Results

Found 83 articles

Clear filters

A holistic approach to interpretability in financial lending: Models, visualizations, and summary-explanations
PDF
2022 | Decision Support Systems | Citations: 0
Authors: Chen, Chaofan; Lin, Kangcheng; Rudin, Cynthia; Shaposhnik, Yaron; Wang, Sijia; Wang, Tong

Abstract: A B S T R A C TLending decisions are usually made with proprietary models that ... Expand

Abstract: A B S T R A C TLending decisions are usually made with proprietary models that provide minimally acceptable explanations to users. In a future world without such secrecy, what decision support tools would one want to use for justified lending decisions? This question is timely, since the economy has dramatically shifted due to a pandemic, and a massive number of new loans will be necessary in the short term. We propose a framework for such decisions, including a globally interpretable machine learning model, an interactive visualization of it, and several types of summaries and explanations for any given decision. The machine learning model is a two-layer additive risk model, which resembles a two-layer neural network, but is decomposable into subscales. In this model, each node in the first (hidden) layer represents a meaningful subscale model, and all of the nonlinearities are transparent. Our online visualization tool allows exploration of this model, showing precisely how it came to its conclusion. We provide three types of explanations that are simpler than, but consistent with, the global model: case-based reasoning explanations that use neighboring past cases, a set of features that were the most important for the model's prediction, and summary-explanations that provide a customized sparse explanation for any particular lending decision made by the model. Our framework earned the FICO recognition award for the Explainable Machine Learning Challenge, which was the first public challenge in the domain of explainable machine learning. 1 Collapse

Semantic filters: theory of case-based reasoning

Topics: logistics management decision support system explainable artificial intelligence database system missing data

Methods: machine learning artificial neural network computational algorithm optimization model paired t-test

Theories: theory of case-based reasoning
Human-machine collaboration in online customer service – a long-term feedback-based approach
PDF
2021 | Electronic Markets | Citations: 0
Authors: Graef, Roland; Klier, Mathias; Kluge, Kilian; Zolitschka, Jan Felix

Abstract: The rising expectations of customers have considerably contributed to the need f ... Expand

Abstract: The rising expectations of customers have considerably contributed to the need for automated approaches supporting employees in online customer service. Since automated approaches still struggle to meet the challenge to fully grasp the semantics of texts, hybrid approaches combining the complementary strengths of human and artificial intelligence show great potential for assisting employees. While research in Case-Based Reasoning (CBR) already provides well-established approaches, they do not fully exploit the potential of CBR as hybrid intelligence. Against this background, we follow a design-oriented approach and develop an adapted textual CBR cycle that integrates employees’ feedback on semantic similarity, which is collected during the Reuse phase, into the Retrieve phase by means of long-term feedback methods from information retrieval. Using a real-world data set, we demonstrate the practical applicability and evaluate our approach regarding performance in online customer service. Our novel approach surpasses human-based, machine-based, and hybrid approaches in terms of effectiveness due to a refined retrieval of semantically similar customer problems. It is further favorable regarding efficiency, reducing the average time required to solve a customer problem. Collapse

Semantic filters: theory of case-based reasoning

Topics: customer service information retrieval Quora website artificial intelligence

Methods: literature study design science computational algorithm design process artificial neural network

Theories: theory of case-based reasoning
A Case-based Reasoning Approach for Supporting Facilitation in Online Discussions
PDF
2021 | Group Decision and Negotiation | Citations: 0
Authors: Gu, Wen; Moustafa, Ahmed; Ito, Takayuki; Zhang, Minjie; Yang, Chunsheng

Abstract: In online discussion platforms, participants gather to discuss the effective app ... Expand

Abstract: In online discussion platforms, participants gather to discuss the effective approaches to solve the common issues they face. To facilitate these discussions proceeding smoothly and reaching consensus efficiently, human facilitators are introduced into these discussions. However, human facilitator-related problems such as human bias and scalability arise with the increasing sophistication of these online discussions. As a result, it becomes critical to find approaches that support facilitation in these online discussions. Towards this end, we propose a novel case-based reasoning framework to support online discussion facilitation. In the proposed framework (CBR), each discussion thread is styled using an issue-based information system (IBIS), where complex problems are modeled as argumentation processes among several stack holders. Upon identifying a new discussion case, facilitation suggestions are generated by retrieving the most similar facilitated case from the discussion case base. For the sake of experimental evaluation, we build an online facilitation dataset that contains the facilitation information from annotated real-world discussion data. The experimental results show the validity of the generated facilitation suggestions. Collapse

Semantic filters: theory of case-based reasoning

Topics: evaluation criteria decision making

Methods: computational algorithm experiment machine learning case study

Theories: theory of case-based reasoning
A dynamic classification unit for online segmentation of big data via small data buffers
PDF
2020 | Decision Support Systems | Citations: 0
Authors: Khalemsky, Anna; Gelbard, Roy

Abstract: In many segmentation processes, we assign new cases according to a model that wa ... Expand

