检索结果-内蒙古大学图书馆

29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)

作者： Awadelkarim, Amel Seshadri, Arjun Ashlagi, Itai Lo, Irene Ugander, Johan Stanford Univ Stanford CA 94305 USA Amazon San Francisco CA USA

ISBN: (纸本)9798400701030

School choice mechanism designers use discrete choice models to understand and predict families' preferences. The most widely-used choice model, the multinomial logit (MNL), is linear in school and/or household attributes. While the model is simple and interpretable, it assumes the ranked preference lists arise from a choice process that is uniform throughout the ranking, from top to bottom. In this work, we introduce two strategies for rank-heterogeneous choice modeling tailored for school choice. First, we adapt a context-dependent random utility model (CDM), considering down-rank choices as occurring in the context of earlier up-rank choices. Second, we consider stratifying the choice modeling by rank, regularizing rank-adjacent models towards one another when appropriate. Using data on household preferences from the San Francisco Unified School District (SFUSD) across multiple years, we show that the contextual models considerably improve our out-of-sample evaluation metrics across all rank positions over the non-contextual models in the literature. Meanwhile, stratifying the model by rank can yield more accurate first-choice predictions while down-rank predictions are relatively unimproved. These models provide performance upgrades that school choice researchers can adopt to improve predictions and counterfactual analyses.

关键词： school choice discrete choice preference modeling ranking models

来源：评论

学校读者我要写书评

暂无评论

The use of multi-criteria decision-making methods in project portfolio selection: a literature review and future research directions

引用

ANNALS OF OPERATIONS RESEARCH 2024年第1-3期332卷 807-830页

作者： Kandakoglu, M. Walther, G. Ben Amor, S. Rhein Westfal TH Aachen Chair Operat Management Aachen Germany Univ Ottawa Telfer Sch Management Ottawa ON Canada

In most project portfolio selection (PPS) situations, the presence of multiple attributes and decision-maker preference is inevitable. As Multi-criteria Decision Analysis (MCDA) methods provide a framework well-suited to deal with these challenges in PPS problems, the use of MCDA methods in real-life PPS problems has increased in recent years. This paper provides a comprehensive literature review of the use of different MCDA methods and their individual or combined utilization with other modeling techniques to support PPS problems. First, we summarize how MCDA methods are used in different modeling approaches. Second, we examine the mathematical models that are generally used to combine MCDA with mathematical programming techniques to solve PPS problems with resource constraints. Third, we present the drawbacks of combined utilization and discuss recent advances. Finally, we visualize the summary of the reviewed papers as a decision tree to assist researchers and practitioners in the use of MCDA methods in a specific PPS context and propose some future research directions.

关键词： Multi-criteria decision analysis Integer programming Project portfolio selection preference modeling Alternative solutions

来源：评论

学校读者我要写书评

暂无评论

Interactive Evolutionary Multiobjective Optimization via Learning to Rank

引用

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION 2023年第4期27卷 749-763页

作者： Li, Ke Lai, Guiyu Yao, Xin Univ Elect Sci & Technol China Coll Comp Sci & Engn Chengdu 611731 Peoples R China Univ Exeter Dept Comp Sci NorthPark Rd Exeter EX4 4QF England Southern Univ Sci & Technol Dept Comp Sci & Engn Guangdong Prov Key Lab Brain Inspired Intelligent Shenzhen 518055 Peoples R China

In practical multicriterion decision making, it is cumbersome if a decision maker (DM) is asked to choose among a set of tradeoff alternatives covering the whole Pareto-optimal front. This is a paradox in conventional evolutionary multiobjective optimization (EMO) that always aim to achieve a well balance between convergence and diversity. In essence, the ultimate goal of multiobjective optimization is to help a DM identify solution(s) of interest (SOI) achieving satisfactory tradeoffs among multiple conflicting criteria. Bearing this in mind, this article develops a framework for designing preference-based EMO algorithms to find SOI in an interactive manner. Its core idea is to involve human in the loop of EMO. After every several iterations, the DM is invited to elicit her feedback with regard to a couple of incumbent candidates. By collecting such information, her preference is progressively learned by a learning-to-rank neural network and then applied to guide the baseline EMO algorithm. Note that this framework is so general that any existing EMO algorithm can be applied in a plug-in manner. Experiments on 48 benchmark test problems with up to ten objectives and a real-world multiobjective robot control problem fully demonstrate the effectiveness of our proposed algorithms for finding SOI.

关键词： Evolutionary multiobjective optimization (EMO) gradient descent learning to rank (LTR) preference modeling

来源：评论

学校读者我要写书评

暂无评论

Separating and Learning Latent Confounders to Enhancing User preferences modeling 29th

Separating and Learning Latent Confounders to Enhancing User...

