to predict the trajectory of surrounding vehicles and a future integrated risk assessment model to estimate the possible driving risk.Second,a heuristic decaying state entropy deep reinforcement learning algorithm is introduced to address the exploration and exploitation dilemma of reinforcement learning.Finally,the framework also includes a rule-based vehicle decision model for interaction decision problems with surrounding vehicles.The proposed framework is validated in both low-density and high-density traffic scenarios.The results show that the traffic efficiency and vehicle safety are both improved compared to the common dueling double deep Q-Network method and rule-based method.