Search results for: agent learning

Authors: Sung-Hae Jun, Kyung-Whan Oh

Abstract:

Statistical learning theory was developed by Vapnik. It is a learning theory based on Vapnik-Chervonenkis dimension. It also has been used in learning models as good analytical tools. In general, a learning theory has had several problems. Some of them are local optima and over-fitting problems. As well, statistical learning theory has same problems because the kernel type, kernel parameters, and regularization constant C are determined subjectively by the art of researchers. So, we propose an evolutionary statistical learning theory to settle the problems of original statistical learning theory. Combining evolutionary computing into statistical learning theory, our theory is constructed. We verify improved performances of an evolutionary statistical learning theory using data sets from KDD cup.

Keywords: Evolutionary computing, Local optima, Over-fitting, Statistical learning theory

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1728

Authors: Gilbert Ndjatou

Abstract:

We propose a formal framework for the specification of the behavior of a system of agents, as well as those of the constituting agents. This framework allows us to model each agent-s effectoric capability including its interactions with the other agents. We also provide an algorithm based on Milner-s "observation equivalence" to derive an agent-s perception of its task domain situations from its effectoric capability, and use "system computations" to model the coordinated efforts of the agents in the system . Formal definitions of the concept of "behavior equivalence" of two agents and that of system computations equivalence for an agent are also provided.

Keywords: Multiagent system, object system, observation equivalence, reactive systems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1205

Authors: Soe Winn, May Thwe Oo

Abstract:

Business process automation is an important task in an enterprise business environment software development. The requirements of processing acceleration and automation level of enterprises are inherently different from one organization to another. We present a methodology and system for automation of business process management system architecture by multi-agent collaboration based on SOA. Design layer processes are modeled in semantic markup language for web services application. At the core of our system is considering certain types of human tasks to their further automation across over multiple platform environments. An improved abnormality processing with model for automation of BPMS architecture by multi-agent collaboration based on SOA is introduced. Validating system for efficiency of process automation, an application for educational knowledge base instance would also be described.

Keywords: Business process management system, businessprocess automation, multi-agent collaboration, Service OrientedArchitecture, extensible service application

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1709

Authors: Kamalendu Pal

Abstract:

Supply chains are the backbone of trade and commerce. Their logistics use different transport corridors on regular basis for operational purpose. The international supply chain transport corridors include different infrastructure elements (e.g. weighbridge, package handling equipments, border clearance authorities, and so on). This paper presents the use of multi-agent systems (MAS) to model and simulate some aspects of transportation corridors, and in particular the area of weighbridge resource optimization for operational profit. An underlying multi-agent model provides a means of modeling the relationships among stakeholders in order to enable coordination in a transport corridor environment. Simulations of the costs of container unloading, reloading, and waiting time for queuing up tracks have been carried out using data sets. Results of the simulation provide the potential guidance in making decisions about optimal service resource allocation in a trade corridor.

Keywords: Multi-agent systems, simulation, supply chain, transport corridor, weighbridge.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2120

Authors: Tappei Yotsumoto, Atsushi Nomura, Kozo Tanigawa, Kenichi Takahashi, Takao Kawamura, Kazunori Sugahara

Abstract:

In a human tracking system, expanding a monitoring range of one system is complicating the management of devices and increasing its cost. Therefore, we propose a method to realize a wide-range human tracking by connecting small systems. In this paper, we examined an agent deploy method and information contents across the heterogeneous human tracking systems. By implementing the proposed method, we can construct a human tracking system across heterogeneous systems, and the system can track a target continuously between systems.

Keywords: Human tracking system, mobile agent, monitoring.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1471

Authors: Costin Badica, Maria Ganzha, Maciej Gawinecki, Pawel Kobzdej, Marcin Paprzycki

Abstract:

Recently, we have presented an initial implementation of a model agent-based e-commerce system, which utilized a simple price negotiation mechanism–English Auction. In this note we discuss how a Dutch Auction involving multiple units of a product can be included in our system. We present UML diagrams of agents involved in price negotiations and briefly discuss rule-based mechanism exemplifying Dutch Auction.

