Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Sentiment-Aware Mean-Variance Portfolio Optimization for Cryptocurrencies

Qizhao Chen

TL;DR

Backtesting across multiple cryptocurrencies shows that the integrated approach outperforms traditional benchmarks, including momentum strategy, Bitcoin Long-Short strategy, and an equal-weighted portfolio, achieving stronger risk-adjusted returns and more consistent cumulative growth.

Abstract

Cryptocurrency markets are highly volatile and influenced by both price trends and market sentiment, making effective portfolio management challenging. This paper proposes a dynamic cryptocurrency portfolio strategy that integrates technical indicators and sentiment analysis to enhance investment decision-making. Market momentum is captured using the 14-day Relative Strength Index (RSI) and Simple Moving Average (SMA), while sentiment signals are extracted from news articles with VADER and further validated using the Google Gemini large language model. These signals are incorporated into expected return estimates and used in a constrained mean-variance optimization framework. Backtesting across multiple cryptocurrencies shows that the integrated approach outperforms traditional benchmarks, including momentum strategy, Bitcoin Long-Short strategy, and an equal-weighted portfolio, achieving stronger risk-adjusted returns and more consistent cumulative growth. Furthermore, comparing the sentiment-only and technical-only strategies shows that incorporating sentiment information alongside technical indicators can lead to more consistent performance gains. However, the strategies exhibit substantial drawdowns that coincide with known periods of market stress, indicating that additional risk-management components are required to improve stability.

Sentiment-Aware Mean-Variance Portfolio Optimization for Cryptocurrencies

TL;DR

Backtesting across multiple cryptocurrencies shows that the integrated approach outperforms traditional benchmarks, including momentum strategy, Bitcoin Long-Short strategy, and an equal-weighted portfolio, achieving stronger risk-adjusted returns and more consistent cumulative growth.

Abstract

Cryptocurrency markets are highly volatile and influenced by both price trends and market sentiment, making effective portfolio management challenging. This paper proposes a dynamic cryptocurrency portfolio strategy that integrates technical indicators and sentiment analysis to enhance investment decision-making. Market momentum is captured using the 14-day Relative Strength Index (RSI) and Simple Moving Average (SMA), while sentiment signals are extracted from news articles with VADER and further validated using the Google Gemini large language model. These signals are incorporated into expected return estimates and used in a constrained mean-variance optimization framework. Backtesting across multiple cryptocurrencies shows that the integrated approach outperforms traditional benchmarks, including momentum strategy, Bitcoin Long-Short strategy, and an equal-weighted portfolio, achieving stronger risk-adjusted returns and more consistent cumulative growth. Furthermore, comparing the sentiment-only and technical-only strategies shows that incorporating sentiment information alongside technical indicators can lead to more consistent performance gains. However, the strategies exhibit substantial drawdowns that coincide with known periods of market stress, indicating that additional risk-management components are required to improve stability.

Paper Structure

This paper contains 11 sections, 16 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data and Methodology
  4. Data
  5. Feature Engineering and Return Adjustment
  6. Model Setup
  7. Evaluation
  8. Results
  9. Coefficient Stability Analysis
  10. Strategy Performance Analysis
  11. Further Discussion: Verifying VADER with Google Gemini

Figures (4)

  • Figure 1: Evolution of estimated Ridge Regression coefficients over time (Bitcoin shown as an illustrative example).
  • Figure 2: Drawdown of the Proposed Strategy
  • Figure 3: Normalized price trajectories of major cryptocurrencies from 2020 to 2025. Each series is scaled by its value at the beginning of the sample, allowing all assets to be shown on a comparable scale. A normalized value of 1 represents the initial price, and deviations above or below this level reflect proportional gains or losses relative to the starting point. This transformation highlights the timing and magnitude of the market-wide contraction during the 2022 cryptocurrency downturn.
  • Figure 4: Drawdown of Five Cryptocurrecies from 2020 to 2025