检索结果-内蒙古大学图书馆

4th International Conference on Process Mining (ICPM)

作者： Padella, Alessandro de Leoni, Massimiliano Dogan, Onur Galanti, Riccardo Univ Padua Padua Italy Izmir Bakiracy Univ Izmir Turkey IBM Corp Bologna Italy

ISBN: (数字)9798350397147

ISBN: (纸本)9798350397147

Process-aware Recommender systems (PAR systems) are information systems that aim to monitor process executions, predict their outcome, and recommend effective interventions to have better ends. Recent literature puts forward proposals of PAR systems that return valuable, practical recommendations. However, recommendations without sensible explanations prevent process owners from feeling engaged in the decision process or understanding why these interventions should be carried out. Therefore, the risk of process owners do not trust the PAR system and overlook these recommendations is high. This paper proposes a framework to accompany recommendations with sensible explanations based on the process behavior, the intrinsic characteristics, and the context in which the process is carried on. The paper illustrates the potential relevance of these explanations for process owners in two use cases.

关键词： Process Mining prescriptive analytics Recommender Systems Explainability Process Improvement

来源：评论

学校读者我要写书评

暂无评论

Human-Augmented prescriptive analytics With Interactive Multi-Objective Reinforcement Learning

引用

IEEE ACCESS 2021年 9卷 100677-100693页

作者： Lepenioti, Katerina Bousdekis, Alexandros Apostolou, Dimitris Mentzas, Gregoris Natl Tech Univ Athens NTUA Inst Commun & Comp Syst ICCS Informat Management Unit IMU Zografos 15780 Greece Univ Piraeus Dept Informat Piraeus 18534 Greece

The rise of Artificial Intelligence (AI) enables enterprises to manage large amounts of data in order to derive predictions about future performance and to gain meaningful insights. In this context, descriptive and predictive analytics has gained a significant research attention;however, prescriptive analytics has just started to emerge as the next step towards increasing data analytics maturity and leading to optimized decision making ahead of time. Although machine learning for decision making has been identified as one of the most important applications of AI, up to now, prescriptive analytics is mainly addressed with domain-specific optimization models. On the other hand, existing literature lacks generalized prescriptive analytics models capable of being dynamically adapted according to the human preferences. Reinforcement Learning, as the third machine learning paradigm alongside supervised learning and unsupervised learning, has the potential to deal with the dynamic, uncertain and time-variant environments, the huge states space of sequential decision making processes, as well as the incomplete knowledge. In this paper, we propose a human-augmented prescriptive analytics approach using Interactive Multi-Objective Reinforcement Learning (IMORL) in order to cope with the complexity of real-life environments and the need for optimized human-machine collaboration. The decision making process is modelled in a generalized way in order to assure scalability and applicability in a wide range of problems and applications. We deployed the proposed approach in a stock market case study in order to evaluate the proactive trading decisions that will lead to the maximum return and the minimum risk that the user's experience and the available data can yield in combination.

关键词： Decision making Reinforcement learning Artificial intelligence Business Task analysis Data analysis Complexity theory Big data data analytics human-augmented analytics machine learning prescriptive analytics reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A prescriptive analytics METHOD FOR COST REDUCTION IN CLINICAL DECISION MAKING

引用

MIS QUARTERLY 2021年第1期45卷 83-115页

作者： Fang, Xiao Gao, Yuanyuan Hu, Paul Jen-Hwa Univ Delaware Alfred Lerner Coll Business & Econ 357 Purnell Hall Newark DE 19716 USA Calif State Univ East Bay Coll Business & Econ 25800 Carlos Bee Blvd Hayward CA 94542 USA Univ Utah David Eccles Sch Business 1655 East Campus Ctr Dr Salt Lake City UT 84112 USA

