---
title: Boosted Return with News
url: https://www.ml-quant.com/papers/ssrn/4900825/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4900825
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4900825
featured: 2024-07-24
citations: unknown
topic: LLMs & Text
---


# Boosted Return with News

The article uses XGBoost to predict next-day volatility jumps based on over 1400 news topics, improving portfolio performance.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4900825
- Identifier: SSRN 4900825
- Released: 2023-09-01
- First featured: Quant Letter No. 58 (2024-07-24): https://www.ml-quant.com/issues/2024-07-24/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: LLMs & Text

## Related

- [Leveraging Automatically Optimized Forecasters and Large Language Model for Forecasting of Vietnamese Macroeconomic Indicators](https://www.ml-quant.com/papers/ssrn/4976975/): The study proposes a framework for predicting Vietnamese macroeconomic indicators by combining traditional data with insights from news articles, highlighting the reliability of Gradient Boost Decision Tree models.
- [Online Investor Sentiment and Stock Market Risk](https://www.ml-quant.com/papers/repec/gam-jmathe-v-12-y-2024-i-20-p-3192-d-1497063/): Machine learning techniques like extreme gradient boosting and random forest are more accurate in predicting the aggregated stock market risk premium based on online investor sentiment than traditional linear models.
- [News Volatility and Portfolio Implications](https://www.ml-quant.com/papers/ssrn/4677789/): The article shows how the XGBoost machine learning algorithm can predict next-day volatility jumps based on firm-specific news, leading to improved portfolio performance.
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://www.ml-quant.com/papers/arxiv/2402.03300/): Advancing Math Reasoning in Language Models: DeepSeekMath7B is a new language model that uses web data and Group Relative Policy Optimization for advanced mathematical reasoning, scoring high on the MATH benchmark.
- [Mistral 7B](https://www.ml-quant.com/papers/arxiv/2310.06825/): Superior Language Model: Mistral 7B v0.1 is a language model with 7 billion parameters that excels in reasoning, mathematics, and code generation, and has a version specifically designed to follow instructions.
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://www.ml-quant.com/papers/arxiv/2408.03314/): The research investigates enhancing Large Language Models' (LLMs) performance using more test-time computation, suggesting a compute-optimal scaling strategy based on prompt difficulty.