ML project focused on predicting Titanic passenger survival using various algorithms and extensive data analysis techniques. This project includes detailed data visualization and interpretation to uncover key factors affecting survival. By leveraging various ML models the analysis aims to achieve high predictive accuracy.

A multi-functional library for full-stack Deep Learning. Simplifies Model Building, API development, and Model Deployment.

This repository contains the LifeExpectancy Prediction Project, a comprehensive data science project aimed at predicting life expectancy based on various health, economic, and social factors. The project includes steps for data preprocessing, exploratory data analysis (EDA), model selection, training, hyperparameter tuning, and model interpretation

Prediction of students' dropout using classification models. Data visualisation, feature selection, dimensionality reduction, model selection and interpretation, parameters tuning.

Analyzed customer churn using transaction data. Built ML model to predict lapses. Dataset includes customer status, collection/redemption info, and program tenure. Delivered business presentation outlining modeling approach, findings, and churn reduction strategies.

Creating predictive models to classify Trump's vote share and clustering counties based on demographics and economic variables. Report findings in PDF with detailed methodologies, model assessments, and R code for the project.

Advise one of Cognizant’s clients on a supply chain issue by applying knowledge of machine learning models.

Cognizant Artificial Intelligence job simulation on Forage.

Benchmarking bank data to enhance marketing strategies. Models: Decision Tree and Random Forest. Libraries: Pandas, Matplotlib, Seaborn, Scikit-Learn, Numpy. Findings: Customer patterns and seasonal behaviors.

A python library for decision tree visualization and model interpretation.

Integrating multimodal data through heterogeneous ensembles

I performed 4 different tasks during the Data Science & Advanced Analytics virtual internship provided by BCG via Forage. I successfully utilized the Random Forest model to predict customers likely to churn, enabling me to proactively address potential losses.

InterpretDL: Interpretation of Deep Learning Models，基于『飞桨』的模型可解释性算法库。

The primary objective of this study is to develop a dependable and precise prediction model to forecast alterations in Bitcoin's hash rate.

Exploratory data analysis, data modelling, model building and interpretation, machine learning production, quality assurance

This project included a XGBoost Regression model, which predict the purchase possibility of a customer customer based on their online shopping behavior. In addtion, a recommendation model including both CF and CBF was built using customer purchase transaction data.

This repository has all of the assignments I had to do for the Standard Bank Data Science Virtual Experience Program. 📉👨‍💻📊📈

Streamlit dashboard frontend (user interface) to deploy a machine learning model to the web

API backend to deploy a machine learning model to the web

What Has Been Enhanced in my Knowledge-Enhanced Language Model?