Containing skyrocketing health care costs is imperative. Toward that end, prescriptive analytics that analyzes health care data to recommend optimal decisions is both relevant and crucial. We develop a novel prescriptive analytics method to improve the cost effectiveness in clinical decision making (CDM), a critical health care dimension that can greatly benefit from analytics. Effective prescriptive analytics for CDM has to address its probabilistic, cost-sensitive, and investment-related characteristics simultaneously. Unlike existing methods that often overlook the investment-related characteristic, the proposed method accounts for all of these characteristics. Specifically, our method considers two sets of costs associated with clinical decisions-before and after an investment-in combination with the probabilities of cost changes due to the investment. In contrast, prevalent methods only emphasize one set of costs, before an investment. Furthermore, the proposed method involves both clinical and investment decisions, whereas existing methods ignore investment decisions. Empirical evaluations with two real-world clinical data sets indicate that the proposed method consistently and significantly outperforms several salient methods from previous research, thereby demonstrating the value of addressing the investment-related characteristic in efforts to improve CDM.

关键词： Machine learning cost-sensitive learning prescriptive analytics health care clinical decision making

来源：评论

学校读者我要写书评

暂无评论

A prescriptive analytics FRAMEWORK FOR OPTIMAL POLICY DEPLOYMENT USING HETEROGENEOUS TREATMENT EFFECTS

引用

MIS QUARTERLY 2021年第4期45卷 1807-1832页

作者： McFowland, Edward, III Gangarapu, Sandeep Bapna, Ravi Sun, Tianshu Univ Minnesota Carlson Sch Management Minneapolis MN 55455 USA Univ Southern Calif Marshall Sch Business Los Angeles CA 90007 USA

We define a prescriptive analytics framework that addresses the needs of a constrained decision-maker facing, ex ante, unknown costs and benefits of multiple policy levers. The framework is general in nature and can be deployed in any utility-maximizing context, public or private. It relies on randomized field experiments for causal inference, machine learning for estimating heterogeneous treatment effects, and on the optimization of an integer linear program for converting predictions into decisions. The net result is the discovery of individual-level targeting of policy interventions to maximize overall utility under a budget constraint. The framework is set in the context of the four pillars of analytics and is especially valuable for companies that already have an existing practice of running A/B tests. The key contribution of this work is to develop and operationalize a framework to exploit both within-and between-treatment arm heterogeneity in the utility response function in order to derive benefits from future (optimized) prescriptions. We demonstrate the value of this framework as compared to benchmark practices-i.e., the use of the average treatment effect, uplift modeling, as well as an extension to contextual bandits-in two different settings. Unlike these standard approaches, our framework is able to recognize, adapt to, and exploit the (potential) presence of different subpopulations that experience varying costs and benefits within a treatment arm while also exhibiting differential costs and benefits across treatment arms. As a result, we find a targeting strategy that produces an order of magnitude improvement in expected total utility for the case where significant within-and between-treatment arm heterogeneity exists.

关键词： prescriptive analytics heterogeneous treatment effects optimization observed utility rank condition (OUR) between-treatment heterogeneity

来源：评论

学校读者我要写书评

暂无评论

prescriptive analytics: Literature review and research challenges

引用

INTERNATIONAL JOURNAL OF INFORMATION MANAGEMENT 2020年 50卷 57-70页

作者： Lepenioti, Katerina Bousdekis, Alexandros Apostolou, Dimitris Mentzas, Gregoris Inst Commun & Comp Syst Informat Management Unit Athina Greece Univ Piraeus Dept Informat Piraeus Greece

Business analytics aims to enable organizations to make quicker, better, and more intelligent decisions with the aim to create business value. To date, the major focus in the academic and industrial realms is on descriptive and predictive analytics. Nevertheless, prescriptive analytics, which seeks to find the best course of action for the future, has been increasingly gathering the research interest. prescriptive analytics is often considered as the next step towards increasing data analytics maturity and leading to optimized decision making ahead of time for business performance improvement. This paper investigates the existing literature pertaining to prescriptive analytics and prominent methods for its implementation, provides clarity on the research field of prescriptive analytics, synthesizes the literature review in order to identify the existing research challenges, and outlines directions for future research.