Keywords: e-commerce, rule-based price negotiation mechanism, Dutch Auction, agent system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1691

Authors: Konstantinos Sofianos, Michail Stefanidakis

Abstract:

Nowadays, despite the great advances in technology, most educational frameworks lack a strong educational design basis. E-learning has become prevalent, but it faces various challenges such as student isolation and lack of quality in the learning process. An intelligent learning system provides a student with educational material according to their learning background and learning preferences. It records full information about the student, such as demographic information, learning styles, and academic performance. This information allows the system to be fully adapted to the student’s needs. In this paper, we propose a framework and an ontology for music education, consisting of the learner model and all elements of the learning process (learning objects, teaching methods, learning activities, assessment). This framework can be integrated into an intelligent learning system and used for music education in schools for the development of professional skills and beyond.

Keywords: Intelligent learning systems, e-learning, music education, ontology, semantic web.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 379

Authors: Omar Boutkhoum, Mohamed Hanine, Tarik Agouti, Abdessadek Tikniouine

Abstract:

This paper discusses the intake of combining multi-criteria decision analysis (MCDA) with OLAP systems, to generate an integrated analysis process dealing with complex multi-criteria decision-making situations. In this context, a multi-agent modeling is presented for decision support systems by combining multi-criteria decision analysis (MCDA) with OLAP systems. The proposed modeling which consists in performing the multi-agent system (MAS) architecture, procedure and protocol of the negotiation model is elaborated as a decision support tool for complex decision-making environments. Our objective is to take advantage from the multi-agent system which distributes resources and computational capabilities across interconnected agents, and provide a problem modeling in terms of autonomous interacting component-agents. Thus, the identification and evaluation of criteria as well as the evaluation and ranking of alternatives in a decision support situation will be performed by organizing tasks and user preferences between different agents in order to reach the right decision. At the end, an illustrative example is conducted to demonstrate the function and effectiveness of our MAS modeling.

Keywords: Multidimensional Analysis, OLAP Analysis, Multi-criteria Decision Analysis, Multi-Agent System, Decision Support System.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1799

Authors: Ramin Halavati, Saeed B. Shouraki, Mahdieh Noroozian, Saman H. Zadeh

Abstract:

Packing problems arise in a wide variety of application areas. The basic problem is that of determining an efficient arrangement of different objects in a region without any overlap and with minimal wasted gap between shapes. This paper presents a novel population based approach for optimizing arrangement of irregular shapes. In this approach, each shape is coded as an agent and the agents' reproductions and grouping policies results in arrangements of the objects in positions with least wasted area between them. The approach is implemented in an application for cutting sheets and test results on several problems from literature are presented.

Keywords: Optimization, Bin Packing, Agent Based Systems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2429

Authors: Adel Sabry Eesa, Adnan Mohsin Abdulazeez Brifcani, Zeynep Orman

Abstract:

Feature selection has been used in many fields such as classification, data mining and object recognition and proven to be effective for removing irrelevant and redundant features from the original dataset. In this paper, a new design of distributed intrusion detection system using a combination feature selection model based on bees and decision tree. Bees algorithm is used as the search strategy to find the optimal subset of features, whereas decision tree is used as a judgment for the selected features. Both the produced features and the generated rules are used by Decision Making Mobile Agent to decide whether there is an attack or not in the networks. Decision Making Mobile Agent will migrate through the networks, moving from node to another, if it found that there is an attack on one of the nodes, it then alerts the user through User Interface Agent or takes some action through Action Mobile Agent. The KDD Cup 99 dataset is used to test the effectiveness of the proposed system. The results show that even if only four features are used, the proposed system gives a better performance when it is compared with the obtained results using all 41 features.

Keywords: Distributed intrusion detection system, mobile agent, feature selection, Bees Algorithm, decision tree.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1883

Authors: Phyoung Jung Kim, Seogyun Kim

Abstract:

In mobile computing environments, there are many new non existing problems in the distributed system, which is consisted of stationary hosts because of host mobility, sudden disconnection by handoff in wireless networks, voluntary disconnection for efficient power consumption of a mobile host, etc. To solve the problems, we proposed the architecture of Partial Connection Manager (PCM) in this paper. PCM creates the limited number of mobile agents according to priority, sends them in parallel to servers, and combines the results to process the user request rapidly. In applying the proposed PCM to the mobile market agent service, we understand that the mobile agent technique could be suited for the mobile computing environment and the partial connection problem management.

