Three decision making levels in portfolio management

Raudys, Šarūnas; Raudys, Aistis

doi:10.1109/cifer.2012.6327795

Cited by 4 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In ATSs [33], [34], the number of activities (autonomous trading robots, agents) N often is close or even exceeds learning set size L. Equations (14) and (15) show that effect of learning set size can be very influential if the dimensionality N is close to L. It means that, in very small learning set situations, proper estimation of the covariance matrix becomes a critical task. The situation can become even dangerous: a small increase in dimensionality can ruin the portfolio completely.…”

Section: B In-sample and Out-of-sample Standard Portfoliomentioning

confidence: 98%

See 1 more Smart Citation

Portfolio of Automated Trading Systems: Complexity and Learning Set Size Issues

Raudys

2013

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

View full text Add to dashboard Cite

In this paper, we consider using profit/loss histories of multiple automated trading systems (ATSs) as N input variables in portfolio management. By means of multivariate statistical analysis and simulation studies, we analyze the influences of sample size (L) and input dimensionality on the accuracy of determining the portfolio weights. We find that degradation in portfolio performance due to inexact estimation of N means and N(N - 1)/2 correlations is proportional to N/L; however, estimation of N variances does not worsen the result. To reduce unhelpful sample size/dimensionality effects, we perform a clustering of N time series and split them into a small number of blocks. Each block is composed of mutually correlated ATSs. It generates an expert trading agent based on a nontrainable 1/N portfolio rule. To increase the diversity of the expert agents, we use training sets of different lengths for clustering. In the output of the portfolio management system, the regularized mean-variance framework-based fusion agent is developed in each walk-forward step of an out-of-sample portfolio validation experiment. Experiments with the real financial data (2003-2012) confirm the effectiveness of the suggested approach.

show abstract

Section: B In-sample and Out-of-sample Standard Portfoliomentioning

confidence: 98%

“…In [34], the objective was directed toward developing an evolvable MAS aimed at finding the proper values of parameters just mentioned. In this approach, a multitude of "expert trading agents" based on N A input ATSs were designed and compared on the basis of training set information (N A < N).…”

Section: B Multiagent Atssmentioning

confidence: 99%

Portfolio of Automated Trading Systems: Complexity and Learning Set Size Issues

Raudys

2013

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Let us mention some examples. In Raudys (2011, 2012), decisions of portfolio management are considered in the context of artificial intelligence. In the paper of Ramanauskas and Rutkauskas (2009), an artificial stock market is simulated by learning agents.…”

Section: Introductionmentioning

confidence: 99%

On the Optimization of Investment Strategies in the Context of Virtual Financial Market by the Individual Approach to Risk

Mockus¹,

Katin²,

Katina³

2014

Informatica

View full text Add to dashboard Cite

The optimal financial investment (Portfolio) problem was investigated by leading financial organizations and scientists. Nobel prizes were awarded for the Modern Portfolio Theory (MPT) and further developments. The aim of these works was to define the optimal diversification of the assets depending on the acceptable risk level.In contrast, the objective of this work is to provide a flexible, easily adaptable model of virtual financial markets designed for the needs of individual users in the context of utility theory. The aim is to optimize investment strategies. This aim is the new element of the proposed model and simulation system since optimization is performed in the space of investment strategies; both short term and longer term.The new and unexpected result of experiments with the historical financial time series using the PORTFOLIO model is the observation that the minimal prediction errors do not provide the maximal profits.

show abstract

Agent-based modelling of excitation propagation in social media groups

Plikynas

Raudys

2014

Journal of Experimental & Theoretical Artificial Intelligen

View full text Add to dashboard Cite

Three decision making levels in portfolio management

Cited by 4 publications

References 22 publications

Portfolio of Automated Trading Systems: Complexity and Learning Set Size Issues

Portfolio of Automated Trading Systems: Complexity and Learning Set Size Issues

On the Optimization of Investment Strategies in the Context of Virtual Financial Market by the Individual Approach to Risk

Agent-based modelling of excitation propagation in social media groups

Contact Info

Product

Resources

About