Explore the corpus

Find evidence, not just documents.

Search Minerva’s current Findings using transparent hybrid retrieval. Results remain strictly inside the configured corpus.

Hybrid retrieval

Results for “Trading Equities”

30 findings

68match

Finding 69231 source

The research underscores AI's transformative potential in financial investment, suggesting applications in market prediction and strategy optimization. Future research should address data quality and algorithm transparency. Potential applications include enhanced investment decision-making and improved financial service efficiency.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, strategy, trading

68match

Finding 23451 source

The research suggests that machine learning-based strategies can significantly enhance investment performance. Potential applications include automated trading systems for hedge funds and other financial institutions. Future research could explore other asset classes and machine learning models.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

66match

Finding 21801 source

The study concludes that continuous action space DRL, specifically TD3, significantly improves trading performance. Future research should focus on refining reward functions and integrating diverse methods. Potential applications include enhanced trading strategies in financial markets.

LexicalMeaningQualityGraph

Matched: algorithmic, stock, strategy, trading

64match

Finding 25361 source

The autonomous AI system generates actionable trading signals in real time, with transaction costs kept below a critical threshold, making the strategy practical and potentially revolutionary for algorithmic trading and quantitative finance.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

64match

Finding 25381 source

The input text lacks substantive content, providing only a title, authors, and a partial sentence. Without details on methodology, results, or innovations, it is impossible to assess originality, novelty, or impact. The absence of information precludes highlighting compelling aspects, making the paper unassessable for its uniqueness or significance.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

64match

Finding 33971 source

The research demonstrates that MITD3 can significantly improve stock trading strategies. Potential applications include automated trading systems and financial decision support tools. Future research could explore further enhancements and broader market applications.

LexicalMeaningQualityGraph

Matched: investment, stock, strategy, trading

64match

Finding 62981 source

The research suggests that the proposed model can assist in rational investing and achieving significant returns. Future research should explore more criteria for the scoring model and apply the model to other markets. Potential applications include enhancing stock market stability and aiding investors in making informed decisions.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

61match

Finding 82011 source

This paper presents TiMi, a rationality-driven multi-agent system for quantitative finance, uniquely decoupling strategy development from minute-level deployment. Leveraging LLMs for semantic, coding, and mathematical tasks, its layered architecture and closed-loop optimization are empirically validated across 200+ trading pairs, offering novel, impactful advances for financial AI agents and algorithmic trading.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

59match

Finding 20841 source

This paper presents the Agent Trading Arena, a novel simulation where LLM-based agents interact in a dynamic, competitive trading environment, directly influencing price dynamics. Integrating LLMs, real-time feedback, and visual reasoning modules is original, enabling realistic evaluation of agent adaptability and reasoningoffering compelling insights for AI-driven investment management and trading research.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

59match

Finding 20811 source

Agent Trading Arena is a novel simulation platform where LLM-based agents compete in a virtual stock market, directly impacting prices through real-time bid-ask interactions, closely mimicking real-world trading dynamics.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

58match

Finding 60611 source

The research demonstrates the potential of network momentum in multi-asset trading strategies, emphasizing the importance of inter-class connections. Future research could explore other machine learning models and turnover regularization. Potential applications include enhanced portfolio construction and risk management in quantitative finance.

LexicalMeaningQualityGraph

Matched: equities, investment, stock, strategy, trading

57match

Finding 68651 source

Integrating established trend-following with portfolio optimization, this paper develops a systematic trading strategy for U.S. equities. Relying on momentum investing and mean-variance optimization, it offers practical refinements and addresses market constraints. Its moderate originality and applied enhancements yield fresh insights, making the work both interesting and valuable for finance professionals.

LexicalMeaningQualityGraph

Matched: equities, strategy, trading

57match

Finding 63431 source

The system outperformed benchmarks: in stock trading, it achieved a 20.42% return and Sharpe ratio of 2.63, beating the S&P 500; in high-frequency Bitcoin trading, it earned 8.39% versus 3.8% for Buy-and-Hold, with lower risk.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, trading

57match

Finding 25351 source

A new paper introduces 'agentic AI nowcasting,' a novel method combining agent-based modeling and advanced AI to predict stock returns for highly liquid Russell 1000 constituents using high-frequency data.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

57match

Finding 66531 source

The research suggests that AlphaMix can significantly improve quantitative investment strategies by addressing model uncertainty and leveraging multi-task learning. Potential applications include more robust and profitable trading strategies in real-world financial markets, with future research focusing on refining risk evaluation heuristics.

