PPO optimizes LLM-generated alpha weights for better trading performance.
problem Adapting LLM-generated alphas for varying market conditions.
method Proximal Policy Optimization (PPO) for dynamic alpha weight adjustment.
result PPO-optimized strategy achieves higher Sharpe ratios and smaller drawdowns.
EFS uses LLMs to optimize sparse portfolios by evolving alpha factors.
problem Sparse portfolio optimization in dynamic market regimes.
method Evolutionary feedback loop with LLM-generated alpha factors.
result Significantly outperforms baselines in diverse datasets.
PandaAI: A practical agent for neuro-symbolic data analysis and decision-making in finance
problem Sequential decision-making in finance
method Leveraging LLMs for market regime modeling and constrained alpha generation
result PandaAI achieves higher Rank IC and lower maximum drawdown
Paper proposes a data augmentation method for LLM-generated data in market research.
problem Bias in LLM-generated data in market research.
method Statistical data augmentation approach integrating LLM-generated and real data.
result Statistically robust estimators with reduced bias and cost savings.
Telescope detects LLM generated text by measuring token repetition probability.
problem Distinguishing LLM generated text from human writing.
method Telescope Perplexity, evaluating token repetition probability.
result Telescope Perplexity enables effective zero-shot LLM detection.
Improves feature selection in high-dimensional data using LLM-generated weights.
problem Inaccurate LLM-generated weights degrade feature selection performance.
method Integrates LLM-generated weights into prior inclusion probabilities using LLM Sparsity Prior (LSP).
result Improves prediction accuracy and identifies clinically relevant features.
LLMs outperform human analysts in predicting earnings direction.
problem Evaluating financial statements without narrative or industry-specific information.
method Trained GPT4 on standardized, anonymous financial statements and instructed to predict earnings direction.
result LLMs predict earnings directionally with accuracy comparable to narrowly trained ML models.
Paper introduces a statistical framework for watermarking LLM-generated text.
problem Detecting LLM-generated text from human-written text with statistical signals.
method Hypothesis testing formulation, pivotal statistic selection, secret key, closed-form expression of false negative rate, minimax optimization.
result Derives optimal detection rules for LLM-generated text, demonstrating higher power than existing methods.
Alpha2 discovers logical formulaic alphas using deep reinforcement learning.
problem Discovering interpretable formulaic alphas for better trading strategies.
method Formulating alpha discovery as program construction, using deep reinforcement learning to navigate the search space.
result Empirical experiments show Alpha2 identifies diverse, logical, and effective alphas improving trading strategy performance.
LLM generates coherent macroeconomic stress scenarios for portfolio risk assessment.
problem Macro-financial stress testing and portfolio risk assessment using traditional methods.
method Hybrid prompt-RAG pipeline combining structured prompting and retrieval of country fundamentals and news.
result LLM-generated scenarios yield stable tail-risk amplification with limited sensitivity to retrieval choices.
Alpha-GPT mines new trading signals with human-AI interaction.
problem Mining new alphas for effective trading signals.
method Human-AI interaction and prompt engineering algorithmic framework.
result Demonstrates Alpha-GPT's effectiveness in generating creative, insightful, and effective alphas.
Adaptive testing segments watermarked text from LLMs.
problem Distinguishing LLM-generated text from human-written content.
method Generalized likelihood-based detection method adapted to inverse transform sampling, removing prompt estimation sensitivity.
result Effective and robust method for segmenting watermarked text.
We give an explicit algorithm and source code for extracting expected returns for stocks from expected returns for alphas. Our algorithm altogether bypasses combining alphas with weights into "alpha combos". Simply put, we have developed a new method for trading alphas which does not involve combining them. This yields…
Paper introduces a new algorithm to detect LLM-generated text.
problem Detecting LLM-generated text to prevent misinformation.
method Adaptively learns the distance between original and rewritten text.
result Empirically, the new algorithm outperforms existing methods in most scenarios.
Paper proposes a new framework to mine synergistic formulaic alphas for better stock trend forecasting.
problem Mining alphas separately ignores their combined performance, leading to suboptimal models.
method Proposes a reinforcement learning-based framework that optimizes the mining of synergistic formulaic alpha sets.
result Demonstrates higher returns in stock trend forecasting compared to previous approaches.
Alpha-R1 uses LLMs to reason about economic factors and news for better alpha screening.
problem Challenges in data-driven investment strategies due to signal decay and regime shifts.
method Reinforcement learning trained on 8B parameters to evaluate alpha relevance under changing market conditions.
result Empirically outperforms benchmark strategies and shows improved robustness to alpha decay.
