Realtime Sign Language Detection: Deep learning model for accurate, real-time recognition of sign language gestures using Python and TensorFlow.

Master data analysis, visualization, Python, machine learning, and real-world projects to drive data-driven decisions and advance your career in tech, business, or analytics.

To import data from multiple sources, clean and wrangle data, perform exploratory data analysis (EDA), and create meaningful data visualizations. I will then predict future trends from data by developing linear, multiple, polynomial regression models & pipelines and learn how to evaluate them.

Model Evaluation is the process through which we quantify the quality of a system’s predictions. To do this, we measure the newly trained model performance on a new and independent dataset. This model will compare labeled data with it’s own predictions.

Label-Free Model Evaluation and Weighted Uncertainty Sample Selection for Domain Adaptive Instance Segmentation

I developed a sophisticated ML model using LLMs to predict user preferences in chatbot interactions.implemented a comprehensive data preprocessing pipeline,including feature extraction and encoding,to optimize performance. conducted extensive hyperparameter tuning and evaluation, enhancing accuracy and in AI-driven conversational systems.

machine learning techniques to predict company defaults by optimizing the trade-off between recall (minimizing false negatives) and precision (avoiding false positives). Logistic Regression and Random Forest models were trained, with emphasis on recall to ensure accurate identification of high-risk companies.

The objective of this project is to recognize hand gestures using state-of-the-art neural networks.

This project implements Google Cloud's Vertex AI to develop a machine learning model that predicts loan repayment risks using a tabular dataset. It encompasses data preparation, model training, evaluation, deployment, and prediction processes.

This repository contains code for evaluating different machine learning models for classifying fake news. The dataset used for this evaluation consists of labeled news articles as either "REAL" or "FAKE". Three popular classifiers, Support Vector Machine (SVM), Decision Tree, and Logistic Regression, are trained and evaluated on this dataset.

Data Preprocessing, Data Cleaning, Fine-tuning the Hyperparameters,

Building a model to predict demand of shared bikes. It will be used by the management to understand how exactly the demands vary with different features. They can accordingly manipulate the business strategy to meet the demand levels.

BC4AI：Blockchain Used to Guarantee Credibility of AI Model Evaluations;利用区块链来保证算法模型的真实性

SeqFlipAttention is a forward‑looking PyTorch demonstration of sequence‑to‑sequence learning enhanced by attention, trained on a synthetic reverse‑sequence task and complete with training scripts, loss and accuracy visualizations, and a quantitative analysis of attention’s impact on performance.

This repository contains mini projects inData science in python with notebook files

An advanced machine learning project deploying a model for Titanic passenger survival prediction, including deployment on ngrok for easy access.

The aim of this project is to predict fraudulent credit card transactions using machine learning models.

This repo hosts an end-to-end machine learning project designed to cover the full lifecycle of a data science initiative. The project encompasses a comprehensive approach including data Ingestion, preprocessing, exploratory data analysis (EDA), feature engineering, model training and evaluation, hyperparameter tuning, and cloud deployment.

A bike-sharing system is a service in which bikes are made available for shared use to individuals on a short term basis for a price or free. Many bike share systems allow people to borrow a bike from a "dock" which is usually computer-controlled wherein the user enters the payment information, and the system unlocks it.