Research
RAM AI'S RESEARCH
RAM AI’s research drives our investment decisions and performance.
RAM AI’s researchers relentlessly explore new ways of extracting information from data to uncover new sources of return, increase diversification and improve liquidity.
Our conviction in the fundamentals and the non-linearity of their interactions has led us to develop a Deep Learning infrastructure, which helps reveal the predictive power of the exponentially growing volume of information at our disposal.
Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Prediction
Abstract
We explore model designs and training that merge quantitative factors with LLM-based newsflow to improve stock return prediction and selection.
A Leading Approach to ESG Integration
Abstract
ESG data growth offers new investment dimensions but presents challenges. We introduce ESG shortcomings and value-added inputs for stock selection.
Real-Time Climate Controversy Detection
Abstract
ClimateControversyBERT detects corporate climate controversies in real time, showing significant negative market impacts for committed firms.
2025: Concentration & Opportunities
Abstract
U.S. equities reached 72.5% of MSCI World Index in 2024—a record high. We examine historical parallels to uncover opportunities.
VIX Term Structure: Seeds of the Volatility Trade Unwind
Abstract
Following August 5th's unprecedented VIX spike, we analyze volatility products evolution and the volatility risk premium's attractiveness.
Fine-Tuning Large Language Models for Stock Return Prediction Using Newsflow
Abstract
Fine-tuned LLMs assess newsflow impact on stock returns, outperforming conventional sentiment models with strong portfolio performance.
Financial Sentiment Analysis With Large Language Models
Abstract
LLMs extract information with significant predictive power on future stock returns, particularly for small and mid-cap stocks.
AI for ESG Integration: Training Machines to Predict Sustainable Alpha
Abstract
Our deep learning framework combines ESG and traditional factors, modeling their interactions for optimal stock selection and portfolio construction.
Beyond ESG Rating: The Real Impact of Good Governance
Abstract
SFDR regulation improves transparency in sustainable investment and prevents greenwashing. We analyze its impact on return and style biases.
Systematic Market Neutral: The Benefits of Diversifying Frequencies
Abstract
Our deep learning framework forecasts stock returns. Shorter-term strategies show attractive characteristics benefiting lower-frequency portfolios.
Go Beyond Sentiment: Stock Prediction Enhanced With Financial News
Abstract
Our deep learning framework models interactions between features, comparing sentiment and text embeddings to predict stock returns.
Unlocking the Secrets in Semantics
Abstract
Machine learning processes rich textual data from financial news and reports, revealing correlations currently underexploited by quant managers.
To Invest or Not to Invest? The Effect of Capex Announcements
Abstract
Companies invest profits in organic growth through R&D or Capex. As of January 2021, U.S. net Capex/sales ratio reached 2.54%.
Machine Learning: Financial Data Takes a New Dimension
Abstract
AI and machine learning continue to push boundaries, unlocking new dimensions for finance as technology evolves.
To Invest or Not to Invest? Capitalising R&D Expenses to Increase Valuation Accuracy
Abstract
Companies invest in organic growth through R&D or Capex. This paper analyzes R&D activity and its impact on company fundamentals.
A Deep Learning Framework for Climate Responsible Investment
Abstract
We integrate structured and unstructured climate data into quantitative investing, demonstrating low-carbon portfolios with attractive returns.
Predicting the Impact of ESG News With Deep Learning – ESG2Risk
Abstract
Our ESG news pipeline predicts stock volatility, demonstrating superior performance and identifying high-risk, low-return stocks.