You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
To identify lithologies, geoscientists use subsurface data such as wireline logs and petrophysical data. However, this process is often tedious, repetitive, and time-consuming. This project aims to use machine learning techniques to predict lithology from petrophysical logs, which are direct indicators of lithology.
AI-powered supply chain decision intelligence system for shipment delay prediction, risk assessment, and optimized mitigation recommendations using XGBoost, FastAPI, React, and optimization techniques.
An interactive ML decision engine and Streamlit dashboard for real-time credit risk modeling, Probability of Default (PD) scoring, and portfolio expected loss analytics.
An information-theoretic ML pipeline for Kaggle. Computes rows-wise Shannon Entropy to track service evaluation consistency, applies relativistic Lorentz damping to compress tabular delay outliers, and utilizes regularized Hill Climbing to optimize a Level-1 Triple Stack Ensemble
Complete ML pipeline for Titanic survival prediction using Logistic Regression, Random Forest, XGBoost, and SVM includes EDA, preprocessing, tuning, and feature importance.
Comparison of multiple machine learning classifiers for corporate bankruptcy prediction using financial ratios, class imbalance handling, and cross‑validation.
Proyecto de predicción de ventas para las proximas 6 semanas de todas las tiendas , con representación de datos, usando Python con librerías distintas como Pandas, Numpy,Matlab, Seaborn para análisis de datos, recopilación e interpretación de los datos, además de modelos predictivos.