Leveraging Deep Learning and Online Source Sentiment for Financial Portfolio Management ArXiv ID: 2309.16679 “View on arXiv” Authors: Unknown Abstract Financial portfolio management describes the task of distributing funds and conducting trading operations on a set of financial assets, such as stocks, index funds, foreign exchange or cryptocurrencies, aiming to maximize the profit while minimizing the loss incurred by said operations. Deep Learning (DL) methods have been consistently excelling at various tasks and automated financial trading is one of the most complex one of those. This paper aims to provide insight into various DL methods for financial trading, under both the supervised and reinforcement learning schemes. At the same time, taking into consideration sentiment information regarding the traded assets, we discuss and demonstrate their usefulness through corresponding research studies. Finally, we discuss commonly found problems in training such financial agents and equip the reader with the necessary knowledge to avoid these problems and apply the discussed methods in practice. ...

FinPT: Financial Risk Prediction with Profile Tuning on Pretrained Foundation Models ArXiv ID: 2308.00065 “View on arXiv” Authors: Unknown Abstract Financial risk prediction plays a crucial role in the financial sector. Machine learning methods have been widely applied for automatically detecting potential risks and thus saving the cost of labor. However, the development in this field is lagging behind in recent years by the following two facts: 1) the algorithms used are somewhat outdated, especially in the context of the fast advance of generative AI and large language models (LLMs); 2) the lack of a unified and open-sourced financial benchmark has impeded the related research for years. To tackle these issues, we propose FinPT and FinBench: the former is a novel approach for financial risk prediction that conduct Profile Tuning on large pretrained foundation models, and the latter is a set of high-quality datasets on financial risks such as default, fraud, and churn. In FinPT, we fill the financial tabular data into the pre-defined instruction template, obtain natural-language customer profiles by prompting LLMs, and fine-tune large foundation models with the profile text to make predictions. We demonstrate the effectiveness of the proposed FinPT by experimenting with a range of representative strong baselines on FinBench. The analytical studies further deepen the understanding of LLMs for financial risk prediction. ...

Sparse Index Tracking: Simultaneous Asset Selection and Capital Allocation via $\ell_0$-Constrained Portfolio ArXiv ID: 2309.10152 “View on arXiv” Authors: Unknown Abstract Sparse index tracking is a prominent passive portfolio management strategy that constructs a sparse portfolio to track a financial index. A sparse portfolio is preferable to a full portfolio in terms of reducing transaction costs and avoiding illiquid assets. To achieve portfolio sparsity, conventional studies have utilized $\ell_p$-norm regularizations as a continuous surrogate of the $\ell_0$-norm regularization. Although these formulations can construct sparse portfolios, their practical application is challenging due to the intricate and time-consuming process of tuning parameters to define the precise upper limit of assets in the portfolio. In this paper, we propose a new problem formulation of sparse index tracking using an $\ell_0$-norm constraint that enables easy control of the upper bound on the number of assets in the portfolio. Moreover, our approach offers a choice between constraints on portfolio and turnover sparsity, further reducing transaction costs by limiting asset updates at each rebalancing interval. Furthermore, we develop an efficient algorithm for solving this problem based on a primal-dual splitting method. Finally, we illustrate the effectiveness of the proposed method through experiments on the S&P500 and Russell3000 index datasets. ...

Unraveling the Trade-off between Sustainability and Returns: A Multivariate Utility Analysis ArXiv ID: 2307.12161 “View on arXiv” Authors: Unknown Abstract This paper proposes an expected multivariate utility analysis for ESG investors in which green stocks, brown stocks, and a market index are modeled in a one-factor, CAPM-type structure. This setting allows investors to accommodate their preferences for green investments according to proper risk aversion levels. We find closed-form solutions for optimal allocations, wealth and value functions. As by-products, we first demonstrate that investors do not need to reduce their pecuniary satisfaction in order to increase green investments. Secondly, we propose a parameterization to capture investors’ preferences for green assets over brown or market assets, independent of performance. The paper uses the RepRisk Rating of U.S. stocks from 2010 to 2020 to select companies that are representative of various ESG ratings. Our empirical analysis reveals drastic increases in wealth allocation toward high-rated ESG stocks for ESG-sensitive investors; this holds even as the overall level of pecuniary satisfaction is kept unchanged. ...

