I am doing my MSc in Computer Science.

github

Mukesh Kumar prajapat  • Peerlist

Credit Card Fraud Detection using ANN is a sophisticated deep learning solution aimed at identifying fraudulent credit card transactions. Utilizing Artificial Neural Networks (ANN), the model meticulously analyzes transaction patterns to differentiate between legitimate and fraudulent activities. The system effectively addresses the challenge of imbalanced data through techniques like SMOTE (Synthetic Minority Over-sampling Technique) and offers a user-friendly web interface via Streamlit for real-time predictions.<h3>Key Features</h3><ul><li>Deep Learning Model: Built using TensorFlow/Keras with a Sequential ANN architecture.</li><li>Data Preprocessing: Implemented StandardScaler for feature normalization.</li><li>Imbalance Handling: Used SMOTE to balance the dataset.</li><li>Interactive UI: Deployed on Streamlit for easy user interaction.</li><li>Real-time Prediction: Classifies transactions as "Normal" or "Fraud" instantly.</li></ul><h3>Technologies Used</h3><ul><li>Programming Language: Python</li><li>Deep Learning Framework: TensorFlow / Keras</li><li>Libraries: Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn</li><li>Deployment: Streamlit</li><li>Tools: Jupyter Notebook / VS Code</li></ul>

credit_card_fraud_detection

🔑 Pipeline Stages: • Data Injection: Extracted raw data directly from MySQL for structured ingestion • Data Transformation: Cleaned, processed, and feature-engineered datasets for model readiness • Model Training: Automated experiments with MLflow for tracking parameters, metrics, and versions • Data & Model Versioning: Leveraged DVC + DagsHub for reproducible datasets and collaborative workflows • Model Monitoring: Continuous evaluation and logging to ensure reliability and performance Deployment: • Flask API for backend model serving Live Deployed Streamlit App: Hosted interactive dashboard with 50/50 input-output layout, staged animations, and color-coded risk tiers for clarity and trust ⚙️ Tech Stack: GitHub DagsHub MLflow DVC MySQL Flask Streamlit 💡 Outcome: A fully operational MLOps-driven insurance prediction system that makes risk scoring transparent, interactive, and audience-ready. This project demonstrates how modular ML design, reproducible pipelines, and professional dashboards can deliver real-world impact.

🔥 End-to-End Health Insurance Prediction Pro

Project Overview This project predicts house prices based on various features like area, location, number of rooms, and amenities. It demonstrates a complete machine learning pipeline—from data preprocessing to model deployment—making it ideal for learners and developers aiming to build real-world ML applications. 🚀 Features End-to-end ML pipeline using Scikit-learn Data cleaning, encoding, scaling, and feature engineering Comparison of Linear, Lasso, and Ridge Regression models Evaluation using R² Score, MAE, and MSE Interactive web app built with Streamlit / Flask Modular codebase with app.py Professional UI with sidebar navigation and result placement Optional deployment on GitHub git clone https://github.com/imukeshkumarprajapat/house_price_prediction live>>https://housepriceprediction-4gaxewvefhgtlvhfp6cpqv.streamlit.app/

🏡 House Price Prediction – Machine Learning 

Plant Disease Detection using Deep Learning is a powerful Streamlit-based web application designed to identify potato leaf diseases such as Healthy, Early Blight, and Late Blight. Utilizing a trained Convolutional Neural Network (CNN) model built with TensorFlow and Keras, this application offers an end-to-end workflow from data preprocessing to model training, evaluation, and deployment. Key features include the ability to upload leaf images for instant disease predictions, complete with confidence scores. The interactive dashboard provides visualization tools like a Confusion Matrix and performance comparisons between validation and test datasets. The application is easily deployable with Streamlit and uses a lightweight .h5 model format for portability. The dataset is sourced from the PlantVillage dataset, containing approximately 2,152 images split into train, validation, and test sets. The model architecture features multiple Conv2D and MaxPooling layers, followed by Flatten and Dense layers, with a Softmax output for three classes. Data augmentation techniques such as Random Flip and Random Rotation are employed, and the model is optimized using the Adam optimizer with SparseCategoricalCrossentropy loss. Achieving high accuracy rates of 96.88% on validation and 97.84% on test datasets, this application is a robust tool for plant disease detection.

plant-disease-detection

<h3>Sentiment Analysis Project</h3>This project is a sentiment analysis tool developed by imukeshkumarprajapat, hosted on GitHub. It leverages the power of AI to analyze and interpret the sentiment of textual data, providing valuable insights for developers and businesses alike. The project is built using Python, a versatile programming language known for its robust libraries and frameworks, making it ideal for data analysis and machine learning tasks.Key Features:<ul><li>Utilizes machine learning models to perform sentiment analysis.</li><li>Includes pre-trained models such as logistic regression for efficient sentiment classification.</li><li>Employs vectorization techniques like TF-IDF to process and analyze text data.</li><li>Open source and available for contributions on GitHub.</li></ul>This project is particularly useful for developers looking to integrate sentiment analysis capabilities into their applications, offering a comprehensive solution for understanding customer feedback and market trends. By contributing to this project, developers can enhance their skills in AI and machine learning, while also supporting the open-source community.

setniment-analysis

🔑 Pipeline Stages:
• Data Injection: Extracted raw data directly from MySQL for structured ingestion
• Data Transformation: Cleaned, processed, and feature-engineered datasets for model readiness
• Model Training: Automated experiments with MLflow for tracking parameters, metrics, and versions
• Data &amp; Model Versioning: Leveraged DVC + DagsHub for reproducible datasets and collaborative workflows
• Model Monitoring: Continuous evaluation and logging to ensure reliability and performance

Deployment:
• Flask API for backend model serving

Live Deployed Streamlit App: Hosted interactive dashboard with 50/50 input-output layout, staged animations, and color-coded risk tiers for clarity and trust
⚙️ Tech Stack: GitHub DagsHub MLflow DVC MySQL Flask Streamlit
💡 Outcome:
A fully operational MLOps-driven insurance prediction system that makes risk scoring transparent, interactive, and audience-ready. This project demonstrates how modular ML design, reproducible pipelines, and professional dashboards can deliver real-world impact.

This project is an end-to-end machine learning web application designed to predict the risk of heart disease based on user-provided health metrics. Built using Python, Streamlit, and Scikit-learn, the app allows users to input key cardiovascular indicators such as age, cholesterol levels, blood pressure, and ECG results. The model, trained on a medical dataset, uses a preprocessed pipeline with scaling and one-hot encoding to deliver real-time predictions.

Interactive UI built with Streamlit

Real-time prediction using a trained ML model

Scaled and encoded inputs for accurate classification

Deployment on Streamlit Cloud for public access

Heart Disease Risk Predictor using Machine Le

Project Overview This project predicts house prices based on various features like area, location, number of rooms, and amenities. It demonstrates a complete machine learning pipeline—from data preprocessing to model deployment—making it ideal for learners and developers aiming to build real-world ML applications.

🚀 Features

End-to-end ML pipeline using Scikit-learn
Data cleaning, encoding, scaling, and feature engineering
Comparison of Linear, Lasso, and Ridge Regression models
Evaluation using R² Score, MAE, and MSE
Interactive web app built with Streamlit / Flask
Modular codebase with app.py
Professional UI with sidebar navigation and result placement
Optional deployment on GitHub
git clone https://github.com/imukeshkumarprajapat/house_price_prediction

live&gt;&gt;https://housepriceprediction-4gaxewvefhgtlvhfp6cpqv.streamlit.app/