Deep Learning Transformer models in MATLAB

Financial Domain Question Answering with pre-trained BERT Language Model

An AI-powered personal finance tracker to manage expenses, predict spending, and plan budgets using machine learning.

Deep Reinforcement Learning (DRL) stock trading system with LSTM-PPO, integrating technical indicators and FinBERT-based news sentiment analysis.

Notebooks for fine-tuning a BERT model and training a LSTM model for financial QA

Single-stock analysis using Python and local machine learning/ AI tools (Ollama, LSTM).

Market-Derived Financial Sentiment Analysis: Context-Aware Language Models for Crypto Forecasting

Earnings Call Sentiment Analysis. This repository includes my work on extracting the focus area of companies from their earnings calls transcripts.

AI-powered algorithmic trading system that combines FinBERT sentiment analysis, spaCy NER, and TimeGPT forecasting to generate BUY/SELL/HOLD signals from real-time financial news.

Sentiment Analysis On Financial News Headlines With BERT & FinBERT

Stock Sentinel is a web app providing stock market investors with sentiment analysis and news aggregation. It uses FinBERT for sentiment analysis and offers stock information, similar stocks suggestions, summaries, and news stories. With real-time insights, it helps users make informed investment decisions. Installation is easy with cloning, depend

An end-to-end Python implementation of Cao et al.'s (2025) HLPPL methodology for the identification of financial (asset price) bubbles. Implements 7-parameter Log-Periodic Power Law model fitting, confidence-weighted sentiment analysis, regime-dependent 'BubbleScore' fusion, and Transformer-based forecasting with a backtesting framework.

Interaction-centric behavioral modeling for earnings calls using multimodal neural fusion, text-audio divergence, and Q&A interaction dynamics.

Hands-on guide for sentiment analysis in quarterly conference calls

A Deep Learning Sentiment Analysis on News Headlines using FinBERT (Python)

OSE Scientific Computing for Economists

End-to-end ML system for prediction market trading — 521K markets, 78 features, 7 model architectures, walk-forward validation, live VPS A/B across 7 configs. Honest research-stop on alpha decay (NO-GO verdict). AFML methodology: Purged K-Fold, Deflated Sharpe Ratio, meta-labeling, focal loss.

This repository contains the code and data for an exploratory study on financial sentiment analysis of annual reports from the current member companies of the Philippine Stock Exchange index. The study was conducted as part of the MSFIN299 course at the University of the Philippines Diliman

An offline-first quantitative equity analysis engine. Combines stochastic market modeling (HMM/GARCH), air-gapped NLP sentiment (FinBERT), and sector-aware fundamental scoring to deliver institutional-grade portfolio auditing and tactical trade signals.