Cloning mechanisms to improve agent performances

Rosaci, Domenico; Sarné, Giuseppe M. L.

doi:10.1016/j.jnca.2012.04.018

Cited by 15 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This means that the recommender operates on the server side by performing all the activities necessary for generating recommendations. Such an overhead might become easily unbearable in cases such as with access performed though mobile devices [17]. Counterwisely, implementing more sophisticated recommendation techniques on these centralized architectures generates efficiency and scalability problems on the central server.…”

Section: Weaknesses Of Current Recommender Systems For E-commerce Andmentioning

confidence: 99%

“…However, in most of these approaches, the complexity of the e-Commerce process results in a computation overhead on the client side. Such an overhead might become easily unbearable in cases such as with access performed though mobile devices [17]. 4510 L. PALOPOLI, D. ROSACI AND G. M. L. SARNÉ in the following.…”

Section: Weaknesses Of Current Recommender Systems For E-commerce Andmentioning

confidence: 99%

“…A few of them are distributed, but in this case, the complexity of the e-Commerce process implies computation overhead on the client side, which is often unsuitable if mobile devices are used by customers. Such an overhead might become easily unbearable in cases such as with access performed though mobile devices [17].A DISTRIBUTING ARCHITECTURE FOR E-COMMERCE RECOMMENDATIONS 4509 …”

mentioning

confidence: 99%

See 2 more Smart Citations

A distributed and multi‐tiered software architecture for assessing e‐Commerce recommendations

Palopoli

Rosaci

Sarné

2016

Concurrency and Computation

View full text Add to dashboard Cite

Recently, an ever increasing number of e-Commerce tools has been made available that are able to help customers by generating purposed recommendations. Many of them are centralized so that they have to face problems related to efficiency and scalability. A few of them are distributed, but in this case, the complexity of the e-Commerce process implies computation overhead on the client side, which is often unsuitable if mobile devices are used by customers. In this paper, we study how the software distribution in recommender systems affects their performances, depending on the characteristics of the e-Commerce population. To this end, we present a distributed testbed architecture for e-Commerce recommender systems using a multi-tiered agent-based approach to generate effective recommendations without requiring such an onerous amount of computation per single client. We use such a testbed to study the main advantages and limitations associated with the problem of distributing the computation of recommendations. the presence of message delays, do not affect the recommendation activity. Indeed, in these cases, a global knowledge about the state of the system is not generally required, and message delay is not a relevant problem because the communication model is of the peer-to-peer (P2P) kind.However, it is not clear to what extent these advantages depend on the characteristics of the e-Commerce community [13] and, more generally speaking, what are the actual limits of the adoption of a distributed approach in a B2C e-Commerce scenario. This paper is meant to provide an answer to this question.In order to understand why such an analysis is important, consider a case where we want to design a recommender system for supporting an e-Commerce community such as, for example, a portal for sellers and customers of antiquarian products. In this case, a possible solution consists in adopting an agent-based system such that a software agent is associated with each seller and each customer to support them by generating recommendations. Notice that, in an e-Commerce scenario, there are many activities to support. To illustrate, customers have to be provided with recommendations about the antiquarian products they will be most probably interested in. Also, they will need suggestions about the most convenient merchants. Moreover, some negotiation activities between customers and merchants might be necessary, as well as a support for the delivery process and for the evaluation service. The question is: from the efficiency viewpoint, is it better either to design a single software agent assisting its user (either a customer or a merchant) in all those different activities, or to provide each user with a set of agents, where each agent is dedicated to a specific activity? In other words, given for granted that various actors are assumed to be associated with different agents (horizontal distribution), it must be decided if having a single agent per actor is more convenient than distributing the activities associated with the single a...

show abstract

Section: Weaknesses Of Current Recommender Systems For E-commerce Andmentioning

confidence: 99%

Section: Weaknesses Of Current Recommender Systems For E-commerce Andmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

A distributed and multi‐tiered software architecture for assessing e‐Commerce recommendations

Palopoli

Rosaci

Sarné

2016

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Evolutionary Agents (EVA) is an approach that is based on a cloning process. EVA is similar to the biologic asexualreproductive processes generating clones that initially are the exact copies oftheir parents.EVA approach helps users to substitute unsatisfactory agents with other agents having good reputation [1]. It allows the best agent to emerge over less productive agents.…”

Section: Bmentioning

confidence: 99%

Population Dynamics in Artificial Agent Societies: A Review

Kaur¹,

Kaur²

2015

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

This paper -Population Dynamics in Artificial Agent Society‖ broadly covers the change of population in human and agent societies. There are certain causes like Natality, Mortality, and Migration that are responsible for such a change. These causes are referred to as key elements of population dynamics. Moreover a Demographic view of population is provided. To simulate the human society agent-based modeling is implemented in object oriented programming language that society is called artificial agent society. Through this paper introduction of new agent ,death of agent in society and migration of agents are discussed. At last the metrics for measuring number of agents migrating to and from society, and metrics for measuring agent-based society are discussed.

show abstract

“…It is a kind of information filtering system that predicts users' ratings or preferences for items and provides users with items that they may be interested in. It is applied in a variety of domains such as movies, music, books, news, and any other contents in general [1,4,18,20,22,[25][26][27][28][29]. As a result, many recommendation algorithms have been developed for these domains in recent years.…”

Section: Introductionmentioning

confidence: 99%

A Television Recommender System Learning a User’s Time-Aware Watching Patterns Using Quadratic Programming

Kim

Lee

2018

Applied Sciences

View full text Add to dashboard Cite

In this paper, a novel television (TV) program recommendation method is proposed by merging multiple preferences. We use channels and genres of programs, which is available information in standalone TVs, as features for the recommendation. The proposed method performs multi-time contextual profiling and constructs multiple-time contextual preference matrices of channels and genres. Since multiple preference models are constructed with different time contexts, there can be conflicts among them. In order to effectively merge the preferences with the minimum number of conflicts, we develop a quadratic programming model. The optimization problem is formulated with a minimum number of constraints so that the optimization process is scalable and fast even in a standalone TV with low computational power. Experiments with a real-world dataset prove that the proposed method is more efficient and accurate than other TV recommendation methods. Our method improves recommendation performance by 5-50% compared to the baselines.

show abstract

Cloning mechanisms to improve agent performances

Cited by 15 publications

References 28 publications

A distributed and multi‐tiered software architecture for assessing e‐Commerce recommendations

A distributed and multi‐tiered software architecture for assessing e‐Commerce recommendations

Population Dynamics in Artificial Agent Societies: A Review

A Television Recommender System Learning a User’s Time-Aware Watching Patterns Using Quadratic Programming

Contact Info

Product

Resources

About