引用

29th International Conference on Database Systems for Advanced Applications (DASFAA)

作者： Xu, Hangtong Xu, Yuanbo Yang, Yongjia Jilin Univ Coll Comp Sci & Technol MIC Lab Changchun Peoples R China

ISBN: (纸本)9789819755547;9789819755554

Recommender models aim to capture user preferences from historical feedback and then predict user-specific feedback on candidate items. However, the presence of various unmeasured confounders causes deviations between the user preferences in the historical feedback and the true preferences, resulting in models not meeting their expected performance. Existing debias models either (1) specific to solving one particular bias or (2) directly obtain auxiliary information from user historical feedback, which cannot identify whether the learned preferences are true user preferences or mixed with unmeasured confounders. Moreover, we find that the former recommender system is not only a successor to unmeasured confounders but also acts as an unmeasured confounder affecting user preference modeling, which has always been neglected in previous studies. To this end, we incorporate the effect of the former recommender system and treat it as a proxy for all unmeasured confounders. We propose a novel framework, Separating and Learning Latent Confounders For Recommendation (SLFR), which obtains the representation of unmeasured confounders to identify the counterfactual feedback by disentangling user preferences and unmeasured confounders, then guides the target model to capture the true preferences of users. Extensive experiments in five real-world datasets validate the advantages of our method.

关键词： Recommender system Debiasing Causal inference preference modeling

来源：评论

学校读者我要写书评

暂无评论

Cluster analysis for ethical portfolio optimization problem using fuzzy chance constrained programming

引用

ENVIRONMENTAL ECONOMICS AND POLICY STUDIES 2024年 1-22页

作者： Messaoudi, Laila Higher Inst Management Gabes Res Unit 3E Gabes Tunisia

Choosing the greatest investment possibilities to maximize the value of one's stock investment has always been one of the primary concerns of investors. However, issues like human rights, and business ethics, are at the forefront of the public and political conversation in today's world of globalization and interdependence. Many financial experts, policymakers, and economic and social researchers view Islamic finance as a potential solution to prevent future crises. Consequently, there is a need for new models to facilitate this investment approach. In this study, we propose a new hybrid approach to portfolio selection which combines multiple methodologies like investor topology, cluster analysis, preference modeling and fuzzy multi-objective programming strategy. The proposed model is applied on 9 Tunisian mutual funds including conventional and ethical/Islamic funds in Tunisian financial market. The findings reveal that higher expected losses and greater proportions of ethical or Islamic stocks in a portfolio translate into better portfolio performance as measured by the Sharpe ratio. These findings confirm our hypothesis that ethical investments should be taken into account when developing investment strategies for conventional investors.

关键词： Cluster analysis preference modeling Fuzzy multi-objective programming Ethical investment Islamic finance

来源：评论

学校读者我要写书评

暂无评论

Explanation of Deep Learning Models via Logic Rules Enhanced by Embeddings Analysis, and Probabilistic Models 6th

Explanation of Deep Learning Models via Logic Rules Enhanced...

引用

6th International Workshop on Explainable and Transparent AI and Multi-Agent Systems (EXTRAAMAS)

作者： Contreras, Victor Schumacher, Michael Calvaresi, Davide Univ Appl Sci Western Switzerland HES SO Delemont Switzerland

ISBN: (纸本)9783031700736;9783031700743

Deep Learning (DL) models are increasingly dealing with heterogeneous data (i.e., a mix of structured and unstructured data), calling for adequate eXplainable Artificial Intelligence (XAI) methods. Nevertheless, only some of the existing techniques consider the uncertainty inherent to the data. To this end, this study proposes a pipeline to explain heterogeneous data-based DL models by combining embedding analysis, rule extraction methods, and probabilistic models. The proposed pipeline has been tested using synthetic data (multi-individual food items tracking). This study has achieved (i) inference enhancement through probabilistic and evidential reasoning, (ii) generation of logical explanations based on extracted rules and predictions, and (iii) integration of textual data into the explanation pipeline through embedding analysis.

关键词： XAI Deep learning Uncertainty reasoning Rule extraction preference modeling Heterogeneous data processing

来源：评论

学校读者我要写书评

暂无评论

Ranking Potential Investors Using the FITradeoff Method and Value Focused Thinking in a Group Decision Problem 23rd

Ranking Potential Investors Using the FITradeoff Method and ...

引用

23rd International Conference on Group Decision and Negotiation (GDN)

作者： da Silva, Geyse Maia Frej, Eduarda Asfora de Almeida, Adiel Teixeira Univ Fed Pernambuco UFPE CDSID Ctr Decis Syst & Informat Dev Ave Acad Helio Ramos S-N BR-50740530 Recife PE Brazil

ISBN: (纸本)9783031337796;9783031337802

This work aims to address a problem of attracting companies for direct investments in the state of Pernambuco, Brazil, with the purpose to aid the Economic Development Agency of Pernambuco (ADEPE) to rank the potential investors. Considering different points of view of multiple stakeholders of ADEPE, the Value-Focused Thinking (VFT) and FITradeoff (Flexible and Interactive Tradeoff) techniques are applied in the construction of the multicriteria decision model. The problem structuring provides a better understanding of an investor's decision-making process and leads to a better pitch to persuade them to invest in Pernambuco. Furthermore, the structured problem can be analyzed by a quantitative method aiming to rank the best alternatives that could match with the proposal of the Pernambuco state as a win-win investment movement. For that, the multicriteria decision model is built based on the VFT approach and the FITradeoff method. A set of 25 alternatives were defined and evaluated with respect to six criteria. Throughout the process, the preference modeling is performed in an interactive and flexible way where the decision makers (DMs) can switch between elicitation by decomposition to holistic evaluations.