Keywords: Mobile agent, mobile computing, partial connection

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1571

Authors: Ileladewa Adeoye Abiodun, Cheng Wai Khuen

Abstract:

Multi-Agent Systems (MAS) emerged in the pursuit to improve our standard of living, and hence can manifest complex human behaviors such as communication, decision making, negotiation and self-organization. The Social Network Services (SNSs) have attracted millions of users, many of whom have integrated these sites into their daily practices. The domains of MAS and SNS have lots of similarities such as architecture, features and functions. Exploring social network users- behavior through multiagent model is therefore our research focus, in order to generate more accurate and meaningful information to SNS users. An application of MAS is the e-Auction and e-Rental services of the Universiti Cyber AgenT(UniCAT), a Social Network for students in Universiti Tunku Abdul Rahman (UTAR), Kampar, Malaysia, built around the Belief- Desire-Intention (BDI) model. However, in spite of the various advantages of the BDI model, it has also been discovered to have some shortcomings. This paper therefore proposes a multi-agent framework utilizing a modified BDI model- Belief-Desire-Intention in Dynamic and Uncertain Situations (BDIDUS), using UniCAT system as a case study.

Keywords: Distributed Data Mining, Multi-Agent Systems, Preference-Based, SNS.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1449

Authors: Norazah Yusof, Andi Besse Firdausiah Mansur

Abstract:

Social learning network analysis has drawn attention for most researcher on e-learning research domain. This is due to the fact that it has the capability to identify the behavior of student during their social interaction inside e-learning. Normally, the social network analysis (SNA) is treating the students' interaction merely as node and edge with less meaning. This paper focuses on providing an ontology structure of e-learning Moodle that can enrich the relationships among students, as well as between the students and the teacher. This ontology structure brings great benefit to the future development of e-learning system.

Keywords: Ontology, e-learning, © Learning Network, Moodle.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3109

Authors: Masayuki Higashino, Toshiya Kawato, Takao Kawamura

Abstract:

A monolithic service is based on the N-tier architecture in many cases. In order to divide a monolithic service into microservices, it is necessary to redefine a model as a new microservice by extracting and merging existing models across layers. Refactoring a monolithic service into microservices requires advanced technical capabilities, and it is a difficult way. This paper proposes a design and concept to ease the migration of a monolithic service to microservices using the mobile agent technology. Our proposed approach, mobile agents-based design and concept, enables to ease dividing and merging services.

Keywords: Mobile agent, microservice, web service, distributed system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1041

Authors: Hadi Firouzi, Majid Nili Ahmadabadi, Babak N. Araabi

Abstract:

Conceptualization strengthens intelligent systems in generalization skill, effective knowledge representation, real-time inference, and managing uncertain and indefinite situations in addition to facilitating knowledge communication for learning agents situated in real world. Concept learning introduces a way of abstraction by which the continuous state is formed as entities called concepts which are connected to the action space and thus, they illustrate somehow the complex action space. Of computational concept learning approaches, action-based conceptualization is favored because of its simplicity and mirror neuron foundations in neuroscience. In this paper, a new biologically inspired concept learning approach based on the probabilistic framework is proposed. This approach exploits and extends the mirror neuron-s role in conceptualization for a reinforcement learning agent in nondeterministic environments. In the proposed method, instead of building a huge numerical knowledge, the concepts are learnt gradually from rewards through interaction with the environment. Moreover the probabilistic formation of the concepts is employed to deal with uncertain and dynamic nature of real problems in addition to the ability of generalization. These characteristics as a whole distinguish the proposed learning algorithm from both a pure classification algorithm and typical reinforcement learning. Simulation results show advantages of the proposed framework in terms of convergence speed as well as generalization and asymptotic behavior because of utilizing both success and failures attempts through received rewards. Experimental results, on the other hand, show the applicability and effectiveness of the proposed method in continuous and noisy environments for a real robotic task such as maze as well as the benefits of implementing an incremental learning scenario in artificial agents.

