Norbert Fogarasi

• PhD
• Researcher at Budapest University of Technology and Economics

This paper introduces an effective convergence trading algorithm for mean reverting portfolios using Long Short Term Memory (LSTM) neural networks. Utilizing known techniques for selection of sparse, mean reverting portfolios from asset dynamics following the VAR(1) model, we introduce a 2-step technique to effectively trade the optimal portfolio....

We study the problem of selecting a sparse, mean reverting portfolio from a universe of assets using simulated annealing (SA). Assuming that assets follow a first order vector autoregressive process (VAR(1)), we make a number of improvements in existing methods. First, we extend the underlying asset dynamics to include a time-independent additive t...

Quantum computers have the potential to provide quadratic speedup for Monte Carlo methods currently used in various classical applications. In this work, we examine the advantage of quantum computers for financial option pricing with the Monte Carlo method. Systematic and statistical errors are handled in a joint framework, and a relationship to qu...

We investigated the predictability of mean reverting portfolios and the VAR(1) model in several aspects. First, we checked the dependency of the accuracy of VAR(1) model on different data types including the original data itself, the return of prices, the natural logarithm of stock and on the log return. Then we compared the accuracy of predictions...

In this paper, a Nonlinear AutoRegressive network with eXogenous inputs and a support vector machine are proposed for algorithmic trading by predicting the future value of financial time series. These architectures are capable of modeling and predicting vector autoregressive VAR(p) time series. In order to avoid overfitting, the input is pre-proces...

In this article, a novel algorithm is developed for electronic trading on financial time series. The new method uses quantization and volatility information together with feedforward neural networks for achieving high-frequency trading (HFT). The proposed procedures are based on estimating the Forward Conditional Probability Distribution (FCPD) of...

In this paper, a novel algorithm is developed for electronic trading on financial time series. The new method uses quantization and volatility information together with FeedForward Neural Networks (FFNN) for achieving High Frequency Trading (HFT). The proposed procedures are based on estimating the Forward Conditional Probability Distribution (FCPD...

Let n and k be integers such that n ≥ 2 and 1 ≤ k ≤ n. In this paper, we consider the problem of finding an ordered list of the k best players out of n participants by organizing a tournament of rounds of pairwise matches (comparisons). Assuming that (i) in each match there is a winner (no ties) (ii) the relative strength of the players is constant...

In this paper, a Nonlinear AutoRegressive network with eX-ogenous inputs (NARX) is proposed for algorithmic trading by predicting the future value of financial time series. This network is highly capable of modeling vector autoregressive VAR(p) time series. In order to avoid overfitting, the input is pre-processed by Independent Component Analysis...

Polynomial time heuristic optimization methods applied to problems in computational finance Norbert Fogarasi, Ph.D. dissertation

We study the problem of finding sparse, mean reverting portfolios based on multivariate historical time series. After mapping the optimal portfolio selection problem into a generalized eigenvalue problem, we propose a new optimization approach based on the use of simulated annealing. This new method ensures that the cardinality constraint is automa...

This paper explores novel, polynomial time, heuristic, approximate solutions to the NP-hard problem of finding the optimal job schedule on identical machines which minimizes total weighted tardiness (TWT). We map the TWT problem to quadratic optimization and demonstrate that the Hopfield Neural Network (HNN) can successfully solve it. Furthermore,...

This paper explores fast, polynomial time heuristic approximate solutions to the NP-hard problem of scheduling jobs on N identical machines. The jobs are independent and are allowed to be stopped and restarted on another machine at a later time. They have well-de?ned deadlines, and relative priorities quantified by non-negative real weights. The ob...

We examine the problem of finding sparse, mean reverting portfolios based on multivariate historical time series. After mapping optimal portfolio selections into a generalized eigenvalue problem, two different heuristic algorithms are referenced for finding the solution in a subspace which satisfies the cardinality constraint. Having identified the...

In this paper, we study the problem of finding sparse, mean reverting portfolios in multivariate time series. This can be applied to developing profitable convergence trading strategies by identifying portfolios which can be traded advantageously when their prices differ from their identified long-term mean. Assuming that the underlying assets foll...