SaleFore AI: Ultra-accurate sales forecasting using ensemble ML (XGBoost, LightGBM, CatBoost) with RTX 4060 GPU optimization. Achieves 88-95% accuracy with advanced hyperparameter tuning.
-
Updated
Aug 22, 2025 - Python
SaleFore AI: Ultra-accurate sales forecasting using ensemble ML (XGBoost, LightGBM, CatBoost) with RTX 4060 GPU optimization. Achieves 88-95% accuracy with advanced hyperparameter tuning.
Johansen CCUS reservoir simulation | MRST | Field Injection Planning | Adding real wells in default Johansen simulation | Proposition of converting ligacy explorations wells into injection and surveillance| Surrogate Modelling | Bayesian Optimisation for sweets spot determination of Q, Tstart, Tend | Optuna TPE
This project was developed for the ML Engineering Postgraduate Program, where a classification machine learning model was built to predict whether a customer will subscribe to a term deposit after a marketing campaign.
Automated alpha-research engine for the WorldQuant BRAIN platform - generates, simulates, filters and stages uncorrelated quant signals.
Understanding menstruation and cycle length using clustering, predictive modeling and model interpretability
A reinforcement learning trading agent that uses Proximal Policy Optimization (PPO) with automated hyperparameter tuning via Optuna to learn optimal trading strategies.
A comprehensive framework for developing and backtesting quantitative trading strategies.
End-to-end ML project predicting NYC taxi fares using XGBoost + Optuna on a 33M row dataset | R² = 0.9851 | MAE = $0.66
A machine learning credit scoring
rsna_pneumonia_project
2024 한국인공지능융합기술학회 추계학술대회에 제출한 논문에 대한 연구 내용입니다.
Banking_ML_Project
Hourly Energy Consumption
End-to-end fraud detection system on 590K IEEE-CIS transactions — XGBoost + Autoencoder ensemble (0.60% FPR), SHAP explainability, deployed via FastAPI + Streamlit.
This project implements a **Handwritten Digit Classification** system using the **MNIST dataset**. The model is trained to recognize digits from `0–9` based on grayscale images of handwritten characters. The project demonstrates the application of deep learning techniques for image recognition tasks.
Credit risk prediction using machine learning, ensemble modeling, Optuna optimization, SHAP explainability, fairness analysis, and interactive deployment.
An end-to-end machine learning pipeline for credit card fraud detection using ensemble learning (Stacking) with automated preprocessing, hyperparameter tuning, and a Streamlit demo app.
This project explores Attention-Based Transformer Encoders to develop robust buy/sell classification models for financial time series. It addresses market non-stationarity and noise by combining De Prado-inspired preprocessing with a hybrid Transformer-LSTM architecture.
Autonomous algorithmic trading system- architecture, validation discipline, and verified results. Showcase repository; the production codebase is private.
To associate your repository with the optuna-optimization topic, visit your repo's landing page and select "manage topics."