Publication Library
Smart leverage Rethinking the role of Leveraged Exchange Traded Funds in constructing portfolios to beat a benchmark
Description: Leveraged Exchange Traded Funds (LETFs), while extremely controversial in the literature, remain stubbornly popular with both institutional and retail investors in practice. While the criticisms of LETFs are certainly valid, we argue that their potential has been underestimated in the literature due to the use of very simple investment strategies involving LETFs. In this paper, we systematically investigate the potential of including a broad stock market index LETF in long-term, dynamically-optimal investment strategies designed to maximize the outperformance over standard investment benchmarks in the sense of the information ratio (IR). Our results exploit the observation that positions in a LETF deliver call-like payoffs, so that the addition of a LETF to a portfolio can be a convenient way to add inexpensive leverage while providing downside protection. Under stylized assumptions, we present and analyze closed-form IR-optimal investment strategies using either a LETF or standard/vanilla ETF (VETF) on the same equity index, which provides the necessary intuition for the potential and benefits of LETFs. In more realistic settings, we use a neural network-based approach to determine the IR-optimal strategies, trained on bootstrapped historical data. We find that IR-optimal strategies with a broad stock market LETF are not only more likely to outperform the benchmark than IR-optimal strategies derived using the corresponding VETF, but are able to achieve partial stochastic dominance over the benchmark and VETF-based strategies in terms of terminal wealth.
Created At: 11 December 2024
Updated At: 11 December 2024
Copyright-Protected Language Generation via Adaptive Model Fusion
Description: The risk of language models reproducing copyrighted material from their training data has led to the development of various protective measures. Among these, inference-time strategies that impose constraints via post-processing have shown promise in addressing the complexities of copyright regulation. However, they often incur prohibitive computational costs or suffer from performance trade-offs. To overcome these limitations, we introduce Copyright-Protecting Model Fusion (CP-Fuse), a novel approach that combines models trained on disjoint sets of copyrighted material during inference. In particular, CP-Fuse adaptively aggregates the model outputs to minimize the reproduction of copyrighted content, adhering to a crucial balancing property that prevents the regurgitation of memorized data. Through extensive experiments, we show that CP-Fuse significantly reduces the reproduction of protected material without compromising the quality of text and code generation. Moreover, its post-hoc nature allows seamless integration with other protective measures, further enhancing copyright safeguards. Lastly, we show that CP-Fuse is robust against common techniques for extracting training data.
Created At: 10 December 2024
Updated At: 10 December 2024
Corporate Fundamentals and Stock Price Co-Movement
Description: We introduce an innovative framework that leverages advanced big data techniques to analyze dynamic co-movement between stocks and their underlying fundamentals using high-frequency stock market data. Our method identifies leading co-movement stocks through four distinct regression models: Forecast Error Variance Decomposition, transaction volume-normalized FEVD, Granger causality test frequency, and Granger causality test days. Validated using Chinese banking sector stocks, our framework uncovers complex relationships between stock price co-movements and fundamental characteristics, demonstrating its robustness and wide applicability across various sectors and markets. This approach not only enhances our understanding of market dynamics but also provides actionable insights for investors and policymakers, helping to mitigate broader market volatilities and improve financial stability. Our model indicates that banks' influence on their peers is significantly affected by their wealth management business, interbank activities, equity multiplier, non-performing loans, regulatory requirements, and reserve requirement ratios. This aids in mitigating the impact of broader market volatilities and provides deep insights into the unique influence of banks within the financial ecosystem.
Created At: 05 December 2024
Updated At: 05 December 2024
MILLION A General Multi-Objective Framework with Controllable Risk for Portfolio Management
Description: Portfolio management is an important yet challenging task in AI for FinTech, which aims to allocate investors' budgets among different assets to balance the risk and return of an investment. In this study, we propose a general Multi-objectIve framework with controLLable rIsk for pOrtfolio maNagement (MILLION), which consists of two main phases, i.e., return-related maximization and risk control. Specifically, in the return-related maximization phase, we introduce two auxiliary objectives, i.e., return rate prediction, and return rate ranking, combined with portfolio optimization to remit the overfitting problem and improve the generalization of the trained model to future markets. Subsequently, in the risk control phase, we propose two methods, i.e., portfolio interpolation and portfolio improvement, to achieve fine-grained risk control and fast risk adaption to a user-specified risk level. For the portfolio interpolation method, we theoretically prove that the risk can be perfectly controlled if the to-be-set risk level is in a proper interval. In addition, we also show that the return rate of the adjusted portfolio after portfolio interpolation is no less than that of the min-variance optimization, as long as the model in the reward maximization phase is effective. Furthermore, the portfolio improvement method can achieve greater return rates while keeping the same risk level compared to portfolio interpolation. Extensive experiments are conducted on three real-world datasets. The results demonstrate the effectiveness and efficiency of the proposed framework.
Created At: 05 December 2024
Updated At: 05 December 2024
Turnover of investment portfolio via covariance matrix of returns
Description: An investment portfolio consists of n algorithmic trading strategies, which generate vectors of positions in trading assets. Sign opposite trades (buy/sell) cross each other as strategies are combined in a portfolio. Then portfolio turnover becomes a non linear function of strategies turnover. It rises a problem of effective (quick and precise) portfolio turnover estimation. Kakushadze and Liew (2014) shows how to estimate turnover via covariance matrix of returns. We build a mathematical model for such estimations; prove a theorem which gives a necessary condition for model applicability; suggest new turnover estimations; check numerically the preciseness of turnover estimations for algorithmic strategies on USA equity market.
Created At: 05 December 2024
Updated At: 05 December 2024