关键词： analytics prescriptive analytics Business analytics Big data Literature review

来源：评论

学校读者我要写书评

暂无评论

Design decisions for integrating prescriptive analytics Use Cases into Smart Factories

引用

Procedia CIRP 2024年 128卷 424-429页

作者： Julian Weller Nico Migenda Sebastian von Enzberg Martin Kohlhase Wolfram Schenck Roman Dumitrescu Fraunhofer Institute for Mechatronic Systems Design Zukunftsmeile 1 33102 Paderborn Germany Center for Applied Data Science Gütersloh Faculty of Engineering and Mathematics Bielefeld University of Applied Sciences and Arts Schulstraße 10 33330 Gütersloh Germany Chair for Advanced Systems Engineering Heinz Nixdorf Institute Fürstenallee 11 33102 Paderborn Germany

The emerging trend of prescriptive analytics tries to prescribe actionable decisions. The goal is to help production experts in automating their decisions in the factory. Decision making processes in factories mostly rely on experts inside the company. Current trends such as demographic shifts and shortages of skilled personnel are challenging organizations to find ways to become less dependent on the ad hoc availability of expert knowledge through digitalization and data analytics. Existing data analytics approaches for smart factories usually focus on description, diagnosis, and prediction. An approach to differentiate between different application areas of prescriptive analytics in a smart factory is presented. Focus areas for a useful application and integration of prescriptive analytics are derived. Based on these applications, design principles are constructed. They help decision makers to select future lighthouse use cases for development and help smart factory advocates to strategically decide which prescriptive analytics approaches to highlight. The resulting design principles are based on a literature review and validated in a workshop with experts from research. Approaches are differentiated and key characteristics for future Use Case design decisions are derived.

关键词： prescriptive analytics Smart Factory Design methodology tools technologies

来源：评论

学校读者我要写书评

暂无评论

Adoption of prescriptive analytics for naval vessels risk-based maintenance: A conceptual framework

引用

OCEAN ENGINEERING 2023年第1期278卷

作者： Esa, Mohd Adha Mat Muhammad, Masdi Univ Teknol Petronas Fac Engn Mech Engn Dept Perak Malaysia

prescriptive analytics is a novel maintenance approach by recommending the maintainer, the right maintenance action at the right time through prioritization of maintenance based on the risk. It assists in improving the existing preventive maintenance approach by offering a dynamic maintenance plan based on risk or Risk-based Maintenance Scheduling. To date, there is no clear definition of Naval Vessels Risk-based Maintenance as well as its framework, and it has not been applied extensively in naval vessel maintenance application which is peculiar compared to its application in plant maintenance. This paper reviews Risk-based Maintenance application in industries in an approach to develop prescriptive analytics for a comprehensive and dynamic naval vessels Risk -based Maintenance decision-making framework. It aims to establish an optimal maintenance scheduling to improve naval vessels availability and reduce maintenance costs while meeting stakeholders' expectations. Objectives and considerations are also defined for peculiarities application of naval vessels. The framework is then evaluated to improve the effectiveness of the current Preventive Maintenance practice and the inconsistency of the existing maintenance decision-making model using the expert judgement in Reliability Centered Maintenance.

关键词： Naval maintenance prescriptive analytics Risk-based maintenance

来源：评论

学校读者我要写书评

暂无评论

DAYDREAMS - Development of prescriptive analytics based on Artificial Intelligence for Railways Intelligent Asset Management Systems

