Integrating Sentiment Analysis into Mean-Variance  Portfolio Optimization: Theory, Implementation,  and Empirical Performance Evaluation

Harikrishna Jaidyal Pal

doi:10.36948/ijfmr.2025.v07i02.41758

Integrating Sentiment Analysis into Mean-Variance Portfolio Optimization: Theory, Implementation, and Empirical Performance Evaluation

Author(s)	Mr. Harikrishna Jaidyal Pal
Country	India
Abstract	Classical mean-variance (MV) portfolio optimization, while foundational in modern finance, assumes market efficiency and rational expectations, neglecting behavioral biases that significantly affect market outcomes. Recent advancements suggest that incorporating investor sentiment can substantially enhance optimization accuracy and portfolio performance. In this study, we propose a sentiment-driven mean-variance optimization framework, explicitly integrating sentiment analytics derived from news articles into the traditional Markowitz optimization model. We rigorously formulate a sentiment-adjusted MV model, mathematically deriving adjustments to expected asset returns based on quantified sentiment indicators derived through advanced natural language processing (NLP). Our implementation employs a structured pipeline consisting of real-time market data acquisition via Yahoo Finance, sentiment extraction from financial news using retrieval-augmented generation (RAG), and subsequent sentiment quantification to adjust expected returns in the MV optimization model. Empirical analysis demonstrates that sentiment-driven adjustments mitigate estimation errors inherent in purely historical-data-driven models, yielding port- folios with superior risk-adjusted performance (Sharpe ratios improved by 8–12% empirically). Visualized through clear and insightful graphical representations—including optimized portfolio allocations, sentiment-versus-weight comparisons, and an adjusted efficient frontier—the results indicate that integrating sentiment signals leads to more robust and realistic portfolio allocations. This study contributes a comprehensive methodology supported by theoretical rigor, practical implementation details, and empirical validation, underscoring the value of sentiment analysis in quantitative portfolio management and opening path- ways for further behavioral finance integration into quantitative investment strategies.
Keywords	Sentiment Analysis, Mean-Variance Optimiza- tion, Portfolio Management, Natural Language Processing, Sharpe Ratio, Behavioral Finance.
Field	Computer > Data / Information
Published In	Volume 7, Issue 2, March-April 2025
Published On	2025-04-21
DOI	https://doi.org/10.36948/ijfmr.2025.v07i02.41758
Short DOI	https://doi.org/g9gdrk

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 2 Cover Page Vol 7 Isu 1 Cover Page Vol 6 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Integrating Sentiment Analysis into Mean-Variance Portfolio Optimization: Theory, Implementation, and Empirical Performance Evaluation

Share this