INSAID Assignment to create a ML model to detect fraud transactions for a financial company.

Analytical understanding and applying parameter optimization, regression with gradient descent to predict water quality levels across Indian waters.

This project showcases a Network Intrusion Detection System (NIDS) designed to bolster cybersecurity defenses against evolving threats

Credito - Credit Risk Analysis using XGBoost Classifier with RandomizedSearchCV for loan approval decisions.

We build a chatbot by implementing machine learning and natural language processing.

Focused on advancing credit card fraud detection, this project employs machine learning algorithms, including neural networks and decision trees, to enhance fraud prevention in the banking sector. It serves as the final project for a Data Science course at the University of Ottawa in 2023.

[CIKM 2021] Code and dataset for "Label-informed Graph Structure Learning for Node Classification"

Feature Engineering with Python

Project is about predicting Class Of Beans using Supervised Learning Models

WiDS Datathon 2020 on patient health through data from MIT’s GOSSIS (Global Open Source Severity of Illness Score) initiative.

This sentiment analysis model utilizes a Transformer architecture to classify text sentiment into positive, negative, or neutral categories with high accuracy. It preprocesses text data, trains the model on the IMDB dataset, and effectively predicts sentiment based on user input.

This repository covers my code using regression models to predict if a customer would be exiting a bank or not. It also capture the use classification models to classify if a customer has left the bank or not (binary classification).

This repository is a comprehensive guide to different Encoding techniques in Machine Learning, explaining when to use each method and best practices. You'll find practical examples, ready-to-use code, and comparisons between various techniques like Label Encoding, One-Hot Encoding, Target Encoding, and more!

No description provided.

Repo houses the predictive NN model and its associated .py modules

Built various machine learning models for banks to develop effective credit rating

the code uses KNN, Gaussian Naive Bayes & SVM to classify images. It preprocesses, normalizes data, applies PCA , computes accuracy, precision etc. It evaluates k-NN using Euclidean distance & cosine similarity, visualizing results with line plots, 3D scatter plots, & confusion matrices to demonstrate classifier performance.

Liver Cirrhosis Stage Detection System Using Random Forest and XGBoost with Stacking Classifier

Unofficial but extremely useful Label and One Hot encoders.

🔴 Predicting Insurance Claim Amounts 🔴 This project analyzes the Medical Cost Personal Insurance Dataset to understand key factors influencing healthcare expenses. Through data cleaning, visualization, and feature engineering, important patterns in age, BMI, smoking, and region were uncovered.

Database management and data analytics from a car-sharing dataset. The dataset contains information about the customers' demand rate between January 2017 and August 2018.

This project analyzes employee attrition using machine learning models, including Logistic Regression, Random Forest, and XGBoost. The objective is to identify key factors influencing employee turnover and provide insights to improve retention strategies

This classification task is specifically dependent on a video dataset that includes video clips of kill and death scenes from the first-person shooting game “CS Go”. I have used the ResNet-50 model for image classification and then turn it into a more accurate video classifier by employing the rolling averaging method.

This project focuses on analyzing patient feedback regarding the treatment provided by home healthcare service agencies.

Data Set: House Prices: Advanced Regression Techniques Feature Engineering with 80+ Features

Predicting stroke risk using machine learning models based on healthcare and demographic data.

This is an esophageal cancer detection project which uses dataset from Kaggle. The dataset has been attached to this repo. This repo also contains codes in both jupyter notebook and pdf format. The code involves techniques like EDA and feature engineering, LabelEncoding and One-Hot-Encoding and the model used is Linear Regression.

This is an implementation for a DataCamp project: A Visual History of Nobel Prize Laureates. We try to answer the proposed questions and visualize the results.

A machine learning project that predicts water potability based on chemical and physical attributes, using models like Logistic Regression, Random Forest, and XGBoost.

Empower Sakhi is a data-driven platform that uses machine learning to identify women at risk of domestic violence in India. It offers confidential self-assessments, survivor stories, and emergency resources through a trauma-informed, privacy-focused web app. The project also provides NGOs with actionable insights via Power BI dashboard for support.