Contains our Approach for the competition organized at Udyam'21

A machine learning pipeline for classifying cybersecurity incidents as True Positive(TP), Benign Positive(BP), or False Positive(FP) using the Microsoft GUIDE dataset. Features advanced preprocessing, XGBoost optimization, SMOTE, SHAP analysis, and deployment-ready models. Tools: Python, scikit-learn, XGBoost, LightGBM, SHAP and imbalanced-learn

Jupyter notebooks for training ML models that predict biological sex from skeletal measurements. Companion to the SexEst web app.

A machine learning based forecasting system for taxi demand prediction

This project is about to detecting the text generated by different LLM given prompt. The instance is labeled by Human and Machine, and this project utilised both traditional machine learning method and deep learning method to classify the instance.

Implémentation d'un modèle de scoring (OpenClassrooms | Data Scientist | Projet 7)

This repo is a hands-on implementation of End-to-End MLOps Pipeline, with LGB hyperparameter tuning, MLflow model tracking and CI/CD with GitHub Actions.

This project detects credit card fraud using a Kaggle dataset of over 1.8 million transactions. To handle the highly imbalanced data, it uses SMOTE to balance fraudulent and legitimate transactions. The project then trains several models, with the LightGBM classifier achieving the best performance at 99.5% accuracy.

No description provided.

Predicting transaction fraud using classification problems such as Guardian Boosting as well as user interfaces using Streamlite, Accuracy: 98% AUC-ROC

This approach has the potential to create accurate, generalizable and adaptable machine learning methods that effectively and sustainably address agricultural tasks such as yield prediction and early disease identification.

Spectral type classification using LGBM and deployed using FastAPI, Pydantic, and Docker

It's the Repo having a .ipynb file with bank customer churn prediction using various classifiers and machine learning models

Music Genre Recommender website that can identify and recommend 10 different genres of music using Light Gradient Boosting Machine (LGBM). An accuracy of 90% was achieved on the test set by tuning the hyperparameters of the model with Optuna.

End to end Heart Diseases Prediction Model with webapp using Flask

Using LGBMClassifier to solve To-Be Challenge, which is a machine learning challenge on CodaLab Platform that aims to adress the problems of medical imbalanced data classification.

Machine Learning model for heart failure prediction using LGBM Classifier.

Learning to Rank - Cross Sell

No description provided.

Early prediction of Mortality Risk among Covid -19 Patients in early stages when patients gets admitted into the hospital.

The task is to predict whether a passenger was transported to an alternate dimension during the Spaceship Titanic's collision with the spacetime anomaly. To help us make these predictions, we are given a set of personal records recovered from the ship's damaged computer system.

Various classification algorithms are implemented to predict whether a person is prone to or is suffering from heart disease.

Participated in Analytics Vidya Hackathon ( JOB-A-THON | May 2021 ). This Repository contains all code, reports and approach.

Identifying Giants and Dwarfs Stars through Machine Learning

Predicting Next Booking Destinations for Airbnb Users. Feel free to access the Streamlit App in the link below.

Bank Churn Classification

This project tackles the growing concern of obesity by developing a model to predict an individual's risk. By analyzing various factors, we aim to identify people who might be more susceptible to weight gain and related health problems.

This repository contain my final projekt on the Data science Skillbox school on the topic: "Development of a machine learning algorithm to predict the behavior of customers of the "SberAvtopodpiska"

Loan Eligibility - Classification (Python)

Rank 4/125 MachineHack