Research Reports

Permanent URI for this collectionhttp://dl.cerist.dz/handle/CERIST/34

Browse

Author: search.filters.author.Benatchba, KarimaSubject: search.filters.subject.Simulation

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Artificial financial market. Risk analysis approach
    (CERIST, 2015) Hedjazi Dellal, Badiâa; Aknine, Samir; Benatchba, Karima
    Financial market is in constant confrontation with various financial risks. These contribute to market instabilities, financial crises and substantial losses for investors. To effectively manage these risks, we should understand the complexity of the market due to its evolution in an uncertain environment. This is possible through multi-agent modeling and simulation while taking into consideration risk indicators. We, propose, in this paper, to model a financial market simulation system using a multi-agent model, where agents represent the different market participants. The reasoning model of our agents is based on different risk indicators. We use the classifier systems as reasoning and learning model for the cognitive agents of our system. This system is a decision tool dedicated to managers or experts wanting to analyze and understand through the behaviour of the different participants, the evolution of the global dynamics of the market and the influence of the different risk factors on the market and on the various categories of market participants.
  • Thumbnail Image
    Item
    Artificial financial market. Risk analysis approach
    (CERIST, 2015) Hedjazi Dellal, Badiâa; Aknine, Samir; Benatchba, Karima
    Financial market is in constant confrontation with various financial risks. These contribute to market instabilities, financial crises and substantial losses for investors. To effectively manage these risks, we should understand the complexity of the market due to its evolution in an uncertain environment. This is possible through multi-agent modeling and simulation while taking into consideration risk indicators. We, propose, in this paper, to model a financial market simulation system using a multi-agent model, where agents represent the different market participants. The reasoning model of our agents is based on different risk indicators. We use the classifier systems as reasoning and learning model for the cognitive agents of our system. This system is a decision tool dedicated to managers or experts wanting to analyze and understand through the behaviour of the different participants, the evolution of the global dynamics of the market and the influence of the different risk factors on the market and on the various categories of market participants.
  • Thumbnail Image
    Item
    Overhearing in financial markets: a multi-agent approach markets: a multi-agent approach
    (CERIST, 2010-11) Hedjazi Dellal, Badiâa; Ahmed-Nacer, Mohamed; Aknine, Samir; Benatchba, Karima
    Open complex systems as financial markets evolve in a highly dynamic and uncertain environment. They are often subject to significant fluctuations due to unanticipated behaviours and information. Modelling and simulating these systems by means of agent systems, i.e., through artificial markets is a valuable approach. In this article, we present our model of asynchronous artificial market consisting of a set of adaptive and heterogeneous agents in interaction. These agents represent the various market participants (investors and institutions). Investor Agents have advanced mental models for ordinary investors which do not relay on fundamental or technical analysis methods. On one hand, these models are based on the risk tolerance and on the other hand on the information gathered by the agents. This information results from overhearing influential investors in the market or the order books. We model the system through investor agents using learning classifier systems as reasoning models. As a result, our artificial market allows the study of overhearing impacts on the market. We also present the experimental evaluation results of our model.