A project of using machine learning model (tree-based) to predict short-term instrument price up or down in high frequency trading.

Open solution to the TalkingData AdTracking Fraud Detection Challenge

🟣 LightGBM interview questions and answers to help you prepare for your next machine learning and data science interview in 2025.

This is Kaggle Competition for predicting next 28 data sales for products in 3 states of United States

Data Mining Final Project

Predicting the medical costs charged by health insurers

Earthquake Prediction using Regression Models

multi-variate deep time series forecasting ensemble models

Predicting the time remaning for the next Earthquake. Kaggle Competition

Heroku web service client for sklearn2sql

Determining whether two questions are asking the same thing can be challenging, as word choice and sentence structure can vary significantly. Traditional natural language processing techniques been found to have limited success in separating related question from duplicate questions. In this paper, we explore methods of determining semantic equi…

A Light GBM and LSTM based model to predict whether a windows machine will soon be affected by a malware based on the specifications of the machine.

Sauti East Africa request for a segmentation analysis on all of their user's behavior. Sauti wishes to better optimize their menu design and explore the feasibility of smart menus based on user predicted behavior.

A logistic regression model with cross-validation strategy employed onto it to produce good enough results for India ML Hiring Hackathon 2019 and securing 410th rank.

[KSC 학부생 논문] Short-Form 영상 시청 패턴 분석 및 영상 시청 여부 예측 모델 개발 (장려상)

A project initiated to participate in DataMeka Singapore Competition to predict house prices. Multiple models are developed and compared, whereas LightGBM performs the best.

This project predicts driver attrition at Ola using ensemble models (Random Forest, XGBoost, LightGBM). It includes data preprocessing, feature engineering, imbalance handling, and model tuning, evaluated with Precision, Recall, F1, and ROC-AUC to identify churn factors and improve retention.

Provide pricing prediction as guideline for future airbnb hosts

This project is a comprehensive machine learning dag pipeline designed to predict the potability of water. It integrates various stages of the machine learning lifecycle, from data extraction and cleaning to model training and evaluation.

Solution to the Kepler exoplanet hunt by SmokeTrees