Binary classification and Multiclass classification with pipelining and parameter tuning with GridsearchCV and RandomizedSearchCV

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.

I developed the model to attain the predictive analysis in this task.

Training a model to predict whether a given job posting is fake or not

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

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

Build and Deploy a binary classification model as a plagiarism detector

The given data includes airline reviews from 2016 to 2019 for popular airlines around the world with multiple choice and free text questions. Data is scrapped in spring2019.The main objective is to predict whether passengers will refer the airline to their friends.

This is a machine learning model built in python3 to predict transaction conversion of web visits for an e-commerce website.

This repository serves as a comprehensive resource for understanding and implementing various feature selection techniques, gaining familiarity with Jupyter Notebook, and mastering the process of model training and evaluation

A web application that employs machine learning models to provide accurate and instant car price estimations based on various features and specifications.

A Python Machine Learning Project designed to predict Halloween Candy sales for a company based on historical data

Car Insights with Machine Learning

Semantic Similarity on SNLI dataset using BERT as well as TF-IDF+BERT(Pooled) embeddings.

This project focuses on the classification of banknotes using various supervised machine learning models. The primary objective is to develop a robust system that can accurately distinguish between genuine and counterfeit banknotes based on a set of features.

The aim of this project is to solve a Supervised Image Classification problem of classifying the flower types - rose, daisy, dandelion, sunflower, & tulip which can predict the class of the flower using the Convolutional Neural Networks (CNN), ResNet50 and transfer learning

Predicting the age of crabs using machine learning techniques based on physical characteristics.

Towards evaluation of fairness in MDD models: Automatic analysis of symptom differences for gender groups in the D-vlog dataset

Developed advanced regression models to predict house prices using the Ames Housing dataset. Achieved a grade of 90% under Prof. Vered Aharonson and ranked 550th in the Kaggle competition.

Titanic Machine Learning from Disaster