The TruEnd-procedure: Treating trailing zero-valued balances in credit data ArXiv ID: 2404.17008 “View on arXiv” Authors: Unknown Abstract A novel procedure is presented for finding the true but latent endpoints within the repayment histories of individual loans. The monthly observations beyond these true endpoints are false, largely due to operational failures that delay account closure, thereby corrupting some loans. Detecting these false observations is difficult at scale since each affected loan history might have a different sequence of trailing zero (or very small) month-end balances. Identifying these trailing balances requires an exact definition of a “small balance”, which our method informs. We demonstrate this procedure and isolate the ideal small-balance definition using two different South African datasets. Evidently, corrupted loans are remarkably prevalent and have excess histories that are surprisingly long, which ruin the timing of risk events and compromise any subsequent time-to-event model, e.g., survival analysis. Having discarded these excess histories, we demonstrably improve the accuracy of both the predicted timing and severity of risk events, without materially impacting the portfolio. The resulting estimates of credit losses are lower and less biased, which augurs well for raising accurate credit impairments under IFRS 9. Our work therefore addresses a pernicious data error, which highlights the pivotal role of data preparation in producing credible forecasts of credit risk. ...

BERT vs GPT for financial engineering ArXiv ID: 2405.12990 “View on arXiv” Authors: Unknown Abstract The paper benchmarks several Transformer models [“4”], to show how these models can judge sentiment from a news event. This signal can then be used for downstream modelling and signal identification for commodity trading. We find that fine-tuned BERT models outperform fine-tuned or vanilla GPT models on this task. Transformer models have revolutionized the field of natural language processing (NLP) in recent years, achieving state-of-the-art results on various tasks such as machine translation, text summarization, question answering, and natural language generation. Among the most prominent transformer models are Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformer (GPT), which differ in their architectures and objectives. A CopBERT model training data and process overview is provided. The CopBERT model outperforms similar domain specific BERT trained models such as FinBERT. The below confusion matrices show the performance on CopBERT & CopGPT respectively. We see a ~10 percent increase in f1_score when compare CopBERT vs GPT4 and 16 percent increase vs CopGPT. Whilst GPT4 is dominant It highlights the importance of considering alternatives to GPT models for financial engineering tasks, given risks of hallucinations, and challenges with interpretability. We unsurprisingly see the larger LLMs outperform the BERT models, with predictive power. In summary BERT is partially the new XGboost, what it lacks in predictive power it provides with higher levels of interpretability. Concluding that BERT models might not be the next XGboost [“2”], but represent an interesting alternative for financial engineering tasks, that require a blend of interpretability and accuracy. ...

Interpretable Machine Learning Models for Predicting the Next Targets of Activist Funds ArXiv ID: 2404.16169 “View on arXiv” Authors: Unknown Abstract This research presents a predictive model to identify potential targets of activist investment funds–entities that acquire significant corporate stakes to influence strategic and operational decisions, ultimately enhancing shareholder value. Predicting such targets is crucial for companies aiming to mitigate intervention risks, activist funds seeking optimal investments, and investors looking to leverage potential stock price gains. Using data from the Russell 3000 index from 2016 to 2022, we evaluated 123 model configurations incorporating diverse imputation, oversampling, and machine learning techniques. Our best model achieved an AUC-ROC of 0.782, demonstrating its capability to effectively predict activist fund targets. To enhance interpretability, we employed the Shapley value method to identify key factors influencing a company’s likelihood of being targeted, highlighting the dynamic mechanisms underlying activist fund target selection. These insights offer a powerful tool for proactive corporate governance and informed investment strategies, advancing understanding of the mechanisms driving activist investment decisions. ...

Correlations versus noise in the NFT market ArXiv ID: 2404.15495 “View on arXiv” Authors: Unknown Abstract The non-fungible token (NFT) market emerges as a recent trading innovation leveraging blockchain technology, mirroring the dynamics of the cryptocurrency market. The current study is based on the capitalization changes and transaction volumes across a large number of token collections on the Ethereum platform. In order to deepen the understanding of the market dynamics, the collection-collection dependencies are examined by using the multivariate formalism of detrended correlation coefficient and correlation matrix. It appears that correlation strength is lower here than that observed in previously studied markets. Consequently, the eigenvalue spectra of the correlation matrix more closely follow the Marchenko-Pastur distribution, still, some departures indicating the existence of correlations remain. The comparison of results obtained from the correlation matrix built from the Pearson coefficients and, independently, from the detrended cross-correlation coefficients suggests that the global correlations in the NFT market arise from higher frequency fluctuations. Corresponding minimal spanning trees (MSTs) for capitalization variability exhibit a scale-free character while, for the number of transactions, they are somewhat more decentralized. ...