Keywords: Concept learning, probabilistic decision making, reinforcement learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1485

Authors: Yasser F. Hassan, Marwa Abdeen, Mustafa Fahmy

Abstract:

In recent years multi-agent systems have emerged as one of the interesting architectures facilitating distributed collaboration and distributed problem solving. Each node (agent) of the network might pursue its own agenda, exploit its environment, develop its own problem solving strategy and establish required communication strategies. Within each node of the network, one could encounter a diversity of problem-solving approaches. Quite commonly the agents can realize their processing at the level of information granules that is the most suitable from their local points of view. Information granules can come at various levels of granularity. Each agent could exploit a certain formalism of information granulation engaging a machinery of fuzzy sets, interval analysis, rough sets, just to name a few dominant technologies of granular computing. Having this in mind, arises a fundamental issue of forming effective interaction linkages between the agents so that they fully broadcast their findings and benefit from interacting with others.

Keywords: Granular computing, rough sets, agents, traffic system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1687

Authors: M. Benattou, K. Tamine

Abstract:

This paper presents a distributed intrusion detection system IDS, based on the concept of specialized distributed agents community representing agents with the same purpose for detecting distributed attacks. The semantic of intrusion events occurring in a predetermined network has been defined. The correlation rules referring the process which our proposed IDS combines the captured events that is distributed both spatially and temporally. And then the proposed IDS tries to extract significant and broad patterns for set of well-known attacks. The primary goal of our work is to provide intrusion detection and real-time prevention capability against insider attacks in distributed and fully automated environments.

Keywords: Mobile agent, specialized agent, interpreter agent, event rules, correlation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1793

Authors: Haiyan Wang

Abstract:

Constuctivism learning theory lays emphasis on the learners' active learning, such as learning initiative, sociality and context. By analyzing the relationship between constructivism learning theory and learner autonomy, this paper explores how to cultivate learners' learner autonomy under the guidance of constructivism learning theory.

Keywords: Constructivism learning theory, learner autonomy, relationship, cultivation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 7672

Authors: Reza Ghasemi, Negin Amiri Hazaveh

Abstract:

In this paper, control methodology based on the selection of the type of traffic light and the period of the green phase to accomplish an optimum balance at intersections is proposed. This balance should be flexible to the static behavior of time, and randomness in a traffic situation; the goal of the proposed method is to reduce traffic volume in transportation, the average delay for each vehicle, and control over the crash of cars. The proposed method was specifically investigated at the intersection through an appropriate timing of traffic lights by sampling a multi-agent system. It consists of a large number of intersections, each of which is considered as an independent agent that exchanges information with each other, and the stability of each agent is provided separately. The robustness against uncertainties, scalability, and stability of the closed-loop overall system are the main merits of the proposed methodology. The simulation results show that the fuzzy intelligent controller in this multi-factor system which is a Takagi-Sugeno (TS) fuzzy is more useful than scheduling in the fixed-time method and it reduces the lengths of vehicles queuing.

Keywords: Fuzzy intelligent controller, traffic-light control, multi-agent systems, state space equations, stability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 457

Authors: Wei Hu, Tianzhou Chen, Qingsong Shi

Abstract:

In recent years, the development of e-learning is very rapid. E-learning is an attractive and efficient way for computer education. Student interaction and collaboration also plays an important role in e-learning. In this paper, a collaborative web-based e-learning environment is presented. A wide range of interactive and collaborative methods are integrated into a web-based environment. This e-learning environment is designed for information security curriculum.

Keywords: E-learning, information Security, curriculum, web-based environment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1676

Authors: Teerada Apibunyopas, Nithinant Thammakoranonta

Abstract:

Many organizations bring e-Learning to use as a tool in their training and human development department. It is getting more popular because it is easy to access to get knowledge all the time and also it provides a rich content, which can develop the employees’ skill efficiently. This study is focused on the factors that affect using e-Learning efficiently, so it will make job satisfaction increasing. The questionnaires were sent to employees in large commercial banks, which use e-Learning located in Bangkok, the results from multiple linear regression analysis showed that employee’s characteristics, characteristics of e-Learning, learning and growth have influence on job satisfaction.

