The evaluation of intelligent agent performance — An example of B2C e-commerce negotiation

Liang, Wen‐Yau; Huang, Chun‐Che; Tseng, Tzu-Liang; Lin, Yin-Chen; Tseng, J.C.L.

doi:10.1016/j.csi.2012.02.003

Cited by 16 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the experiments in the paper, we used the scipy.stats 13 library for the statistical outcomes and the matplotlib 14 library for all graphs.…”

Section: A Appendix On Reproducibilitymentioning

confidence: 99%

“…By assigning values to actions committed, we can help evaluate the performance of agents and aid the learning and improvement of future actions. To date, examples of work that explore methods for valuing actions are shown in industrial optimisation [18], agent negotiation [14] and sports analytics [6,23]. Although all these papers aim to assign value to what a human or agent has helped happen, there are many domains in the real-world where some humans/agents are tasked with preventing actions from happening (e.g., in security games agents aim to protect bases or ports and prevent attacks [25]).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data

Merhej

Beal

Matthews³

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Objectively quantifying the value of player actions in football (soccer) is a challenging problem. To date, studies in football analytics have mainly focused on the attacking side of the game, while there has been less work on event-driven metrics for valuing defensive actions (e.g., tackles and interceptions). Therefore in this paper, we use deep learning techniques to define a novel metric that values such defensive actions by studying the threat of passages of play that preceded them. By doing so, we are able to value defensive actions based on what they prevented from happening in the game. Our Defensive Action Expected Threat (DAxT) model has been validated using real-world event-data from the 2017/2018 and 2018/2019 English Premier League seasons, and we combine our model outputs with additional features to derive an overall rating of defensive ability for players. Overall, we find that our model is able to predict the impact of defensive actions allowing us to better value defenders using event-data. CCS CONCEPTS• Applied computing; • Computing methodologies → Model development and analysis; Neural networks;

show abstract

“…For the experiments in the paper, we used the scipy.stats 13 library for the statistical outcomes and the matplotlib 14 library for all graphs.…”

Section: A Appendix On Reproducibilitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data

Merhej

Beal

Matthews³

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

show abstract

“…Because of the large number of jobs and resumes, the importance of intelligent agents appear. An Intelligent agent can be defined in this work as a software component which is capable to finish tasks on behalf of its user [12]. It can help the user to do different tasks such as search and negotiation.…”

Section: Components and Layersmentioning

confidence: 99%

The Impact of CBSE’s Activities on E-Commerce Applications

Khaled¹

2013

View full text Add to dashboard Cite

Component based technology is widely used for both academicians and business. There are numbers of benefits for using this type of technology. First, it helps to increase the efficiency and maintainability of software. Second, it improves quality and helps to enhance productivity. Third, the reuse approach that supports component based technology decreases the time to market. Component based e-commerce can be used to solve e-commerce difficulties at application level as well as at system level. This paper introduces how component based activities have effect mainly on building the framework of the e-commerce. It also discusses how the architectural design of the application can be synthesized.

show abstract

“…Previous EC researchers have focused on the consumers' motivations [30,71], the shopping behaviour [39,81], the intelligent agents [43,86], the satisfaction-loyalty relationship [5,15,63], and the risk [10]. This research has focused on how to manage e-stores and create marketing strategies.…”

Section: Introductionmentioning

confidence: 98%