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 “Financial Ratios & Quantitative Analysis in AI Models”

30 findings

68match

Finding 20571 source

Researchers reveal the unexpected power of the total liabilities-to-operating costs ratio; this metric, when combined with return on equity, current ratio, operating cash flow, and equity multiplier, predicts financial misreporting.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

68match

Finding 20591 source

This paper presents a transparent framework for financial fraud detection employing genetic programming to generate explicit expressions. Its originality is clear as evolutionary methods fuse with established risk indicators, providing a novel, interpretable alternative to black-box models. Readers gain profound insight into advanced quantitative risk management through progressive model evolution.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

67match

Finding 40011 source

This paper uniquely synthesizes stochastic dominance, machine learning, and explainable AI (XAI) within a causality-driven framework for portfolio optimization. Its originality lies in combining structural causal modeling and SHAP to interpret determinants of network stochastic dominance ratios, offering practical relevance, interpretability, and empirical validationmaking it compelling for quantitative finance and AI-driven asset selection.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

67match

Finding 20561 source

Researchers introduce the XGB-GP hybrid model combining Extreme Gradient Boosting for feature selection with Genetic Programming for an interpretable fraud equation, overcoming machine learning black box issues through statistical filtering.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

67match

Finding 40001 source

Using daily returns from 19 assets, XGBoost outperforms quantile regression in predicting NetSDR, but the research is limited by narrow asset classes and time windows, suggesting future expansion and exploration of more machine learning techniques.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

67match

Finding 39991 source

The study introduces NetSDR, a dynamic, time-sensitive measure, and combines structural causal modeling, XGBoost, and SHAP to transparently identify what truly influences asset rankings, offering a fresh, interpretable framework for investors.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

67match

Finding 20581 source

Leveraging CSMAR database data with rigorous preprocessing, including outlier removal and oversampling, the study presents a transparent fraud detection framework advancing risk management, although limited non-financial indicators may reduce generalizability.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

67match

Finding 39981 source

Risk metrics like Expected Shortfall, Maximum Drawdown, and Kurtosis outweigh average returns in asset dominance, overturning traditional finance beliefs and revealing surprising new drivers for investment ranking across stocks, commodities, and cryptocurrencies.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

64match

Finding 70191 source

Extensive analysis with text and table parsing, varied prompt configurations, and ablation studies revealed performance metrics, potential LLM bias, and challenges in capturing nuanced financial analysis, providing notable balanced insights.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

63match

Finding 26671 source

The study reveals substantial temporal biases in LLM performance, with models excelling on post-1995 data following the SECs EDGAR filing system yet struggling and hallucinating details for older financial information.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

63match

Finding 34961 source

The paper introduces a novel integration of structured reasoning supervision and dual-reward reinforcement learning, constructing specialized financial datasets and employing innovative $\text{GRPO}$ methods to precisely align structured outputs with answer accuracy. This fresh, original approach in financial AI enhances reasoning, making the work compelling, significant, and essential for quantitative analysis.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

63match

Finding 70201 source

The paper introduces SECQUE, an inventive benchmark evaluating LLMs on real-world SEC filings. Its novel approach uses SECQUE-Judge to assess complex long-context financial data, blending ratio calculations, risk, and comparison analysis. This tailored and detailed design makes the work uniquely engaging, providing valuable insights and applicability to financial quantitative analysis.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

63match

Finding 34941 source

Surprisingly, even smaller models augmented with reasoning and a novel Group Relative Policy Optimization reinforcement learning technique outperformed larger non-reasoning models, matching multi-agent system performance while dramatically reducing computational costs.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

62match

Finding 70181 source

A notable breakthrough is SECQUE-judge, an evaluation system that uses LLM judges, aligning closely with human evaluations and outperforming simpler methods when aggregating advanced LLM judgments in specialized finance tasks.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

62match

Finding 34931 source

The paper introduces DianJin-R1, a framework embedding explicit reasoning within financial large language models, dramatically enhancing accuracy and interpretability through step-by-step logical explanations built from diverse, high-quality datasets for innovation.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

62match

Finding 70171 source

SECQUE introduces a benchmark using real SEC filings with 565 expert-written questions across four categories, showing even GPT-4o struggles with complex reasoning and analyst insights, spotlighting evaluation challenges in finance.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

62match

Finding 26691 source

Researchers introduce a novel Revenue Prompt Dataset of 200,000 questions, using logistic regression to link market capitalization, investor attention, and filing readability for quantifying retrograde knowledge bias among U.S. companies.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

61match

Finding 26681 source

Surprisingly, even companies with seemingly correct revenue predictions experience simultaneous false data generation, highlighting LLMs paradox: they reliably capture recent figures yet produce consistently misleading numbers for major, renowned enterprises.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

61match

Finding 41171 source

Researchers unveiled a cutting-edge intelligent financial data analysis system integrating large language models with retrieval-augmented generation, dramatically boosting accuracy ($78.6%$) and recall ($89.2%$), outperforming traditional rule-based models significantly across markets.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

61match

Finding 40281 source

Researchers investigated language models ability for financial analysis by leveraging self-explanations that detail reasoning, revealing a surprising statistical link between factual and causal explanation quality and classification accuracy with impact.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

61match

Finding 26701 source

Investigating LLM comprehension of historical financial data, this paper introduces a systematic, data-driven approach highlighting both temporal and cross-sectional biases, notably retrograde knowledge bias. Its originality stems from linking LLM performance with company characteristics, offering novel insights that impact financial modeling and investment decisions, rendering it a compelling, innovative read.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

61match

Finding 34951 source

Key contributions include a defined protocol for reasoning generation, structured output formatting with distinct tags, innovative compliance management via multi-agent synthesization, while noting language diversity and reinforcement learning challenges effectively.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

61match

Finding 25811 source

Innovative terminologies such as transitory efficiency and persistent efficiency enrich economic discussions on cost management, with this methodology paving the way for future exploration of model uncertainty and banking applications.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

61match

Finding 25801 source

The paper presents state-of-the-art techniques including advanced MCMC methods and extensive simulation studies, although its reliance on large datasets and technical complexity may restrict immediate practical application for industry practitioners.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

61match

Finding 41181 source

Surprisingly, incorporating retrieval-augmented generation enhanced the models comprehension of intricate financial datasets by addressing fundamental limitations of old statistical and rule-based systems, setting new benchmarks for financial data mining remarkably.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

60match

Finding 25791 source

The study introduces a dynamic Bayesian nonparametric framework using the Logit Stick-Breaking Process, distinguishing transient and persistent cost inefficiencies and showing banks switch models during major shocks like COVID-19 recently.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

60match

Finding 25571 source

Analyzing narrative sections of 10-K filingsItems 1, 1A, and 7significantly improves bankruptcy prediction, outperforming traditional accounting ratios and offering early warning signals not found in financial data alone.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

60match

Finding 40311 source

The study examines how LM-generated self-explanations correlate with financial analysis accuracy, impacting risk assessment and trading decisions. Building on explainable AI ideas, it applies zero-shot classification with language models in finance. Although derivative in approach, its focus on explanation quality and model trust renders its perspective compelling for further research.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

60match

Finding 40301 source

Comprehensive experiments using multiple language models and innovative data preparation methods showed that improved explanation accuracy correlates with better classification performance despite limited task variety and scale according to research.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios

59match

Finding 47271 source

The study introduces an innovative graph-based framework for factor models that ingeniously integrates bond features like credit rating and country, significantly improving interpretability and robustness in credit spread decompositions, remarkably.

LexicalMeaningQualityGraph

Matched: analysis, financial, models, quantitative, ratios