Search

This paper provides a comprehensive review of the application of Reinforcement Learning (RL) in the domain of finance, shedding light on the groundbreaking progress achieved andthe challenges that lie ahead. We explore how RL, a subfield of machine learning, has been instrumental in solving complex financial problems by enabling decision-making processes that optimize long-term rewards. Reinforcement learning (RL) is a powerful machinelearning technique that can be used to train agents to make decisions in complex environments. In finance, RL has been used to solve a variety of problems, including optimal execution, portfolio optimization, option pricing and hedging, market making, smart order routing, and robo-advising. In this paper, we review the recent developments in RL for finance. We begin by introducing RL and Markov decision processes (MDPs), which is the mathematical framework for RL. We then discuss the various RL algorithms that have beenused in finance, with a focus on value-based and policy-based methods. We also discuss the use of neural networks in RL for finance. Finally, we discuss the results of recent studies that have used RL to solve financial problems. We conclude by discussing the challenges and opportunities for future research in RL for finance. [ABSTRACT FROM AUTHOR]

Early termination is a contractual compensation mechanism implemented in ppp infrastructure projects where private investors have the right to abandon the project to mitigate risks such as traffic risk. In this paper we used the Real Options Theory to value early termination as an option to abandon a project where both the traffic risk and the compensation fee are modelled assuming correlated stochastic processes. The option pricing model was implemented with an analytical solution and results were compared with the Monte Carlo simulation technique. The results confirm the benefits that the contractual mechanism offers to private investors to mitigate risks, while at the same time improving a project's value. [ABSTRACT FROM AUTHOR]

Simulations and empirical studies suggest that incorporating a discontinuous jump process in asset pricing models improve volatility forecasting, pricing of instruments, and hedging positions in a portfolio. In this paper we analyze high frequency market data of Colombian sovereign bonds to study the presence or absence of discontinuities in the price generating process. We find that Colombian sovereign debt experiments jumps across all maturities but with different frequencies, in particular, we do not find that long term bonds jump less frequently than short term bonds. Furthermore, bonds with closer maturities cojump in greater magnitude than those with a greater distance between them. Finally, we find significant day-of-the-week effects, as well as an important increase in the jump frequency due to surprises in economic information related to US monetary policy, and no effect due to direct monetary policy announcements in Colombia. [ABSTRACT FROM AUTHOR]

This paper presents the main theoretical developments of modern portfolio theory. At first, the fundamental elements of the Markowitz mean-variance model (MV), its formulation and solution of the optimization problem, as well as its limitations, are introduced. Then, different extensions of the MV model are presented by introducing alternative risk measures, as well as the adjustments of the portfolio construction model. In that sense, the downside risk approach is presented. Finally, robust portfolio approaches are introduced considering Bayesian, robust optimization, and risk-parity approaches. From these novel approaches, the adjustments that allow us overcoming some of the limitations of the MV model are highlighted. Also, recent developments that extend the original formulations of the portfolio model to address new challenges and current issues are introduced. [ABSTRACT FROM AUTHOR]

This paper explores the effect of the frequency of data on the accuracy (measure by variance) of the maximum likelihood estimator (MLE) of the trend parameter μ in a jump-diffusion process à la Press (1967). First, we consider the case without jumps (i.e., the geometric Brownian motion (GBM)) as a benchmark case to show that the frequency of data is irrelevant in this first setting. Then, we consider the case with jumps and highlight that things are different in this second situation. Specifically, the asymptotic variance of the MLE of the trend parameter turns out to be higher compared to the case without jumps. Nevertheless, we also prove that when sampling occurs infinitely often (i.e., high frequency) it is possible to obtain the same accuracy for the MLE of μ as for the GBM, given that for higher frequencies it is easier to "identify" price discontinuities (i.e., jumps) for this model. Mathematical proofs are performed under the assumption that the MLE of μ is estimated given the other parameters, but numerical (Montecarlo) simulations indicate that this is also the case even when all parameters are estimated together. [ABSTRACT FROM AUTHOR]

The financial cycle consists of the joint evolution of asset prices and credit aggregates. Its regularity has been abundantly studied for panels of countries which regularly include developed countries and sometimes include less developed or developing countries. This paper employs an innovative methodology to analyze the Colombian financial cycle from time series and bivariate perspectives. First, we characterize expansions and contractions in the stock market and the real exchange rate. These are two distinct asset classes that play an essential role as stores of value in middle-income countries. Our analysis is completed by identifying bull and bear phases in the local-currency credit market. We test the hypothesis that the changes in regulation that originated with the end-of-century crisis in the country impacted the evolution of asset prices and credit aggregates. We find that the amplitude and severity of contraction phases decreased post-reforms, which may signal the success of the new regulation. We find no effect on the behaviour of asset prices and argue that this is to be expected since they were not targeted. Finally, we find that the joint movement of stocks and credit peaks during financial crises and troughs during economic expansions, consistent with findings in the international literature. [ABSTRACT FROM AUTHOR]