We propose a framework for constructing factor models for alpha streams. Our motivation is threefold. 1) When the number of alphas is large, the sample covariance matrix is singular. 2) Its out-of-sample stability is challenging. 3) Optimization of investment allocation into alpha streams can be tractable for a factor …
We compute the analytic expression of the probability distributions F{FTSE100,+} and F{FTSE100,-} of the normalized positive and negative FTSE100 (UK) index daily returns r(t). Furthermore, we define the alpha re-scaled FTSE100 daily index positive returns r(t)^alpha and negative returns (-r(t))^alpha that we call, aft…
In terms of the stock exchange returns, we compute the analytic expression of the probability distributions F{DAX,+} and F{DAX,-} of the normalized positive and negative DAX (Germany) index daily returns r(t). Furthermore, we define the alpha re-scaled DAX daily index positive returns r(t)^alpha and negative returns (-…
Alpha-GPT 2.0 integrates human insights into AI-driven investment research.
problem Efficiency and precision in quantitative investment research.
method Iterative Human-AI interaction using large language models.
result Enhanced efficiency and precision in quantitative investment research.
It is well known that combining multiple hedge fund alpha streams yields diversification benefits to the resultant portfolio. Additionally, crossing trades between different alpha streams reduces transaction costs. As the number of alpha streams increases, the relative turnover of the portfolio decreases as more trades…
RiskMiner discovers formulaic alphas using MCTS for better performance.
problem Mining formulaic alphas without considering structural information and alpha correlations.
method Formulates alpha mining as an MDP and solves it with a risk-seeking MCTS.
result Our method outperforms state-of-the-art benchmarks and achieves the most profitable results.
Regurgitative training with synthetic data harms LLM performance.
problem The impact of training LLMs with synthetic data generated by other LLMs.
method Fine-tuning GPT-3.5 with synthetic and real data in a machine translation task.
result Regurgitative training significantly reduces LLM performance.
Internal crossing of trades between multiple alpha streams results in portfolio turnover reduction. Turnover reduction can be modeled using the correlation structure of the alpha streams. As more and more alphas are added, generally turnover reduces. In this note we use a factor model approach to address the question o…
Enhances genetic programming for stock alpha discovery with warm start and structural constraints.
problem Overwhelming search space and computational burden in traditional genetic programming for alpha factor discovery.
method Proposes a new GP framework with warm start and structural constraints to enhance search performance and interpretability.
result Superior out-of-sample prediction results and higher portfolio returns compared to benchmarks.
We give an explicit algorithm and source code for combining alpha streams via bounded regression. In practical applications typically there is insufficient history to compute a sample covariance matrix (SCM) for a large number of alphas. To compute alpha allocation weights, one then resorts to (weighted) regression ove…
This paper combines LLMs with RL for better trading strategies.
problem Myopic behavior and opaque policies in RL for trading.
method LLMs generate strategic trading advice to guide RL agents.
result LLM-guided RL agents outperform unguided RL in return and risk metrics.
Unified convergence analysis of alpha-SVRG under strong convexity.
problem Analyzing the convergence of alpha-SVRG in strongly convex environments.
method Unified convergence rate expression for alpha-SVRG under fixed learning rate, demonstrating faster convergence than SGD and SVRG.
result alpha-SVRG has a faster convergence rate compared to SGD and SVRG under suitable choice of alpha.
AlphaEval evaluates alpha mining models efficiently and comprehensively.
problem Lack of systematic evaluation for alpha mining models.
method Unified, parallelizable evaluation framework assessing predictive power, stability, robustness, financial logic, and diversity.
result AlphaEval achieves evaluation consistency comparable to comprehensive backtesting, providing more comprehensive insights and higher efficiency.
New methods for tuning alpha in Gibbs posteriors improve speed and accuracy.
problem Inconsistency in Bayesian inference and lack of fast tuning methods for alpha.
method Proposed two data-driven methods: sample-splitting and bootstrapping. Formulated alpha-posteriors for three models.
result Sample-splitting outperforms SafeBayes in speed and accuracy, especially in complex models.
An explicit expression is obtained for the sectional curvature in the plane spanned by two stationary flows, cos(k, x) and cos(l, x). It is shown that for certain values of the wave vectors k and l the curvature becomes positive for alpha > alpha_0, where 0 < alpha_0 < 1 is of the order 1/k. This suggests that the flow…
The weak variance-alpha-gamma process is a multivariate Lévy process constructed by weakly subordinating Brownian motion, possibly with correlated components with an alpha-gamma subordinator. It generalises the variance-alpha-gamma process of Semeraro constructed by traditional subordination. We compare three calibrati…
Researchers calculate alpha invariant for certain complex projective spaces.
problem Computing alpha invariant for specific types of complex projective spaces.
method Computed alpha invariant using total degree and Pontryagin classes.
result Alpha invariant depends only on total degree and Pontryagin classes.