Market Making in Spot Precious Metals ArXiv ID: 2404.15478 “View on arXiv” Authors: Unknown Abstract The primary challenge of market making in spot precious metals is navigating the liquidity that is mainly provided by futures contracts. The Exchange for Physical (EFP) spread, which is the price difference between futures and spot, plays a pivotal role and exhibits multiple modes of relaxation corresponding to the diverse trading horizons of market participants. In this paper, we model the EFP spread using a nested Ornstein-Uhlenbeck process, in the spirit of the two-factor Hull-White model for interest rates. We demonstrate the suitability of the framework for maximizing the expected P&L of a market maker while minimizing inventory risk across both spot and futures. Using a computationally efficient technique to approximate the solution of the Hamilton-Jacobi-Bellman equation associated with the corresponding stochastic optimal control problem, our methodology facilitates strategy optimization on demand in near real-time, paving the way for advanced algorithmic market making that capitalizes on the co-integration properties intrinsic to the precious metals sector. ...

Multiblock MEV opportunities & protections in dynamic AMMs ArXiv ID: 2404.15489 “View on arXiv” Authors: Unknown Abstract Maximal Extractable Value (MEV) in Constant Function Market Making is fairly well understood. Does having dynamic weights, as found in liquidity boostrap pools (LBPs), Temporal-function market makers (TFMMs), and Replicating market makers (RMMs), introduce new attack vectors? In this paper we explore how inter-block weight changes can be analogous to trades, and can potentially lead to a multi-block MEV attack. New inter-block protections required to guard against this new attack vector are analysed. We also carry our a raft of numerical simulations, more than 450 million potential attack scenarios, showing both successful attacks and successful defense. ...

Elicitability and identifiability of tail risk measures ArXiv ID: 2404.14136 “View on arXiv” Authors: Unknown Abstract Tail risk measures are fully determined by the distribution of the underlying loss beyond its quantile at a certain level, with Value-at-Risk, Expected Shortfall and Range Value-at-Risk being prime examples. They are induced by law-based risk measures, called their generators, evaluated on the tail distribution. This paper establishes joint identifiability and elicitability results of tail risk measures together with the corresponding quantile, provided that their generators are identifiable and elicitable, respectively. As an example, we establish the joint identifiability and elicitability of the tail expectile together with the quantile. The corresponding consistent scores constitute a novel class of weighted scores, nesting the known class of scores of Fissler and Ziegel for the Expected Shortfall together with the quantile. For statistical purposes, our results pave the way to easier model fitting for tail risk measures via regression and the generalized method of moments, but also model comparison and model validation in terms of established backtesting procedures. ...

On a fundamental statistical edge principle ArXiv ID: 2404.14252 “View on arXiv” Authors: Unknown Abstract This paper establishes that conditioning the probability of execution of new orders on the self-generated historical trading information (HTI) of a trading strategy is a necessary condition for a statistical trading edge. It is shown, in particular, that, given any trading strategy S that does not use its own HTI, it is always possible to construct a new strategy S* that yields a systematically increasing improvement over S in terms of profit and loss (PnL) by using the self-generated HTI. This holds true under rather general conditions that are frequently met in practice, and it is proven through a decision mechanism specifically designed to formally prove this idea. Simulations and real-world trading evidence are included for validation and illustration, respectively. ...

On Risk-Sensitive Decision Making Under Uncertainty ArXiv ID: 2404.13371 “View on arXiv” Authors: Unknown Abstract This paper studies a risk-sensitive decision-making problem under uncertainty. It considers a decision-making process that unfolds over a fixed number of stages, in which a decision-maker chooses among multiple alternatives, some of which are deterministic and others are stochastic. The decision-maker’s cumulative value is updated at each stage, reflecting the outcomes of the chosen alternatives. After formulating this as a stochastic control problem, we delineate the necessary optimality conditions for it. Two illustrative examples from optimal betting and inventory management are provided to support our theory. ...

Continuous-time Risk-sensitive Reinforcement Learning via Quadratic Variation Penalty ArXiv ID: 2404.12598 “View on arXiv” Authors: Unknown Abstract This paper studies continuous-time risk-sensitive reinforcement learning (RL) under the entropy-regularized, exploratory diffusion process formulation with the exponential-form objective. The risk-sensitive objective arises either as the agent’s risk attitude or as a distributionally robust approach against the model uncertainty. Owing to the martingale perspective in Jia and Zhou (2023) the risk-sensitive RL problem is shown to be equivalent to ensuring the martingale property of a process involving both the value function and the q-function, augmented by an additional penalty term: the quadratic variation of the value process, capturing the variability of the value-to-go along the trajectory. This characterization allows for the straightforward adaptation of existing RL algorithms developed for non-risk-sensitive scenarios to incorporate risk sensitivity by adding the realized variance of the value process. Additionally, I highlight that the conventional policy gradient representation is inadequate for risk-sensitive problems due to the nonlinear nature of quadratic variation; however, q-learning offers a solution and extends to infinite horizon settings. Finally, I prove the convergence of the proposed algorithm for Merton’s investment problem and quantify the impact of temperature parameter on the behavior of the learning procedure. I also conduct simulation experiments to demonstrate how risk-sensitive RL improves the finite-sample performance in the linear-quadratic control problem. ...