Historically, financial instability has been encouraged changes in the regulation of banking institutions. This paper deals with the first banking experiences occurred in Argentina, Brazil, Spain and Portugal and their crises in the first half of the 19th century. As issuing banks, the main obstacle that these institutions had to overcome was to guarantee the convertibility of their bank notes. In all countries the state intervened, initially and in general, granting the issuing privilege in exchange for economic favors. This had a negative impact on the first banking experiences, mostly unsuccessful. The surviving banks received support from the state to continue, but also had more restrictive regulations regarding issuance. In the analyzed cases, the banking crises produced changes in the regulation of banks. [ABSTRACT FROM AUTHOR]

Real Options Theory arose as an alternative to valuate flexibilities entrenched in projects and has acquired popularity since the end of the twentieth century. Through bibliometric methods and graph theory, this paper develops an analysis of the collaboration network comprised of Real Options' researchers, including scientific papers from over the last eighteen years. In this effort, we meticulously identify authors and their co-authorship alliances, finding a distinct topology without a giant component. Developing unweighted and weighted models, the network is unraveled, providing measurement from internationalization propensity and computing different impact metrics, which recognize the most relevant researchers on the subject. [ABSTRACT FROM AUTHOR]

In this paper we use second order stochastic dominance (hereafter, ssd) and the Omega ratio to measure us equity ETFs performance. Based on Balder and Schweizer's (2017) paper, consistency of the Omega ratio with ssd is illustrated through ETFs performance evaluation. The results presented in this paper show that ETFs ranked as superior for all non-satiated risk-averse investors (ssd) are also ranked as superior using the Omega ratio. In cases where the threshold parameter K with which the strategies are evaluated generates inconsistencies in the ranking between ssd and Omega, it is observed that ssd captures in a more complete way the effect in all the moments of the distribution as compared to Omega. [ABSTRACT FROM AUTHOR]

Since the development of the EGARCH (Exponential General Autoregressive conditional Heteroskedastic process) by Nelson (1991), several authors have reported presence of asymmetry on stock return volatility. This phenomenon has been widely explained as the leverage effect. However, no strong evidence has been described in developed market exchange rate series. Thus, the objective. of this paper is to extend the analysis, testing exchange rate series on emerging markets for asymmetry in volatility. In emerging markets, elements as country risk, economy size and investors' confidence can cause that negative and positive returns affect the volatility level differently. Finally, after applying several methods to evaluate and compare the selected model forecastings, weak in-sample evidence of asymmetry that completely disappeared out-of-sample is reported. [ABSTRACT FROM AUTHOR]

This paper presents the Hierarchical Risk Parity (hrp) approach proposed by López de Prado (2016, 2018, 2020) for the construction of optimal investment portfolios using unsupervised learning, hierarchical clustering, which allow overcome some limitations of the Mean-Variance (MV) model, in particular those related to the need to invert the covariance matrix when implementing the cla algorithm. A sample of 7 assets from the American market is taken, with which an application of the hrp algorithm proposed by López de Prado is carried out, finding that under this model the distribution of assets in different clusters generates improvements in terms of the expected return, as well as of the Sharpe coefficient compared to the results of the Mean-Variance portfolio. [ABSTRACT FROM AUTHOR]

In this paper we implemented a Bayesian robust optimization model to select an optimal investment portfolio. To do that, we extended the model developed by Meucci, which consists of incorporating the Bayesian approach into the robust portfolio model in order to define an ellipsoidal-type uncertainty set under an Inverse Wishart Distribution. Thus, the uncertainty of the estimated parameters for create the robust counterpart in the portfolio model. The proposed model uses a Gamma distribution function, as a generalization of the Wishart function. Results confirm Meucci's conclusions and, it corroborates the properties attributed to those portfolios. [ABSTRACT FROM AUTHOR]

This paper presents an approach for socially responsible investment portfolio selection through the incorporation of esg criteria: environment (A), social (S) and of good governance (G); to the Markowitz's mean-variance (MV) model. For that, different formulations of the MV optimization problem are revised, as well as its adjustment to incorporate these indicators in the construction and optimization of the portfolio. This new approach, known as the MV-esg model, allows the construction of a complete set of feasible optimal portfolios based on the three relationships: return, risk and the esg score; resulting in an efficient surface (ES) on a three-dimensional space. Results show that the achievement of an increasingly higher esg indicator not only reduces the performance of the portfolio with respect to the MV portfolio, but also reduces its risk diversification capacity. However, the fact that the incorporation of esg criteria allows investors to incorporate their preferences to minimize the social and environmental impact of their investments is highlighted, since the optimal esg portfolio generates better indicators than any portfolio that pursue only the optimal risk-return ratio, in addition to outperforming the benchmark. [ABSTRACT FROM AUTHOR]

