38M-param time-series world model: FSQ tokenizer → Mamba-2 JEPA → OT-CFM → TD-MPC2 agent. 838M tokens, TPU v6e, JAX/Flax.

Deep learning pipeline for financial time-series forecasting using LSTM, CNN, CNN–LSTM and ResNet–LSTM with Gramian Angular Difference Field (GADF) encoding and an interactive Streamlit dashboard.

Binary classification neural network using Keras to predict loan approval decisions based on applicant financial and demographic data

Intelligent loan approval system using Support Vector Machine (SVM) for automated credit assessment and loan status prediction

Advanced ML system combining LSTM attention networks, Transformer architectures, and gradient boosting ensembles for financial time series forecasting

Trabajo de Fin de Grado en Ingeniería Matemática: Sistema de predicción direccional de Bitcoin mediante modelos de machine learning (LightGBM) y análisis de sentimiento (RoBERTa). Investigación sobre integración multimodal en mercados financieros.

NIFTY 50 5-day trend classification using Decision Tree, Random Forest and Logistic Regression with live prediction system.

A financial ML pipeline that analyzes earnings call transcripts using FinBERT sentiment analysis and predicts post-earnings stock price movements with XGBoost, validated with expanding-window walk-forward backtesting.

Transformer‑based Bull/Bear classifier for Bitcoin using long‑window trend features and pretrained inference‑only weights.

End-to-end ML pipeline that predicts BTC/USDT price direction (4h horizon) using XGBoost + Optuna + SHAP. 9-phase architecture, Walk-Forward Validation across 15 folds, 37 technical indicators, 98 automated tests. ROC-AUC: 0.5431.

Data science internship deliverables for Primetrade.ai — financial data analysis, predictive modelling, feature engineering, and ML pipeline on trading/market datasets.

Advanced gold price forecasting system beating academic benchmarks with 9+ ML models. Features rolling window predictions, real-time analytics dashboard, and extensible architecture. Built with uv, FastAPI, and Next.js for cross-platform performance.

Bitcoin trading agent using Deep Q-Learning and synthetic market scenarios.

Credit default prediction using dynamic feature importance reweighting that adapts during training. Combines gradient-based feature attribution with temporal curriculum learning to progressively emphasize the most predictive features for different risk segments. The novel contribution is an adaptive loss weighting mechanism that rebalances feature

✅ app.py — your full Stock Market Storyteller app with: Stock charts TA-Lib indicators (SMA, RSI, MACD) Gemini-powered natural language summaries CSV export