We give a simple explicit formula for turnover reduction when a large number of alphas are traded on the same execution platform and trades are crossed internally. We model turnover reduction via alpha correlations. Then, for a large number of alphas, turnover reduction is related to the largest eigenvalue and the corr…
AlphaSAGE mines diverse alphas via GFlowNets, overcoming RL issues.
problem Reward sparsity, inadequate sequential representations, and single optimal mode issues in RL for alphas.
method Structure-aware encoder (RGCN), GFlowNets, dense reward structure.
result Empirically outperforms existing baselines in mining diverse alphas.
We give an explicit algorithm and source code for extracting equity risk factors from dead (a.k.a. "flatlined" or "hockey-stick") alphas and using them to improve performance characteristics of good (tradable) alphas. In a nutshell, we use dead alphas to extract directions in the space of stock returns along which ther…
The paper presents methods to improve uncertainty calibration in Bayesian Neural Networks.
problem Uncalibrated Bayesian Neural Networks often lead to overconfidence.
method The paper uses alpha-divergences from Information Geometry for calibration.
result Calibration using alpha-divergences provides better uncertainty estimates and is more efficient.
AlphaForge mines and dynamically combines alpha factors for better investment performance.
problem Inconsistency and inflexibility of fixed factor weights in alpha factor mining.
method Generative-predictive neural network for factor generation and dynamic weight adjustment.
result Demonstrated superior performance in formulaic alpha factor mining and portfolio returns.
In these notes we discuss investment allocation to multiple alpha streams traded on the same execution platform, including when trades are crossed internally resulting in turnover reduction. We discuss approaches to alpha weight optimization where one maximizes P&L subject to bounds on volatility (or Sharpe ratio). The…
Mannheim curves are defined for immersed curves in 3-dimensional sphere S^3 . The definition is given by considering the geodesics of S^3. First, two special geodesics, called principal normal geodesic and binormal geodesic, of S^3 are defined by using Frenet vectors of a curve immersed in S^3. Later, the curve alpha i…
AlphaCFG discovers alpha factors using grammar-guided search.
problem Discovering formulaic alpha factors in finance.
method AlphaCFG uses a grammar-based framework to define and discover alpha factors with syntactic and semantic constraints.
result AlphaCFG outperforms state-of-the-art methods in trading profitability and efficiency.
We present explicit formulas - that are also computer code - for 101 real-life quantitative trading alphas. Their average holding period approximately ranges 0.6-6.4 days. The average pair-wise correlation of these alphas is low, 15.9%. The returns are strongly correlated with volatility, but have no significant depend…
The paper evaluates biased methods for alpha-divergence minimization.
problem The impact of bias on solutions found for alpha-divergence minimization.
method Empirical evaluation of biased methods for alpha-divergence minimization, focusing on bias effects and dimensionality.
result Solutions are biased towards KL-divergence minimizers and require impractical computation in high dimensions to minimize alpha-divergence.
Given a smooth, closed, oriented 4-manifold X and alpha in H_2(X,Z) such that alpha.alpha > 0, a closed 2-form w is constructed, Poincare dual to alpha, which is symplectic on the complement of a finite set of unknotted circles. The number of circles, counted with sign, is given by d = (c_1(s)^2 -3sigma(X) -2chi(X))/4,…
Unbiased methods for alpha-divergence minimization struggle in high dimensions.
problem The difficulty of unbiased alpha-divergence minimization in high dimensions.
method Signal-to-Noise Ratio (SNR) analysis of gradient estimators.
result The SNR of the gradient estimator worsens exponentially with dimensionality.
Paper proposes a new REINFORCE algorithm for mining formulaic alpha factors with reduced variance.
problem Mining formulaic alpha factors with interpretability and robustness in volatile markets.
method Developed a novel REINFORCE algorithm with a dedicated baseline and reward shaping.
result Boosts correlation with returns by 3.83% and enhances excess returns compared to existing methods.
We present conditions under which positive alpha exists in the realm of active portfolio management- in contrast to the controversial result in Jarrow (2010, pg. 20) which implicates delegated portfolio management by surmising that positive alphas are illusionary. Specifically, we show that the critical assumption used…
This work presents a parametrized family of divergences, namely Alpha-Beta Log- Determinant (Log-Det) divergences, between positive definite unitized trace class operators on a Hilbert space. This is a generalization of the Alpha-Beta Log-Determinant divergences between symmetric, positive definite matrices to the infi…