Robust optimization (OR) models have made it possible to overcome the limitations of the mean-variance (MV) model, which involves the traditional approach for the optimal portfolio selection, by incorporating the uncertainty of the model parameters (expected returns and covariances). In this paper, the or advances in portfolio theory are presented using the worst-case approach, from which the robust formulations for the mv model are incorporated, considering the Markowitz and Sharpe works. From these formulations, a straightforward application is implemented where the advantages and benefits of the robust counterparts are highlighted compared to the original MV model. At the end, a brief discussion of additional formulations regarding uncertainty sets and other performance measures is presented. [ABSTRACT FROM AUTHOR]

Given the high popularity that collective investment funds (cifs) have been gaining and their growing participation in the financial market, both in terms of the amount of investments and the number of investors, it is necessary to have tools that allow for adequate and timely identification of risks, in order to prevent an effect on the stability of the financial system. However, there is a lack of literature on early warnings for these funds, since most of the papers are focused on the banking sector. This document aims to develop an early warning indicator that allows the identification of cif vulnerabilities, with enough time of anticipation for policymakers to implement measures for their containment. In order to achieve this objective, a widely known early warning measure in the banking sector, such as the European Central Bank's Domestic Systemic Risk Indicator (d-SRI), will be adapted to the cif scenario in Colombia. The results obtained show that in the event of a shock of one standard deviation in the cif early warning indicator (iate fic), a drop of 1.4 percentage points in the quarterly growth of the fund's net value (fnv) is expected in the six months following the occurrence of the shock. The findings showed in this work represent an important advance in the detection of vulnerabilities of investment funds and can be of great help to policymakers in making decisions under scenarios of uncertainty in the future behavior of the cif industry. [ABSTRACT FROM AUTHOR]

The binomial model presents a set of properties that make it a suitable approach in order to value the real options, throughout an easy and practical application. This is possible by the adaptation of the valuation principle for non-arbitrage, own of the options pricing theory. However, their adoption may be limited for those options that have multiple sources of uncertainty, given that their interaction should be incorporated into the valuation process. In response, financial theory has proposed valuation approaches that allow different sources of uncertainty to be represented by a consolidated estimate of volatility, such as the Marketed Asset Disclaimer (mad) approach developed by Copeland and Antikarov (2001). As an alternative, a treatment that incorporates the dynamics of each uncertainty can be given. In this context, there are different proposals that extend the Binomial model to k-dimensional or multi-dimensional context. To achieve the application, it is necessary an approximation of the k-dimensional stochastic process, as well as its correlations. This paper presents a concise review of the different methods proposed in this context, as well as their benefits, limitations and, some alternative approaches. [ABSTRACT FROM AUTHOR]

The implementation of trading strategies through computational tools and artificial intelligence, such as artificial neural networks (ann) and genetic algorithms (ag), have presented important advances in the last years, In this paper it is implemented a ag for the optimization of a trading strategy with two moving averages in the inter-day market of crude oil futures. The objective function is the global return of the investment. The document presents the methodology and the design of this investment strategy with consistent results even with out-of-sample data. [ABSTRACT FROM AUTHOR]

This paper identifies the main contributions of Stephen Ross to the definition of the basic principles of the fundamental theorem of asset pricing (ftap), as well as its applications and extensions. By establishing the equivalence between the absence of arbitrage and the existence of a linear asset pricing rule, Ross formulates the principles of a valuation approach that preserves the essential characteristics of the Black-Scholes model, but from a more simple and intuitive framework. [ABSTRACT FROM AUTHOR]

This paper presents the weather derivatives pricing model developed by Alaton et al. (2002) and it proposes an application by use this model with Monte Carlo simulation technique (mc), with the goal of assessing a barrier option (such as weather option) for the rice sector on Yopal (Colombia) by involving critical temperature thresholds for cultivation. Thus, the temperature behavior (underlying) is modeled by the technique of mc assuming a stochastic process with a mean reversion of type Ornstein-Uhlenbeck. The results show that this type of hedging mechanisms becomes a feasible alternative with great potential for implementation. [ABSTRACT FROM AUTHOR]

This paper analyzes the pretrading transparency of the trm futures market in Colombia and its relation to information asymmetry in out-of-stock trading operations between informed and uninformed agents. It is concluded that the transaction records are used by the market intermediaries to generate transactions outside of the available prices via the engine of the bvc and thus, take advantage of its dominant position as an informed agent. Additionally, it is argued that in order to eliminate this advantage, operations between agents classified own position (informed) and customers (not informed), should not be carried out via registration but only using the stock engine. [ABSTRACT FROM AUTHOR]