Abstract: In many segmentation processes, we assign new cases according to a model that was built on the basis of past cases. As long as the new cases are “similar enough” to the past cases, segmentation proceeds normally. However, when a new case is substantially different from the known cases, a reexamination of the previously created segments is required. The reexamination may result in the creation of new segments or in the updating of the existing ones. In this paper, we assume that in big and dynamic data environments it is not possible to reexamine all past data and, therefore, we suggest using small groups of selected cases, stored in small data buffers, as an alternative to the collection of all past data. We present an incremental dynamic classifier that supports real-time unsupervised segmentation in big and dynamic data environments. In order to reduce the computational effort of unsupervised clustering in such environments, the suggested model performs calculations only on the relevant data buffers that store the relevant representative cases. In addition, the suggested model can serve as a dynamic classification unit (DCU) that can act as an autonomous agent, as well as collaborate with other DCUs. The evaluation is presented by comparing three approaches: static, dynamic, and incremental dynamic. Collapse

Semantic filters: theory of case-based reasoning

Topics: database system social media big data anonymity

Methods: experiment cluster analysis decision tree classification computational algorithm machine learning

Theories: theory of case-based reasoning
Using Analytic Hierarchy Process for COBIT 5 Process Prioritization

2018 | Americas Conference on Information Systems | Citations: 0
Authors: Almeida, Rafael

Abstract: COBIT 5 is often used as a reference framework by professionals looking for guid ... Expand

Abstract: COBIT 5 is often used as a reference framework by professionals looking for guidelines regarding Information Technology governance and management. One of the management tools provided by COBIT 5 is the Goals Cascade, which constitutes the core entry point for COBIT 5 process improvement. After the goals cascade run, for each stakeholder need that the stakeholder defines, several processes that support that need should be implemented. Notwithstanding, the goals cascade does not prioritize the processes that should be implemented first, and so, organizations are somehow at a crossroads - they know what to implement, but not where to start. Therefore, in this research, the authors propose to use the Analytical Hierarchy Process (AHP) to help organizations establish the priorities for the COBIT 5 improvement processes. The authors carried out a goals cascade run based on the COBIT 5 guide and then prioritized the selected processes using the AHP method. Collapse

Semantic filters: theory of case-based reasoning

Topics: COBIT business process improvement

Methods: trade-off analysis method design science analytic hierarchy process

Theories: theory of case-based reasoning fuzzy set theory multi-attribute utility theory
Advances in Databases and Information Systems
PDF
2018 | Information Systems Frontiers | Citations: 0
Authors: Bellatreche, Ladjel; Valduriez, Patrick; Morzy, Tadeusz

Abstract: ... Expand

Abstract: Collapse

Semantic filters: theory of case-based reasoning

Topics: database system extract transform load process knowledge representation user requirement

Methods: literature sample ontological modelling design artifact computational algorithm experiment

Theories: theory of case-based reasoning
ETL workflow reparation by means of case-based reasoning
PDF
2018 | Information Systems Frontiers | Citations: 0
Authors: Wojciechowski, Artur

Abstract: Data sources (DSs) being integrated in a data warehouse frequently change their ... Expand

Abstract: Data sources (DSs) being integrated in a data warehouse frequently change their structures/schemas. As a consequence, in many cases, an already deployed ETL workflow stops its execution, yielding errors. Since in big companies the number of ETL workflows may reach dozens of thousands and since structural changes of DSs are frequent, an automatic repair of an ETL workflow after such changes is of high practical importance. In our approach, we developed a framework, called E-ETL, for handling the evolution of an ETL layer. In the framework, an ETL workflow is semi-automatically or automatically (depending on a case) repaired as the result of structural changes in DSs, so that it works with the changed DSs. E-ETL supports two different repair methods, namely: (1) user defined rules, (2) and Case-Based Reasoning. In this paper, we present how Case-Based Reasoning may be applied to repairing ETL workflows. In particular, we contribute an algorithm for selecting the most suitable case for a given ETL evolution problem. The algorithm applies a technique for reducing cases in order to make them more universal and capable of solving more problems. The algorithm has been implemented in prototype E-ETL and evaluated experimentally. The obtained results are also discussed in this paper. Collapse

Semantic filters: theory of case-based reasoning

Topics: extract transform load process mobile application workstation database system application programming interface

Methods: computational algorithm experiment design artifact data modeling

Theories: theory of case-based reasoning
Product lifecycle management in knowledge intensive collaborative environments: An application to automotive industry
PDF
2017 | International Journal of Information Management | Citations: 1
Authors: Ferreira, Filipe; Faria, José; Azevedo, Américo; Marques, Ana Luisa

Abstract: Keywords:Hybrid process management Knowledge based engineering Collaborative en ... Expand