LexicalMeaningQualityGraph

Matched: investment, stock, strategy, trading

57match

Finding 20831 source

Vision-enhanced LLM agents consistently outperform traditional and text-only models on real NASDAQ and CSI datasets, especially in volatile markets, though bridging the gap to live trading remains a significant challenge.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

57match

Finding 25371 source

Despite promising results, the study lacks detailed analysis of robustness across market conditions and does not fully address concerns like overfitting or adaptability to sudden market shocks, leaving room for further validation.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

57match

Finding 20821 source

LLMs struggle with numerical reasoning using only text data, often overfitting to recent trends; however, providing chart-based visualizations and a reflection module dramatically boosts their trading performance and strategic reasoning.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

57match

Finding 81981 source

TiMi, a multi-agent trading system powered by large language models, introduces a rationality-driven architecture that separates complex strategy design from rapid, minute-level execution for high efficiency and robust risk control.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

56match

Finding 68621 source

Researchers present a trend-following strategy leveraging utility optimization to trade U.S. equities, dynamically rebalancing with mean-variance methods to achieve superior risk-adjusted performance, boosting $$\text{Sharpe}$$, $$\text{Sortino}$$, and Calmar ratios across benchmarks.

LexicalMeaningQualityGraph

Matched: equities, strategy, trading

56match

Finding 50911 source

The research offers a robust tool for quantitative investment, showing potential for practical application in stock market trading. Future work could explore deeper mining of social media data and further optimization of neural network parameters.

LexicalMeaningQualityGraph

Matched: investment, stock, strategy, trading

56match

Finding 63421 source

A new AI-powered framework, 'agentic trading,' replaces traditional algorithmic trading by mapping key financial tasksplanning, risk, execution, auditto specialized agents, ensuring transparency, reproducibility, and modularity through structured protocols and shared memory.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, trading

55match

Finding 24991 source

A new 'Attention Factor' model for equities trading uses deep learning and attention mechanisms to jointly learn asset similarity and trading strategies, optimizing risk-adjusted returns after transaction costs.

LexicalMeaningQualityGraph

Matched: equities, investment, strategy, trading

55match

Finding 82001 source

In live tests on 200+ stock and crypto pairs, TiMi outperformed traditional and LLM-based methods in annual returns, risk metrics, and latency, though retraining is needed for new markets and ethical concerns remain.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, strategy, trading

55match

Finding 61551 source

The research suggests that the conditional factor model in a state space framework is a robust approach for statistical arbitrage. Future work could explore alternative data, non-linear factor models, and intraday time scales to enhance performance. Potential applications include hedge funds and quantitative trading strategies.

LexicalMeaningQualityGraph

Matched: equities, strategy, trading

55match

Finding 72171 source

The research demonstrates a versatile data science pipeline for algorithmic trading, applicable to both stock and crypto assets. Potential applications include designing new trading algorithms and enhancing existing ones. Future research could explore advanced reinforcement learning algorithms and sentiment analysis.

LexicalMeaningQualityGraph

Matched: algorithmic, stock, trading

55match

Finding 63441 source

Leveraging large language models for reasoning and strict safeguards against data leakage, the framework democratizes advanced trading, but short backtest periods and limited market coverage highlight the need for broader, long-term validation.

LexicalMeaningQualityGraph

Matched: algorithmic, investment, stock, trading

55match

Finding 35851 source

DNN-forwardtesting offers a promising alternative to traditional backtesting, providing better profitability and risk metrics. Potential applications include stock market trading and algorithmic trading systems. Future research could explore its use in different markets and timeframes.

LexicalMeaningQualityGraph

Matched: algorithmic, stock, strategy, trading

55match

Finding 75721 source

This paper uniquely augments the Carhart four-factor model by explicitly integrating Bitcoin and gold returns, rigorously analyzing MicroStrategy as a leveraged Bitcoin proxy. Its novel framework addresses limitations in traditional equity models for crypto-correlated equities, offering valuable empirical insights and practical portfolio implications, making it compelling for academics and practitioners.

LexicalMeaningQualityGraph

Matched: equities, stock, strategy, trading

55match

Finding 75311 source

The research demonstrates the potential of dual-process meta-learning in stock volume prediction, suggesting its application in algorithmic trading and other Fintech areas. Future research could explore further enhancements and applications of this method in different financial contexts.

LexicalMeaningQualityGraph

Matched: algorithmic, stock, trading