关键词： Value-Focused Thinking (VFT) Multicriteria Group Decision Making (MCGDM) preference modeling FITradeoff method

来源：评论

学校读者我要写书评

暂无评论

Utility with fuzzy numbers

引用

FUZZY SETS AND SYSTEMS 2022年 434卷 88-97页

作者： Prati, Nando Univ Udine Dipartimento Sci Econ & Stat Via Tomadini 30-A I-33100 Udine Italy

In this paper, we introduce crisp utility functions with range in the class of fuzzy numbers. These utility functions can be employed to prove a generalization of the classical result of Cantor using partially ordered sets as domain of the utility functions. In particular, for every partially ordered countable set, we prove that it can be represented by an order preserving function (utility). (c) 2021 Elsevier B.V. All rights reserved.

关键词： Fuzzy numbers Economics Utility Order isomorphism preference modeling

来源：评论

学校读者我要写书评

暂无评论

Exploring the Mobile Usability of Argumentative Dialogue Systems for Opinion Building 4th

Exploring the Mobile Usability of Argumentative Dialogue Sys...

引用

4th International Conference on Design, Operation and Evaluation of Mobile Communications (MOBILE) Held as Part of the 25th International Conference on Human-Computer Interaction (HCII)

作者： Aicher, Annalena Hillmann, Stefan Moeller, Sebastian Minker, Wolfgang Ultes, Stefan Ulm Univ Inst Commun Engn Albert Einstein Allee 43 D-89081 Ulm Germany TU Berlin Qual & Usabil Lab Ernst Reuter Pl 7 D-10587 Berlin Germany Univ Bamberg Language Generat & Dialogue Syst Weberei 5 D-96047 Bamberg Germany

ISBN: (纸本)9783031359200;9783031359217

Nowadays speech-driven interfaces such as mobile digital assistants and chatbots can support collaborative information seeking and are becoming increasingly commonplace. Especially, mobile dialogue assistants offer innovative approaches to deliver and access information and thus, display a promising approach to assist humans in their opinion building process. Still, due to the complexity of argumentative tasks mobile argumentative speech interfaces are still very scarce. Hence, the effect of such interfaces on a user's opinion building process is quite unexplored. In this paper, we investigate the influence of such interfaces on the interest and opinion building process of users. Both categories Therefore we introduce two (I/O) modalities (menu/speech) of the argumentative dialog system (ADS) BEA ("Building Engaging Argumentation" [2]) which enables the user to scrutinize arguments on both sides of a controversial topic. In particular, we reflect on the influence and advantages of a spoken hands-free versus a clickable drop-down menu-based ADS with regard to "mobile" dialog systems use cases. Therefore the users' expectations and experiences in a self-assessment questionnaire are evaluated and discussed in comparison to our user interest and opinion model.

关键词： preference modeling Interest modeling Human-Computer Interaction Spoken Dialogue Systems Cooperative Argumentative Dialoguec Systems

来源：评论

学校读者我要写书评

暂无评论

A Temporal-Context-Aware Approach for Individual Human Mobility Inference Based on Sparse Trajectory Data 6th

A Temporal-Context-Aware Approach for Individual Human Mobil...

引用

6th Asia Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data (APWeb-WAIM)

作者： Xu, Shuai Guan, Donghai Ma, Zhuo Meng, Qing Nanjing Univ Aeronaut & Astronaut Nanjing Peoples R China Southeast Univ Key Lab Comp Network & Informat Integrat Minist Educ Nanjing Peoples R China Jiangsu Police Inst Nanjing Peoples R China Singapore Univ Technol & Design Singapore Singapore

ISBN: (纸本)9783031251573;9783031251580

Inferring individual human mobility at a given time is not only beneficial for personalized location-based services, but also crucial for trajectory tracking of the confirmed cases in the context of the COVID-19 pandemic. However, individual generated trajectory data using mobile Apps is characterized by implicit feedback, which means only a few individual-location interactions can be observed. Existing studies based on such sparse trajectory data are not sufficient to infer individual's missing mobility in his/her historical trajectory and further predict individual's future mobility given a specific time. To address this concern, in this paper, we propose a temporal-context-aware approach that incorporates multiple factors to model the time sensitive individual-location interactions in a bottom-up way. Based on the idea of feature fusion, the driving effect of heterogeneous information such as time, space, category and sentiment on individual's mobile behavior is gradually strengthened, so that the temporal context when a check-in occurs can be accurately depicted. We leverage Bayesian Personalized Ranking (BPR) to optimize the model, where a novel negative sampling method is employed to alleviate data sparseness. Based on three real-world datasets, we evaluate the proposed approach with regard to two different tasks, namely, missing mobility inference and future mobility prediction at a given time. The empirical results encouragingly demonstrate that our approach outperforms multiple baselines in terms of two evaluation metrics, i.e., accuracy and average percentile rank.

关键词： Mobility inference preference modeling Feature fusion Trajectory mining Context awareness

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：