Fuzzy Logic as Agents’ Knowledge Representation in A-Trader System

Korczak, Jerzy; Hernes, Marcin; Bac, Maciej

doi:10.1007/978-3-319-30528-8_7

Cited by 5 publications

(13 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our project H2O has been integrated with A-Trader. Detailed architecture of this system has been presented in [19,20,21]. In this paper, we have outlined only those components closely related to Deep Learning Model (Fig 4).…”

Section: Deployment and Evaluation Of DL Modelmentioning

confidence: 99%

“…Our platform, called A-Trader [19,20,21], allows for implementation of various algorithms or trading decision support methods. Recently, A-Trader is aimed at supporting trading decisions on FOREX market (Foreign Exchange Market).…”

mentioning

confidence: 99%

“…On the other hand, a short position relies on "buying high and selling low". On FOREX, as one currency in a pair rises in value, other drops, and vice versa [19]. A-Trader mainly supports High Frequency Trading (HFT) [20], putting strong emphasis on price formation processes, shortterm positions, fast computing, and efficient and robust indicators [21].…”

mentioning

confidence: 99%

“…A-Trader architecture and description of different groups of agents have already been detailed [19]. In order to support trading decisions, agents apply technical, fundamental and behavioral analysis as well as different methods for knowledge integration (e.g.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning for Financial Time Series Forecasting in A-Trader System

Korczak¹,

Hemes²

2017

Proceedings of the 2017 Federated Conference on Computer Science and Information Systems

Self Cite

View full text Add to dashboard Cite

Abstract-The paper presents aspects related to developing methods for financial time series forecasting using deep learning in relation to multi-agent stock trading system, called A-Trader. On the basis of this model, an investment strategies in A-Trader system can be build. The first part of the paper briefly discusses a problem of financial time series on FOREX market. Classical neural networks and deep learning models are outlined, their performances are analyzed. The final part presents deployment and evaluation of a deep learning model implemented using H20 library as an agent of A-Trader system.

show abstract

Section: Deployment and Evaluation Of DL Modelmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning for Financial Time Series Forecasting in A-Trader System

Korczak¹,

Hemes²

2017

Proceedings of the 2017 Federated Conference on Computer Science and Information Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…14, 15, 16] state that using a fundamental analysis is also necessary for supporting trading decisions. A few of solutions combine fundamental analysis and behavioral sentiments.Our platform, called A-Trader [17,18], allows for the implementation of various algorithms or trading decision support methods [e.g. 19, 20].…”

mentioning

confidence: 99%

Fundamental analysis in the multi-agent trading system

Korczak¹,

Hernes²,

Bac³

2016

Annals of Computer Science and Information Systems

Self Cite

View full text Add to dashboard Cite

Abstract-The paper presents issues related to developing methods for fundamental analysis used to expand capabilities of multi-agent trading system, to better predict the financial market. The fundamental analysis indicators can be used as confirmation of decisions generated by other strategies of the system. The first part of the article discusses briefly the fundamental analysis issues in relation to the online trading on FOREX market. The statistical analysis of correlations of the different time series indicators and algorithms of fundamental analysis agents are examined. The final part discusses the results of the performance evaluation of selected investment strategies, including fundamental-based agents. I. INTRODUCTIONn trading support systems, the advices might be computed by one or many algorithms, or by one or many software agents using one or many information sources. An overview of of the agents operating on financial markets has already been given by B. LeBaron [1]. Currently, most trading systems are based on one or only a few algorithms. For example, the solutions described by L. Mendes, P. Godinho and J. Dias [2] use genetic algorithms to perform analysis on the basis of historical quotations. The system described by J.R. Thompson, J.R. Wilson and E. P. Fitts [3] is based on the multifractal time series. In the system described in [4,5] technical analysis indicators are used. There are many solutions based on multi-agent approach. H. C. Aladag, U. Yolco and E. Egrioglu [6] present an evaluation of the portfolio optimisation strategies by three agents: rational agent, interference agent, and technical analysis agent. P. Singh and B. Borah [7] apply a multi-agent system where the agents' intelligence is based on fuzzy expert system. O. Badawy and A. Almotwaly [8] developed the neural networks and neuro-fuzzy computing for taking into account the geometrical patterns of the financial data. M. Aloud, E.P.K. Tsang and R. Olsen [9] introduce an agent-based model for simple prediction of financial markets, where each agent predicts the development of selected subsets of the assets pairs in real time by separately examining the similarities between ask and bid assets histories. P. Kaltwasser [10] describes an agent that uses multiple behavioral techniques to make bidding decisions in the face of market uncertainty. J. Glattfelder, A. Dupuis and R. Olsen [11] develop a system that supports multiple strategies, but they use only movingaverage crossover strategies in the current stage of development. The paper by R. Barbosa and O. Belo [12] describes a multi-agent system that consists of a set of trading models such as an ensemble of classifiers, regression models, case-based reasoning, and an expert system. F. H. Westerhoff [13] presents a system where two groups of agents applying the methods of fundamental and technical analysis try to shape market dynamics.Summing up, more often the trading advice is provide by multiple software agents that use mainly technical analysis. However, many papers relate...

show abstract