This paper analyzes the pretrading transparency of the TRM futures market in Colombia and its relation to information asymmetry in out-of-stock trading operations between informed and uninformed agents. It is concluded that the transaction records are used by the market intermediaries to generate transactions outside of the available prices via the engine of the BVC and thus, take advantage of its dominant position as an informed agent. Additionally, it is argued that in order to eliminate this advantage, operations between agents classified own position (informed) and customers (not informed), should not be carried out via registration but only using the stock engine. [ABSTRACT FROM AUTHOR]

In this paper, the importance of Ito's lemma in the field of corporate finance is highlighted. Thus, the main application fields are identified when stochastics processes adapt following the Black-Scholes-Merton valuation model of financial options and the partial differential equation to model the value of real assets and investment projects under the CCA approach. These developments have allowed to manage corporate problems, following the same structure of financial options models. Similarly, the advantages of this application in order to make valuations under uncertainty are highlighted, so that it could be overcome the limitations of the traditional approach (discounted cash flow - DCF). [ABSTRACT FROM AUTHOR]

The classical model for the behavior of the price of risky assets assumes constant volatility, which usually does not match the behavior of real assets. Alternatively stochastic volatility models, which have a higher number of parameters and difficulty in estimation arise. In the paper stochastic volatility models are described in the context of state space models, and how it may be done by applying the MCMC estimation algorithms. The problem of estimating the likelihood function in this type of models is considered, and how the Gibbs sampler is used in these cases. The empirical application is performed using series of Colombian stocks and concludes on the estimated volatility processes in the unobserved values ?? of such series. Extension to models with non-Gaussian noise and jumps is proposed. [ABSTRACT FROM AUTHOR]

As a result of the most recent global financial crisis, literature has embraced size, connectedness and substitutability as key indicators for financial institutions' systemic importance. This paper applies Principal Components Analysis to some metrics for assessing size, connectedness and substitutability, where those metrics rely on a combination of balance sheet data and the application of network theory to large-value payment system's information. The main results are the following: (i) the three concepts and their metrics are explanatory and non-redundant for differentiating financial institutions' relative systemic importance; (ii) these metrics allow the construction a PCA-based Systemic Importance Index, a valuable tool for financial authorities' policy and decision-making; and (iii the importance of the too-connected-to-fail criteria and the presence of non-banking firms among the most systemically important financial institutions in the Colombian case are confirmed. [ABSTRACT FROM AUTHOR]

Parisian options are a particular type of barrier option, where the activation or deactivation option is not only subject to the underlying price reaches and exceeds a certain threshold value, if not that the bypass must occur at an interval of longer than a time window established in the option. Have developed mainly two methods for evaluating these options, the method of inverse Laplace transform and partial differential equations approach. This paper presents the basic definitions related to this type of assessment options and characterized by the same Laplace transform. [ABSTRACT FROM AUTHOR]

Chamber risk of central counterpart have become one of the most important structural pillars of the financial markets in the world, both stand as a central counterparty for all transactions in capital markets and some OTC, establish schedules for operating the highly weighted Systems Robust Risk Management. This paper aims to outline the structure of this system, emphasizing on how to model the risk that these institutions take in pursuit of its objects. In this sense, the establishment of margins is established as a critical step and function of a schematic approach that integrates securities risk, stress scenarios, the most recent behavior of volatility, collateral formation, and the financial capacity of operators to settle its obligations on time. As a result, the margin / collateral, and limits on open positions is the end product of a Risk Management System to guarantee the integrity of the market. [ABSTRACT FROM AUTHOR]

The development of transactional platforms, has enabled the study of ever larger financial markets from the intraday perspective. However, we found a problem of high frequency data: the accumulation of microeconomic-noise. The following document develops, based on the methodology of Bandi and Russell 2002 and Barndorff-Nielsen and Shephard 2002, a theoretical and practical framework for tackling the problems of microeconomic noise in the estimation of diary volatility in the market for USP / COP. The conclusions of the paper point to an optimal intraday sampling spacing for 10 minutes. [ABSTRACT FROM AUTHOR]

This work is undertaken in an analysis of the growth of local public debt market, which has served the government as a mechanism for financing and restructuring of the debt profile, and the local capital market is dynamic and thrives as a source basis of methodologies exist for the valuation of financial assets, the market does not have indexes that meet the principles and purposes of a benchmark. This lack hinders the work of portfolio management, limits the ability of actors to make investment decisions, makes it difficult to analyze and compare the performance of the public debt market, while it undertakes. the development of financial products. So this paper describes the main methodological principles and foundations for the construction of rates of existing debt at the international level, then adjust them to the Colombian case. [ABSTRACT FROM AUTHOR]

This paper inquires into the flexibility of real assets as a quality that determines the existence of real options. It establishes an association between the types of real options and flexibility and also determines that the innovation is the dynamic force that creates new forms of flexibility. [ABSTRACT FROM AUTHOR]