Iterative Hierarchy and Ranking Process (IHRP): A Novel Effective Hierarchy Method for Densely Connected Systems and Case Study in Student Performance Assessment

• URL: http://arxiv.org/abs/2306.10409v2
• Date: Sat, 3 Feb 2024 20:10:54 GMT
• Title: Iterative Hierarchy and Ranking Process (IHRP): A Novel Effective Hierarchy Method for Densely Connected Systems and Case Study in Student Performance Assessment
• Authors: Suvojit Dhara and Adrijit Goswami
• Abstract summary: Interpretive structural modeling (ISM) is a widely used hierarchy-building method that mines factor inter-influences based on expert opinions. This paper discusses one of the main drawbacks of the conventional ISM method in systems where the factors are densely interrelated. We propose a novel iterative hierarchy-building technique, called 'Iterative Hierarchy and Ranking Process'(IHRP) which performs effectively in such dense systems.
• Score: 1.6317061277457001
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In real-life decision-making problems, determining the influences of the factors on the decision attribute is one of the primary tasks. To affect the decision attribute most, finding a proper hierarchy among the factors and determining their importance values in the system becomes quite important. Interpretive structural modeling (ISM) is a widely used hierarchy-building method that mines factor inter-influences based on expert opinions. This paper discusses one of the main drawbacks of the conventional ISM method in systems where the factors are densely interrelated. We refer to such systems as "dense systems". We propose a novel iterative hierarchy-building technique, called 'Iterative Hierarchy and Ranking Process'(IHRP) which performs effectively in such dense systems. To take the vagueness of the expert opinions into account, intuitionistic fuzzy linguistics has been used in the research work. In this paper, we propose a two-stage calculation of the relative importance of the factors in the system based on their hierarchical positions and rank the factors accordingly. We have performed a case study on student performance assessment by taking up novel Indian high-school administrative factors' data collected by surveying the experts in this field. A comparative study has been conducted in terms of the correlation of the factor ranking achieved by the proposed method and conventional ISM method with that of standard outranking methods like TOPSIS, and VIKOR. Our proposed IHRP framework achieves an 85-95% correlation compared to a 50-60% correlation for the conventional ISM method. This proves the effectiveness of the proposed method in determining a better hierarchy than the conventional method, especially in dense systems.

Related papers

• Hierarchical Reinforcement Learning for Temporal Abstraction of Listwise Recommendation [51.06031200728449]
  We propose a novel framework called mccHRL to provide different levels of temporal abstraction on listwise recommendation. Within the hierarchical framework, the high-level agent studies the evolution of user perception, while the low-level agent produces the item selection policy. Results observe significant performance improvement by our method, compared with several well-known baselines.
  arXiv  Detail & Related papers  (2024-09-11T17:01:06Z)
• Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis [16.0130560365211]
  This study provides a benchmark framework for Source-Free Unsupervised Domain Adaptation (SF-UDA) in image classification. The study empirically examines a diverse set of SF-UDA techniques, assessing their consistency across datasets. It exhaustively evaluates pre-training datasets and strategies, particularly focusing on both supervised and self-supervised methods.
  arXiv  Detail & Related papers  (2024-02-25T13:37:36Z)
• Performance Improvement in Multi-class Classification via Automated Hierarchy Generation and Exploitation through Extended LCPN Schemes [0.0]
  This study explores the performance of hierarchical classification (HC) through a comprehensive analysis. Two novel hierarchy exploitation schemes, LCPN+ and LCPN+F, have been introduced and evaluated. The findings reveal the consistent superiority of LCPN+F, which outperforms other schemes across various datasets and scenarios.
  arXiv  Detail & Related papers  (2023-10-31T17:11:29Z)
• Analyzing Different Expert-Opined Strategies to Enhance the Effect on the Goal of a Multi-Attribute Decision-Making System Using a Concept of Effort Propagation and Application in Enhancement of High School Students' Performance [0.0]
  This paper proposes two such strategies, namely parallel and hierarchical effort assignment, and propagation strategies. The strategies are analyzed for a real-life case study regarding Indian high school administrative factors that play an important role in enhancing students' performance.
  arXiv  Detail & Related papers  (2023-07-05T12:53:40Z)
• Better Understanding Differences in Attribution Methods via Systematic Evaluations [57.35035463793008]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods over a wide range of models.
  arXiv  Detail & Related papers  (2023-03-21T14:24:58Z)
• Vote'n'Rank: Revision of Benchmarking with Social Choice Theory [7.224599819499157]
  This paper proposes Vote'n'Rank, a framework for ranking systems in multi-task benchmarks under the principles of the social choice theory. We demonstrate that our approach can be efficiently utilised to draw new insights on benchmarking in several ML sub-fields.
  arXiv  Detail & Related papers  (2022-10-11T20:19:11Z)
• Towards Better Understanding Attribution Methods [77.1487219861185]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We also propose a post-processing smoothing step that significantly improves the performance of some attribution methods.
  arXiv  Detail & Related papers  (2022-05-20T20:50:17Z)
• Confounder Identification-free Causal Visual Feature Learning [84.28462256571822]
  We propose a novel Confounder Identification-free Causal Visual Feature Learning (CICF) method, which obviates the need for identifying confounders. CICF models the interventions among different samples based on front-door criterion, and then approximates the global-scope intervening effect upon the instance-level interventions. We uncover the relation between CICF and the popular meta-learning strategy MAML, and provide an interpretation of why MAML works from the theoretical perspective.
  arXiv  Detail & Related papers  (2021-11-26T10:57:47Z)
• Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach [12.468550800027808]
  In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted. In this paper, a novel pre-ranking approach is proposed which supports complicated models with interaction-focused architecture. It achieves a better tradeoff between effectiveness and efficiency by utilizing the proposed learnable Feature Selection method.
  arXiv  Detail & Related papers  (2021-05-17T09:48:15Z)
• Leveraging Expert Consistency to Improve Algorithmic Decision Support [62.61153549123407]
  We explore the use of historical expert decisions as a rich source of information that can be combined with observed outcomes to narrow the construct gap. We propose an influence function-based methodology to estimate expert consistency indirectly when each case in the data is assessed by a single expert. Our empirical evaluation, using simulations in a clinical setting and real-world data from the child welfare domain, indicates that the proposed approach successfully narrows the construct gap.
  arXiv  Detail & Related papers  (2021-01-24T05:40:29Z)
• Deep Learning feature selection to unhide demographic recommender systems factors [63.732639864601914]
  The matrix factorization model generates factors which do not incorporate semantic knowledge. DeepUnHide is able to extract demographic information from the users and items factors in collaborative filtering recommender systems.
  arXiv  Detail & Related papers  (2020-06-17T17:36:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.