Angel Marchev

University of National and World Economy | UNWE · Department of Management

The precise forecasting of bus arrival times is an important element of implementing on demand city transport. This research uses of Long Short Term Memory (LSTM) networks for predicting bus arrival times in Sofia, Bulgaria. We evaluate the LSTM model against advanced models such as ARIMAX, VARX SARIMAX with Fourier terms Vector Autoregression, Bay...

This manuscript presents a rigorous examination and reconstruction of a risk preference questionnaire, identifying opportunities for augmenting its diagnostic precision. An initial analysis underscored a significant disparity in the responses to the first and latter halves of the questionnaire. The in-depth statistical probe, employing Cronbach's A...

This article explores methods for generating synthetic data, algorithmically created for testing and training machine learning models. Probabilistic approaches, such as Monte Carlo simulation and Generative Adversarial Networks (GANs), rely on random sampling. Non-probabilistic methods, like Inverse Copula Sampling and Cholesky Decomposition, prese...

This paper presents a novel approach to generating synthetic data arrays that address the scarcity of datasets containing sensitive information due to restrictions imposed by legislation such as the GDPR and the Bank Secrecy Act. By integrating statistical methods, including Monte-Carlo simulation and Cholesky decomposition, with business logic, t...

This research paper explores the concept of customized fintech investment services, focusing on individualization, diversification, and the construction algorithm of such services. The study highlights the importance of diversification in investment portfolios, emphasizing its role in minimizing risk levels and increasing profitability by includin...

Developing multifaceted contemporary individuals implies that they have to be constructed as one whole system, as well as provide for their creative realization. In order to improve the training of university students, innovative models for conducting lectures and seminars should be implemented. The change in curricula should meet the social requir...

We develop a general framework for analysis and prediction of air pollution in the city of Sofia, Bulgaria, as measured by the level of the PM10 air pollutant indicator. As a starting point in our analysis, we consider earlier findings documented in the literature. We focus on utilized methodology so as to support the process of defining proper pre...

This document describes the methodical approaches for Module 5 of INNOAIR On-demand Public Transport Platform for route optimization and, in particular, for travel times predictions. The text presents the chosen models of travel time between stops. There are four predictive models presented – all of which have been tested on a particular use-case d...

This paper presents six different methods to synthesize data sets consisting of personal anonymized multi-dimensional data set. A quick comparative analysis is done at the end. The data is required for various business uses where there is a need to identify the basic individual characteristics of group of persons, without using actual non-sanctione...

This study is part of bigger research about self-learning systems for the management of individualized investment portfolios. In this research, we present several approaches for generating multi-dimensional synthetic data in conformity with business logic, correlations, previous datasets, concatenation, neural networks, etc. Each approach is descri...

Abstract: This study is part of bigger research about self-learning systems for the management of individualized investment portfolios. This paper emphasizes on necessity of multi-dimensional data for banking services in setting up a predictive model. This paper presents an approach to simulating the multi-dimensional data in conformity with the bu...

Abstract: This paper considers a conceptual model of an individualized system for managing individualized investment portfolios. The dynamic development of technologies creates an opportunity for a fundamental change in the markets for investment products. An entirely new field for investments appears, which is determined by the changed client's at...

Following previous work this paper analyzes the portfolio investment process in the terms of a cybernetic system where the portfolio is the controlled system and the investor is the controlling system. As of now the financial markets have become very dynamic and complex environment which requires means of autonomy of the portfolio investment proces...

In this paper we present an implementation of pricing algorithm for single and double barrier options and its suitability for real-world applications. A detailed analysis of the applied algorithm is accompanied by implementation in C++ (source code included) that is then compared to existing solutions in terms of efficiency and computational power....

In this paper we discuss the numerical algorithm of Milev-Tagliani [25] used for pricing of discrete double barrier options. The problem can be reduced to accurate valuation of an n-dimensional path integral with probability density function of a multivariate normal distribution. The efficient solution of this problem with the Milev-Tagliani algori...

Following previous work this paper analyzes the portfolio investment process in the terms of a cybernetic system where the portfolio is the controlled system and the investor is the controlling system. Among the many proposed approaches for managing an investment portfolio there are those which borrow ideas from non-financial fields. This paper...

Following previous work this paper analyzes the portfolio investment process in the terms of a cybernetic system where the portfolio is the controlled system and the investor is the controlling system. Among the many proposed approaches for managing an investment portfolio there are those which borrow ideas from non-financial fields. This paper pro...

Building on the notion of systematically analyzing investment portfolio as a feedback system, there is a need of experimentation system. In this paper such system for experimenting with various traditional, classical, advanced, etc. models for portfolio management is described. The main objective is to have the ability to compete the models systema...

The theory of investment portfolios is a well defined component of financial science. While sound in principle, it faces some setbacks in its real-world implementation. In this paper the authors propose a reformulation of the investment portfolio problem as a cybernetic system where the Investor is the controlling system and the portfolio is the...

The theory of investment portfolios is a well defined component of financial science. While sound in principle, it faces some setbacks in its real-world implementation. The authors state that cybernetics present an unorthodox "new" way of studying the process of portfolio management. First, the known theory is translated in cybernetic terminology....

The portfolio investment process could be analyzed in the terms of a cybernetic system where the portfolio is the controlled system and the investor is the controlling system. While this paper continues previous work in the field, it proposes a new approach for generating possible solutions to the investment portfolio problem using multi-stage sele...

Nowadays a large number of IT solutions, facilitating Knowledge Management (KM) and Knowledge Sharing (KS) are available in the market, but different studies (KPMG, 2004) prove that they still remain moderately used in practice. KS is recognized as an increasingly important KM problem because it influences the capacity of the organization to absorb...

This paper presents a new fuzzy approach for the evaluation of investment portfolio, where the approach is viewed by the authors as a sub-phase of the management process of these port-folios. The approach defines the mutual and delayed effects among the significant variables of the investment portfolio. The evaluation of the effects is described as...

The main focus of this paper is on proposing a new fuzzy approach for evaluating investment portfolios. The approach suggested uses tools of the theory of confidence intervals, theory of fuzzy subsets and the method of expertise. Using the mentioned instrumentarium an empirical approbation is conducted. The approbation is realized through the case...

The theory of investment portfolios is a well defined component of the financial science. And while sound in principle it faces some setbacks in its real-world implementation. The authors state that cybernetics present an unorthodox “new” way of studying the process of portfolio management. First, the known theory is translated in cybernetic termin...