Keywords: e-Learning, Job Satisfaction, Learning and growth.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2344

Authors: Dimitri Perrin, Heather J. Ruskin, Martin Crane

Abstract:

This study focuses on examining why the range of experience with respect to HIV infection is so diverse, especially in regard to the latency period. An agent-based approach in modelling the infection is used to extract high-level behaviour which cannot be obtained analytically from the set of interaction rules at the cellular level. A prototype model encompasses local variation in baseline properties, contributing to the individual disease experience, and is included in a network which mimics the chain of lymph nodes. The model also accounts for stochastic events such as viral mutations. The size and complexity of the model require major computational effort and parallelisation methods are used.

Keywords: HIV, Immune modelling, Agent-based system, individual response.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1230

Authors: James D. Gadze, Niki Pissinou, Kia Makki

Abstract:

In this paper we propose an intelligent agent approach to control the electric power grid at a smaller granularity in order to give it self-healing capabilities. We develop a method using the influence model to transform transmission substations into information processing, analyzing and decision making (intelligent behavior) units. We also develop a wireless communication method to deliver real-time uncorrupted information to an intelligent controller in a power system environment. A combined networking and information theoretic approach is adopted in meeting both the delay and error probability requirements. We use a mobile agent approach in optimizing the achievable information rate vector and in the distribution of rates to users (sensors). We developed the concept and the quantitative tools require in the creation of cooperating semiautonomous subsystems which puts the electric grid on the path towards intelligent and self-healing system.

Keywords: Mobile agent, power system operation and control, real time, wireless communication.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1626

Authors: Conradie, P.W., Lombard, A., Moller, M.

Abstract:

The dramatic effect of information technology on society is undeniable. In education, it is evident in the use of terms like active learning, blended learning, electronic learning and mobile learning (ubiquitous learning). This study explores the perceptions of 54 learners in a higher education institution regarding the use of mobile devices in a third year module. Using semi-structured interviews, it was found that mobile devices had a positive impact on learner motivation, engagement and enjoyment. It also improved the consistency of learning material, and the convenience and flexibility (anywhere, anytime) of learning. User-interfacelimitation, bandwidth and cognitive overload, however, were of concern. The use of cloud based resources like Youtube and Google Docs, through mobile devices, positively influenced learner perceptions, making them prosumers (both consumers and producers) of education content.

Keywords: Active learning, education, mobile learning, pedagogy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2151

Authors: J. Seke Mboungou Mouyabi

Abstract:

This paper is an exploration of the conceptual confusion between E-learning and M-learning particularly in Africa. Section I provides a background to the development of E-learning and M-learning. Section II focuses on the conceptual analysis as it applies to Africa. It is with an investigative and expansive mind that this paper is elaborated to respond to a profound question of the suitability of the concepts in a particular era in Africa. The aim of this paper is therefore to shed light on which concept best suits the unique situation of Africa in the era of cloud computing.

Keywords: African Concept, Cloud computing, E-learning, Mlearning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1995

Authors: G. B. Hong, H. W. Chen

Abstract:

Liquid-Liquid Equilibrium (LLE) data are measured for the ternary mixtures of water + 1-butanol + butyl acetate and quaternary mixtures of water + 1-butanol + butyl acetate + glycerol at atmospheric pressure at 313.15 K. In addition, isothermal vapor–liquid–liquid equilibrium (VLLE) data are determined experimentally at 333.15 K. The region of heterogeneity is found to increase as the hydrophilic agent (glycerol) is introduced into the aqueous mixtures. The experimental data are correlated with the NRTL model. The predicted results from the solution model with the model parameters determined from the constituent binaries are also compared with the experimental values.

Keywords: LLE, VLLE, hydrophilic agent, NRTL.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1245

Authors: K. Kumpas

Abstract:

Bologna process has influenced enhancing studentcentered learning in Estonian higher education since 2009, but there is no information about what helps or hinders students to achieve learning outcomes and how quality of student-centered learning might be improved. The purpose of this study is to analyze two questions from outcome-based course evaluation questionnaire which is used in Estonian Entrepreneurship University of Applied Sciences. In this qualitative research, 384 students from 22 different courses described what helped and hindered them to achieve learning outcomes. The analysis showed that the aspects that hinder students to achieve learning outcomes are mostly personal: time management, family and personal matters, motivation and non-academic activities. The results indicate that students- learning is commonly supported by school, where teacher, teaching and characteristics of teaching methods help mostly to achieve learning outcomes, also learning material, practical assignments and independent study was brought up as one of the key elements.

