← Back
Evidence source 4495Spot Checked

AI reshaping financial modeling

npj Artificial Intelligence2025-10-01Survey
Executive summary

A new survey finds artificial intelligence, especially natural language processing, is reshaping financial modeling by improving classic models like the Capital Asset Pricing Model (CAPM), Markowitz Mean-Variance Optimization, and Black-Litterman Model. AI uses data from news and social media to adjust variables such as expected returns and risk. Notably, sentiment analysis creates models that reflect investor mood and market anomalies. The study urges more research on ethical issues and broader AI integration beyond sentiment analysis.

What it examines

This survey explores how artificial intelligence, especially natural language processing, can improve traditional financial models like CAPM, MVO, and BLM. Instead of replacing these models, AI is used to add new data sources and recalibrate key variables, making financial predictions more accurate and interpretable.

What it concludes

AI-enhanced financial models offer better predictions and risk management by using new data like news and social media. These methods help investors make smarter decisions and adapt to changing markets. Future research should address ethical issues, data quality, and expand AI applications beyond sentiment analysis for broader financial use-cases.

Extracted from this source

Evidence objects

Evidence 214086% extraction confidence
AI, especially natural language processing, is revolutionizing financial modeling by enhancingnot replacingclassic models like CAPM ($\text{CAPM}$), Markowitz Mean-Variance Optimization, and Black-Litterman ($\text{BLM}$), making them more accurate and responsive.

key_findings bullet 1 · key_findings · validation V0

Evidence 214186% extraction confidence
A standout finding is AI-driven sentiment analysis, which creates 'sentiment-aware' versions of CAPM and BLM, capturing investor mood and market anomalies for more personalized, robust investment strategies using alternative data sources.

key_findings bullet 2 · key_findings · validation V0

Evidence 214286% extraction confidence
The approach combines traditional financial theory with deep neural networks and large language models, preserving interpretability for compliance but facing challenges like AI error control, data quality, and ethical concerns needing further research.

key_findings bullet 3 · key_findings · validation V0

Evidence 214386% extraction confidence
This paper compellingly explores integrating AIespecially NLP and LLMsinto foundational financial models like CAPM, MVO, and BLM, addressing interpretability and sentiment-aware forecasting. Its originality lies in advocating augmentation over replacement, synthesizing current approaches. While not introducing new methodologies, it offers a timely, well-argued paradigm shift for quantitative finance.

key_findings bullet 4 · key_findings · validation V0

Raw abstract and provenance

- … how AI, particularly Natural Language Processing (NLP) … , sentiment extraction from financial text and sentiment-… and a deeper understanding of financial markets. Just …

Source row: 144 · abstract type: snippet