Quantitative Finance

Lütkebohmert, Eva;Sester, Julian;Shen, Hongyi

doi: 10.48550/arxiv.2311.13802pmid: N/A

Abstract:Sovereign loan portfolios of Multilateral Development Banks (MDBs) typically consist of only a small number of borrowers and hence are heavily exposed to single name concentration risk. Based on realistic MDB portfolios constructed from publicly available data, this paper quantifies the magnitude of the exposure to name concentration risk using exact Monte Carlo simulations. In comparing the exact adjustment for name concentration risk to its analytic approximation as currently applied by the major rating agency Standard & Poor's, we further investigate whether current capital adequacy frameworks for MDBs are overly conservative. Finally, we discuss the choice of appropriate model parameters and their impact on measures of name concentration risk.

He, Jiaer;Rivera, Roberto

doi: 10.48550/arxiv.2311.06282pmid: N/A

Abstract:Popular investment structured products in Puerto Rico are stock market tied Individual Retirement Accounts (IRA), which offer some stock market growth while protecting the principal. The performance of these retirement strategies has not been studied. This work examines the expected return and risk of Puerto Rico stock market IRA (PRIRAs) and compares their statistical properties with other investment instruments before and after tax. We propose a parametric modeling approach for structured products and apply it to PRIRAs. Our method first estimates the conditional expected return (and variance) of PRIRA assets from which we extract marginal moments through the Law of Iterated Expectation. Our results indicate that PRIRAs underperform against investing directly in the stock market while still carrying substantial risk. The expected return of the stock market IRA from Popular Bank (PRIRA1) after tax is slightly greater than that of investing in U.S. bonds, while PRIRA1 has almost two times the risk. The stock market IRA from Universal (PRIRA2) performs similarly to PRIRA1, while PRIRA2 has a lower risk than PRIRA1. PRIRAs may be reasonable for some risk-averse investors due to their principal protection and tax deferral.

Wang, Meng;Wang, Tai-Ho

doi: 10.48550/arxiv.2311.06476pmid: N/A

Abstract:The problem of order execution is cast as a relative entropy-regularized robust optimal control problem in this article. The order execution agent's goal is to maximize an objective functional associated with his profit-and-loss of trading and simultaneously minimize the execution risk and the market's liquidity and uncertainty. We model the market's liquidity and uncertainty by the principle of least relative entropy associated with the market volume. The problem of order execution is made into a relative entropy-regularized stochastic differential game. Standard argument of dynamic programming yields that the value function of the differential game satisfies a relative entropy-regularized Hamilton-Jacobi-Isaacs (rHJI) equation. Under the assumptions of linear-quadratic model with Gaussian prior, the rHJI equation reduces to a system of Riccati and linear differential equations. Further imposing constancy of the corresponding coefficients, the system of differential equations can be solved in closed form, resulting in analytical expressions for optimal strategy and trajectory as well as the posterior distribution of market volume. Numerical examples illustrating the optimal strategies and the comparisons with conventional trading strategies are conducted.

Wen, Chengyao;Lou, Yin

doi: 10.1145/3637528.3671521pmid: N/A

Abstract:Rules are widely used in Fintech institutions to make fraud prevention decisions, since rules are highly interpretable thanks to their intuitive if-then structure. In practice, a two-stage framework of fraud prevention decision rule set mining is usually employed in large Fintech institutions; Stage 1 generates a potentially large pool of rules and Stage 2 aims to produce a refined rule subset according to some criteria (typically based on precision and recall). This paper focuses on improving the flexibility and efficacy of this two-stage framework, and is concerned with finding high-quality rule subsets in a bi-objective space (such as precision and recall). To this end, we first introduce a novel algorithm called SpectralRules that directly generates a compact pool of rules in Stage 1 with high diversity. We empirically find such diversity improves the quality of the final rule subset. In addition, we introduce an intermediate stage between Stage 1 and 2 that adopts the concept of Pareto optimality and aims to find a set of non-dominated rule subsets, which constitutes a Pareto front. This intermediate stage greatly simplifies the selection criteria and increases the flexibility of Stage 2. For this intermediate stage, we propose a heuristic-based framework called PORS and we identify that the core of PORS is the problem of solution selection on the front (SSF). We provide a systematic categorization of the SSF problem and a thorough empirical evaluation of various SSF methods on both public and proprietary datasets. On two real application scenarios within Alipay, we demonstrate the advantages of our proposed methodology over existing work.

Azzone, Michele;Pocelli, Maria Chiara;Stocco, Davide

doi: 10.48550/arxiv.2311.12450pmid: N/A

Abstract:Sustainable investing refers to the integration of environmental and social aspects in investors' decisions. We propose a novel methodology based on the Triangulated Maximally Filtered Graph and node2vec algorithms to construct an hedging portfolio for climate risk, represented by various risk factors, among which the CO2 and the ESG ones. The CO2 factor is strongly correlated consistently over time with the Utility sector, which is the most carbon intensive in the S&P 500 index. Conversely, identifying a group of sectors linked to the ESG factor proves challenging. As a consequence, while it is possible to obtain an efficient hedging portfolio strategy with our methodology for the carbon factor, the same cannot be achieved for the ESG one. The ESG scores appears to be an indicator too broadly defined for market applications. These results support the idea that bank capital requirements should take into account carbon risk.

