automated-ml

AI platform for automated research paper analysis, knowledge extraction, and ML experimentation with SHAP explainability and PDF report generation.

Automated‑ML automates training and evaluating machine learning models on tabular data with minimal setup.

Autonomous multi-agent Data Science pipeline — upload a CSV, get a trained model, EDA charts, and an executive report. Zero manual intervention. Built with CrewAI · FastAPI · React · XGBoost · WebSockets.

An automated-ML library that automates model training completely using simple APIs. Moreover, it provides curated data analysis modules for preprocessing, anomaly/outlier removal, sanity check(bias-variance tradeoffs), data splitter and explainability of model predictions with visualizations.

Dataset Auto-Diagnosis Python Library — detect and fix data quality issues (leakage, skewness, outliers, imbalance) before model training.

Automated customer churn prediction pipeline with feature selection, model comparison, and deployment-ready output. Python + scikit-learn.

Automated end-to-end MLOps pipeline for predicting customer purchase likelihood of a wellness tourism package, enabling data-driven marketing through CI/CD-enabled model training and deployment.

An algorithmic bias audit and fairness evaluation of an emergency department clinical triage model using Azure Machine Learning and macro-balanced mitigation strategies.

My first startup failed after corporate life... still best decision I ever made (I will not promote)

Upload any dataset, explore it, clean it, train 30+ ML models, compare results, and download a full PDF report — all in the browser.

Predict whether a news article is real or fake.

Neural Architecture Search using Differential Evolution

Classify customer churn (yes/no) from usage and account features (classification).

Classify wine quality from physicochemical properties

Trust & Safety risk analysis system detecting account takeover, credential stuffing and data exfiltration in 50K+ user activity logs. Statistical analysis + ML scoring (ROC-AUC: 0.9998, Precision@10: 1.0). CI/CD via Azure DevOps.

Recommend products based on user behavior

Spine surgery has massive decision variability. Retrospective ML won’t fix it. Curious if a workflow-native, outcome-driven approach could. [D]

A simple explanation of Naive Bayes Classification

Nvidia: End-to-End Test-Time Training for Long Context aka Being Able To Update A Model's Weights In Real-Time As You Use It | "TTT changes the paradigm from re

Test Final Improvements Classification