Discrete time optimal investment under model uncertainty ArXiv ID: 2307.11919 “View on arXiv” Authors: Unknown Abstract We study a robust utility maximization problem in a general discrete-time frictionless market under quasi-sure no-arbitrage. The investor is assumed to have a random and concave utility function defined on the whole real-line. She also faces model ambiguity on her beliefs about the market, which is modeled through a set of priors. We prove the existence of an optimal investment strategy using only primal methods. For that we assume classical assumptions on the market and on the random utility function as asymptotic elasticity constraints. Most of our other assumptions are stated on a prior-by-prior basis and correspond to generally accepted assumptions in the literature on markets without ambiguity. We also propose a general setting including utility functions with benchmark for which our assumptions are easily checked. ...

Multimodal Document Analytics for Banking Process Automation ArXiv ID: 2307.11845 “View on arXiv” Authors: Unknown Abstract Traditional banks face increasing competition from FinTechs in the rapidly evolving financial ecosystem. Raising operational efficiency is vital to address this challenge. Our study aims to improve the efficiency of document-intensive business processes in banking. To that end, we first review the landscape of business documents in the retail segment. Banking documents often contain text, layout, and visuals, suggesting that document analytics and process automation require more than plain natural language processing (NLP). To verify this and assess the incremental value of visual cues when processing business documents, we compare a recently proposed multimodal model called LayoutXLM to powerful text classifiers (e.g., BERT) and large language models (e.g., GPT) in a case study related to processing company register extracts. The results confirm that incorporating layout information in a model substantially increases its performance. Interestingly, we also observed that more than 75% of the best model performance (in terms of the F1 score) can be achieved with as little as 30% of the training data. This shows that the demand for data labeled data to set up a multi-modal model can be moderate, which simplifies real-world applications of multimodal document analytics. Our study also sheds light on more specific practices in the scope of calibrating a multimodal banking document classifier, including the need for fine-tuning. In sum, the paper contributes original empirical evidence on the effectiveness and efficiency of multi-model models for document processing in the banking business and offers practical guidance on how to unlock this potential in day-to-day operations. ...

Social and individual learning in the Minority Game ArXiv ID: 2307.11846 “View on arXiv” Authors: Unknown Abstract We study the roles of social and individual learning on outcomes of the Minority Game model of a financial market. Social learning occurs via agents adopting the strategies of their neighbours within a social network, while individual learning results in agents changing their strategies without input from other agents. In particular, we show how social learning can undermine efficiency of the market due to negative frequency dependent selection and loss of strategy diversity. The latter of which can lock the population into a maximally inefficient state. We show how individual learning can rescue a population engaged in social learning from such inefficiencies. ...

An Adaptive Dual-level Reinforcement Learning Approach for Optimal Trade Execution ArXiv ID: 2307.10649 “View on arXiv” Authors: Unknown Abstract The purpose of this research is to devise a tactic that can closely track the daily cumulative volume-weighted average price (VWAP) using reinforcement learning. Previous studies often choose a relatively short trading horizon to implement their models, making it difficult to accurately track the daily cumulative VWAP since the variations of financial data are often insignificant within the short trading horizon. In this paper, we aim to develop a strategy that can accurately track the daily cumulative VWAP while minimizing the deviation from the VWAP. We propose a method that leverages the U-shaped pattern of intraday stock trade volumes and use Proximal Policy Optimization (PPO) as the learning algorithm. Our method follows a dual-level approach: a Transformer model that captures the overall(global) distribution of daily volumes in a U-shape, and a LSTM model that handles the distribution of orders within smaller(local) time intervals. The results from our experiments suggest that this dual-level architecture improves the accuracy of approximating the cumulative VWAP, when compared to previous reinforcement learning-based models. ...

Fast and Furious: A High-Frequency Analysis of Robinhood Users’ Trading Behavior ArXiv ID: 2307.11012 “View on arXiv” Authors: Unknown Abstract We analyze Robinhood (RH) investors’ trading reactions to intraday hourly and overnight price changes. Contrasting with recent studies focusing on daily behaviors, we find that RH users strongly favor big losers over big gainers. We also uncover that they react rapidly, typically within an hour, when acquiring stocks that exhibit extreme negative returns. Further analyses suggest greater (lower) attention to overnight (intraday) movements and exacerbated behaviors post-COVID-19 announcement. Moreover, trading attitudes significantly vary across firm size and industry, with a more contrarian strategy towards larger-cap firms and a heightened activity on energy and consumer discretionary stocks. ...

Reinforcement Learning for Credit Index Option Hedging ArXiv ID: 2307.09844 “View on arXiv” Authors: Unknown Abstract In this paper, we focus on finding the optimal hedging strategy of a credit index option using reinforcement learning. We take a practical approach, where the focus is on realism i.e. discrete time, transaction costs; even testing our policy on real market data. We apply a state of the art algorithm, the Trust Region Volatility Optimization (TRVO) algorithm and show that the derived hedging strategy outperforms the practitioner’s Black & Scholes delta hedge. ...