Abstract: Keywords:Hybrid process management Knowledge based engineering Collaborative engineering Product design and development Manufacturing planning a b s t r a c t Today, manufacturing is moving towards customer-driven and knowledge-based proactive production. Shorter product life cycles lead to increased complexity in areas such as product and process design, factory deployment and production operations. To handle this complexity, new knowledge-based methods and technologies are needed to model, simulate, optimize and monitor manufacturing systems. Product lifecycle management research tends to focus on situations that are responsive to formal analysis and modelling. However, in several domains such as knowledge intensive collaborative environments, it's not possible to model processes using formal notations. Knowledge based and collaborative process management involves a combination of structured and non-structured processes. Structured processes management can be reduced to a set of fully-defined rules leading to high efficiency but also low flexibility, whereas the management of non-structured processes is not prone to a full formalization. A combination of both structured and unstructured management approaches is required in order to achieve a successful trade-off between efficiency, flexibility and controllability. We call a process as semi-structured when it contains both structured and non-structured sub-processes leading to a flexible and efficient hybrid approach. Large enterprise information systems, impose structured and predictable workflows, while knowledge based collaborative processes are unpredictable to some extent, involving high amount of human-decision. Moreover, large enterprise information systems are not able to manage the daily ad hoc communication inherent to the knowledge-based process itself. This paper introduces a set of concepts, methods and tools of an innovative Hybrid Process Management approach validated by a real world business case in the automotive industry. Collapse

Semantic filters: theory of case-based reasoning

Topics: business process management information management expert system production management product lifecycle management

Methods: regression analysis method

Theories: theory of case-based reasoning
OptiPres: a distributed mobile agent decision support system for optimal patient drug prescription
PDF
2017 | Information Systems Frontiers | Citations: 1
Authors: Miller, Kevin; Mansingh, Gunjan

Abstract: Prescribing the right drugs for a patient is a difficult task that takes into co ... Expand

Abstract: Prescribing the right drugs for a patient is a difficult task that takes into consideration several factors. The Institute of Medicine (IOM), U.S.A., has reported based on two major studies (1999–2001 & 2006) that prescribing the wrong medication is a big problem, and the effects can sometimes be fatal. To address this problem, we designed and implemented, a distributed intelligent mobile agent-based system by the name, OptiPres. This system will be used by doctors on their smart phones while prescribing medicines. It will assist them in making more informed decisions by either choosing the optimal solution from processing a repository of past decisions or by presenting a set of possible drugs and using criteria specified by them to identify the optimal drug. The evaluation of OptiPres was done by comparing its recommended outcome of three predefined medical scenarios against the recommendations from a group of doctors and the World Health Organization (WHO) manual entitled:‘Guide to Good Prescribing’. The results indicate that OptiPres is effective in prescribing optimal drugs and in reducing the cognitive burden on doctors, especially in subjective decision making contexts where they have to consider multiple parameters. Collapse

Semantic filters: theory of case-based reasoning

Topics: database system conversational agent client-server model decision support system electronic health record

Methods: experiment computational algorithm simulation design science business process modeling

Theories: decision theory theory of case-based reasoning
CBR-based negotiation RBAC model for enhancing ubiquitous resources management
PDF
2017 | International Journal of Information Management | Citations: 0
Authors: Tseng, Shian-Shyong; Chen, Hsing-Chung; Hu, Li-Ling; Lin, Yen-Tsung

Abstract: a b s t r a c tWith the progress of new technologies of information management, ... Expand

Abstract: a b s t r a c tWith the progress of new technologies of information management, Ubiquitous Resource Management (URM) is a dominant areas of research which requires efficient access management approaches. There have been huge challenges of controlling access to ubiquitous resources among collaborative multiservers based on the negotiating security policies on URMs. However, the traditional access control mechanisms were insufficient to meet the requirements of role assignment management for URMs that allow accessing services via huge clients. Therefore, Ubiquitous RBAC (Role-based Access Control) with CBR (case-based reasoning) based negotiation technique is proposed in this paper. The novel RBAC scheme could efficiently manage not only one ubiquitous server, but also multiple ubiquitous servers on the cooperation domain through supporting both negotiating role assignment (NRA) task and cooperative role assignment (CRA) task in URM-platform by using a spiral negotiating process. Furthermore, it solves the difficulties in reducing the costs of ubiquitous computing resources, e.g., the role reassigned rate, handover rate, bandwidth, and power consumption, etc. Due to the ease of use and its efficiency in negotiating and managing the user-to-role as well as virtual role assignment by applying CBR approach, it is a highly powerful strategy of information management for conducting the innovative research and design for ubiquitous RBAC scheme. Collapse

Semantic filters: theory of case-based reasoning

Topics: knowledge representation ubiquitous computing smart device information management mobile system

Methods: literature study

Theories: theory of case-based reasoning

Page 1 of 9 Next

AIS11

Journals

Conferences

Semantic Filter

Found 83 articles

A holistic approach to interpretability in financial lending: Models, visualizations, and summary-explanations

Human-machine collaboration in online customer service – a long-term feedback-based approach

A Case-based Reasoning Approach for Supporting Facilitation in Online Discussions

A dynamic classification unit for online segmentation of big data via small data buffers

Using Analytic Hierarchy Process for COBIT 5 Process Prioritization

Advances in Databases and Information Systems

ETL workflow reparation by means of case-based reasoning

Product lifecycle management in knowledge intensive collaborative environments: An application to automotive industry

OptiPres: a distributed mobile agent decision support system for optimal patient drug prescription

CBR-based negotiation RBAC model for enhancing ubiquitous resources management