Keywords: Learning outcomes, learning quality, student-centered learning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1715

Authors: M. E. Marwan, A. R. Madar, N. Fuad

Abstract:

Mobile learning (m-learning) is a new method in teaching and learning process which combines technology of mobile device with learning materials. It can enhance student's engagement in learning activities and facilitate them to access the learning materials at anytime and anywhere. In Kolej Poly-Tech Mara (KPTM), this method is seen as an important effort in teaching practice and to improve student learning performance. The aim of this paper is to discuss the development of m-learning application called Mobile EEF Learning System (MEEFLS) to be implemented for Electric and Electronic Fundamentals course using Flash, XML (Extensible Markup Language) and J2ME (Java 2 micro edition). System Development Life Cycle (SDLC) was used as an application development approach. It has three modules in this application such as notes or course material, exercises and video. MEELFS development is seen as a tool or a pilot test for m-learning in KPTM.

Keywords: Flash, mobile device, mobile learning, teaching and learning, SDLC, XML.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1933

Authors: Talal Alsulaiman, Khaldoun Khashanah

Abstract:

In this paper, we provided a literature survey on the artificial stock problem (ASM). The paper began by exploring the complexity of the stock market and the needs for ASM. ASM aims to investigate the link between individual behaviors (micro level) and financial market dynamics (macro level). The variety of patterns at the macro level is a function of the AFM complexity. The financial market system is a complex system where the relationship between the micro and macro level cannot be captured analytically. Computational approaches, such as simulation, are expected to comprehend this connection. Agent-based simulation is a simulation technique commonly used to build AFMs. The paper proceeds by discussing the components of the ASM. We consider the roles of behavioral finance (BF) alongside the traditionally risk-averse assumption in the construction of agent’s attributes. Also, the influence of social networks in the developing of agents interactions is addressed. Network topologies such as a small world, distance-based, and scale-free networks may be utilized to outline economic collaborations. In addition, the primary methods for developing agents learning and adaptive abilities have been summarized. These incorporated approach such as Genetic Algorithm, Genetic Programming, Artificial neural network and Reinforcement Learning. In addition, the most common statistical properties (the stylized facts) of stock that are used for calibration and validation of ASM are discussed. Besides, we have reviewed the major related previous studies and categorize the utilized approaches as a part of these studies. Finally, research directions and potential research questions are argued. The research directions of ASM may focus on the macro level by analyzing the market dynamic or on the micro level by investigating the wealth distributions of the agents.

Keywords: Artificial stock markets, agent based simulation, bounded rationality, behavioral finance, artificial neural network, interaction, scale-free networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2485

Authors: Taylan Kabbani, Ekrem Duman

Abstract:

Deep Reinforcement Learning (DRL) algorithms can scale to previously intractable problems. The automation of profit generation in the stock market is possible using DRL, by combining  the financial assets price ”prediction” step and the ”allocation” step of the portfolio in one unified process to produce fully autonomous systems capable of interacting with its environment to make optimal decisions through trial and error. This work represents a DRL model to generate profitable trades in the stock market, effectively overcoming the limitations of supervised learning approaches. We formulate the trading problem as a Partially observed Markov Decision Process (POMDP) model, considering the constraints imposed by the stock market, such as liquidity and transaction costs. We then solved the formulated POMDP problem using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm and achieved a 2.68 Sharpe ratio on the test dataset. From the point of view of stock market forecasting and the intelligent decision-making mechanism, this paper demonstrates the superiority of DRL in financial markets over other types of machine learning and proves its credibility and advantages of strategic decision-making.

Keywords: Autonomous agent, deep reinforcement learning, MDP, sentiment analysis, stock market, technical indicators, twin delayed deep deterministic policy gradient.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 460