Explainable Hybrid Stock Market Prediction Framework Using XGBoost, FinBERT Sentiment Analysis, and Candlestick Pattern Recognition

Shirin A. M. Kazi, Shruti B. Kadam and Tejas V. Joshi

International Journal of Scientific Research in Science and Technology, 2026, vol. 13, issue 3, 929-939

Abstract: This research presents an explainable stock market prediction framework that combines technical market indicators, financial news sentiment, and candlestick pattern analysis to generate transparent and reliable forecasts. The framework integrates these heterogeneous data sources into a unified predictive pipeline that estimates future stock price behavior. This paper addresses two primary questions: first, forecasting the direction of stock price movements, and second, predicting the specific future price. The system also explains why it made each prediction by highlighting the patterns it saw and how people were feeling about the news. The primary objective of this research is to develop a stock prediction framework that is both accurate and interpretable. It wants to bring what people are thinking and feeling about the market with the actual numbers and data. By doing this it hopes to help people make decisions about what to do with their stocks. The stock prediction system uses news and real market data to give people a clearer picture of what is going on in the market. This can help people make informed decisions and get a better sense of what their stocks might do, in the short term.

Keywords: Candlestick Embeddings; Transformer; FinBERT; XGBoost; Stock Prediction; Explainability; Sentiment Analysis; NIFTY50 (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijsrst.com/home/article/view/IJSRST26133221 Abstract page (text/html)
https://ijsrst.com/home/article/download/IJSRST26133221/IJSRST26133221 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:etm:ijsrst:v13:y2026:i3:id:1684

DOI: 10.32628/IJSRST26133221

Access Statistics for this article

More articles in International Journal of Scientific Research in Science and Technology from Technoscience Academy
Bibliographic data for series maintained by Pankaj Sharma ().