Li, Yinheng;Wang, Shaofei;Ding, Han;Chen, Hang

doi: 10.48550/arxiv.2311.10723pmid: N/A

Abstract:Recent advances in large language models (LLMs) have opened new possibilities for artificial intelligence applications in finance. In this paper, we provide a practical survey focused on two key aspects of utilizing LLMs for financial tasks: existing solutions and guidance for adoption. First, we review current approaches employing LLMs in finance, including leveraging pretrained models via zero-shot or few-shot learning, fine-tuning on domain-specific data, and training custom LLMs from scratch. We summarize key models and evaluate their performance improvements on financial natural language processing tasks. Second, we propose a decision framework to guide financial professionals in selecting the appropriate LLM solution based on their use case constraints around data, compute, and performance needs. The framework provides a pathway from lightweight experimentation to heavy investment in customized LLMs. Lastly, we discuss limitations and challenges around leveraging LLMs in financial applications. Overall, this survey aims to synthesize the state-of-the-art and provide a roadmap for responsibly applying LLMs to advance financial AI.

Cao, Zhiyu;Feinstein, Zachary

doi: 10.48550/arxiv.2311.05977pmid: N/A

Abstract:Price-mediated contagion occurs when a positive feedback loop develops following a drop in asset prices which forces banks and other financial institutions to sell their holdings. Prior studies of such events fix the level of market liquidity without regards to the level of stress applied to the system. This paper introduces a framework to understand price-mediated contagion in a system where the capacity of the market to absorb liquidated assets is determined endogenously. In doing so, we construct a joint clearing system in interbank payments, asset prices, and market liquidity. We establish mild assumptions which guarantee the existence of greatest and least clearing solutions. We conclude with detailed numerical case studies which demonstrate the, potentially severe, repercussions of endogenizing the market liquidity on system risk.

Zhang, Wentao;Zhao, Yilei;Sun, Shuo;Ying, Jie;Xie, Yonggang;Song, Zitao;Wang, Xinrun;An, Bo

doi: 10.48550/arxiv.2311.10801pmid: N/A

Abstract:Portfolio management (PM) is a fundamental financial trading task, which explores the optimal periodical reallocation of capitals into different stocks to pursue long-term profits. Reinforcement learning (RL) has recently shown its potential to train profitable agents for PM through interacting with financial markets. However, existing work mostly focuses on fixed stock pools, which is inconsistent with investors' practical demand. Specifically, the target stock pool of different investors varies dramatically due to their discrepancy on market states and individual investors may temporally adjust stocks they desire to trade (e.g., adding one popular stocks), which lead to customizable stock pools (CSPs). Existing RL methods require to retrain RL agents even with a tiny change of the stock pool, which leads to high computational cost and unstable performance. To tackle this challenge, we propose EarnMore, a rEinforcement leARNing framework with Maskable stOck REpresentation to handle PM with CSPs through one-shot training in a global stock pool (GSP). Specifically, we first introduce a mechanism to mask out the representation of the stocks outside the target pool. Second, we learn meaningful stock representations through a self-supervised masking and reconstruction process. Third, a re-weighting mechanism is designed to make the portfolio concentrate on favorable stocks and neglect the stocks outside the target pool. Through extensive experiments on 8 subset stock pools of the US stock market, we demonstrate that EarnMore significantly outperforms 14 state-of-the-art baselines in terms of 6 popular financial metrics with over 40% improvement on profit.

James, Nick;Menzies, Max

doi: 10.1209/0295-5075/ad1ef2pmid: N/A

Abstract:We introduce new mathematical methods to study the optimal portfolio size of investment portfolios over time, considering investors with varying skill levels. First, we explore the benefit of portfolio diversification on an annual basis for poor, average and strong investors defined by the 10th, 50th and 90th percentiles of risk-adjusted returns, respectively. Second, we conduct a thorough regression experiment examining quantiles of risk-adjusted returns as a function of portfolio size across investor ability, testing for trends and curvature within these functions. Finally, we study the optimal portfolio size for poor, average and strong investors in a continuously temporal manner using more than 20 years of data. We show that strong investors should hold concentrated portfolios, poor investors should hold diversified portfolios; average investors have a less obvious distribution with the optimal number varying materially over time.

Azzabi, Anas;Lahrichi, Younes

doi: 10.32038/ncaf.2023.09.03pmid: N/A

Abstract:Banks' performance is an important topic for both professionals and researchers. Given the important literature on this subject, this paper aims to bring an up-to-date and organized review of literature on the determinants of banks performance. This paper discusses the main approaches that molded the debate on banks performance and their main determinants. An in-depth understanding of these latter may allow on the one hand, bank managers and regulators to improve the sector efficiency and to deal with the new trends shaping the future of their industry and on the other hand, academicians to enrich research and knowledge on this field. Through the analysis of 54 studies published in 42 peer-reviewed journals, we show that despite the importance of the existent literature, the subject of bank performance factors did not reveal all its secrets and still constitute a fertile field for critical debates, especially since the COVID-19 and the increasingly pressing rise in power of digital transformation and artificial intelligence in general and FinTechs in particular. The study concludes by suggesting new promising research avenues.