引用

Transportation Research Procedia 2023年 72卷 478-485页

作者： L Oneto M Anastasopoulos D Anguita I Baroni R Canepa C Dambra S Gogos W Jentner S Petralli University of Genoa 11A Via Opera Pia Genova 16145 Italy Institute of Accelerating Systems and Applications P.O. Box 17214 Athens 10024 Greece CEFRIEL 226 Viale Sarca Milan 20126 Italy RFI - Technical Department 6/5 Via Don Vincenzo Minetti Genova 16126 Italy ZenaByte 2 Via Cesarea Genova 16121 Italy UNIFE 221 Avenue Louise Brussels 1050 Belgium University of Konstanz 10 Universitätsstr. Konstanz 78464 Germany

DAYDREAMS, which started its activities in December 2020, is a Horizon2020 project within Shift2Rail's 3rd Innovation Programme (IP3). The project's overall objective is to advance - in line with Shift2Rail's vision (now called Europe's Rail Join Undertaking) - on the integration and use of data and artificial/human trustworthy intelligence, together with context-driven Human Machine Interface (HMI) for prescriptive Intelligent Asset Management Systems (IAMS) in railway.

关键词： Railway Asset Maintenance Artificial Intelligence prescriptive analytics Multi Objective Optimisation Context Driven Human Machine Interface

来源：评论

学校读者我要写书评

暂无评论

Fundamental challenge and solution methods in prescriptive analytics for freight transportation

引用

TRANSPORTATION RESEARCH PART E-LOGISTICS AND TRANSPORTATION REVIEW 2023年 169卷

作者： Wang, Shuaian Yan, Ran Hong Kong Polytech Univ Dept Logist & Maritime Studies Hung Hom Kowloon Hong Kong Peoples R China Nanyang Technol Univ Sch Civil & Environm Engn Singapore Singapore

prescriptive analytics, in which some parameters are predicted using statistical or machine learning models and then input into an optimization model, is often used to prescribe recom-mended solutions to freight transportation problems. The effectiveness of the optimal decision prescribed by prescriptive analytics is typically evaluated through a comparison with the results of the current decision model using predicted data. However, such comparisons are often flawed because of insufficient and uncertain data. We use four freight transport examples to illustrate this fundamental challenge in prescriptive analytics modeling. Furthermore, we propose three solu-tions to fully or partially overcome this challenge and fairly compare the optimal decisions generated by prescriptive analytics and the current approach. The three solutions involve using sufficient historical data, constructing new test sets, and generating synthetic data. We show how these solutions address the challenges in the four examples and are suitable for different problems considering data availability. The proposed solutions allow for a more comprehensive, accurate, and fair comparison of the optimal decisions to validate those generated by prescriptive analytics. This improves the effectiveness of the prescriptive analytics paradigm and can promote its application in freight transport and other disciplines.

关键词： prescriptive analytics Freight transportation Prediction Optimization Fundamental challenge

来源：评论

学校读者我要写书评

暂无评论

Data analytics based prescriptive analytics for Selection of Lean Manufacturing System 6

Data Analytics based Prescriptive Analytics for Selection of...

引用

6th International Conference on Inventive Computation Technologies (ICICT)

作者： Faisal, A. Mohammed Karthigeyan, L. Vels Inst Sci Technol & Adv Studies Sch Management Studies Chennai Tamil Nadu India

ISBN: (纸本)9781728185019

In data analytics, prescriptive analytics can be used to select the best solution based on effectiveness. Hence the simulation model is used as prescriptive analytics to select the best lean manufacturing system such as Kanban and CONstant Work In Process (CONWIP) based on the effectiveness. This article is to study the effectiveness of selecting the best lean manufacturing system. The simulation model of Kanban and CONWIP was analyzed based on factors such as Takt time, Pitch, and Production line length. The effectiveness of Kanban and CONWIP is studied based on the key performance indicators (KPIs) such as average throughput, average utilization, and average WIP. While implementing the CONWIP, both the average throughput and WIP increased but the average utilization decreased. However, when the Kanban system was implemented, the average throughput and WIP decreased and utilization increased. So, the CONWIP is selected as the best lean manufacturing system at the introductory stage of implementation.

关键词： data analytics prescriptive analytics simulation CONWIP kanban

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：