There are 10 repositories under data-science-project topic.
This documentation is like a quick snapshot of my project in the data field, showing off my skills and know-how in this area.
A Heart Attack Risk Prediction Project
Random forest analysis of match statistics and team performances in five seasons of the English Premier League (EPL)
A pipeline to scrape, extract, and analyze book data from web pages to insights.
Data analysis project using Python on NCRB Crime in India 2020 dataset. Includes data cleaning, visualization, and insights with Pandas, Seaborn, and Matplotlib.
We solve a regression problem in which it consists of calculating the health insurance charge in the United States Where we will break down the project into 5 phases: Exploratory Analysis. Feature Engineering. Selection of the ideal model. Development of the final model. Creation of a web application in streamlit.
The project is to recognize fraudulent credit transactions. You only need to put the dataset and model will detect the fraudulent credit transactions.
Data science project consisting of 4 parts: 1-Web Scraping 2-Data Preprocessing 3-Data Visualization 4-Machine Learning
A machine-learning model predicting crypto price from the time-series data
This is a Loan Approval Prediction Web App built with FastAPI (Backend) and HTML, CSS, JavaScript (Frontend). It predicts whether a loan application will be approved or not approved based on user input.
This is a Movie Recommendation System that suggests movies to users based on their preferences. The system uses machine learning techniques to recommend similar movies.
This project is a Streamlit-based interactive web application that allows users to explore 128 years of Olympic history (1896–2024) using data analysis and visualizations.
This project focuses on detecting fraudulent payment transactions using machine learning techniques.
Using exploratory data analysis and k-means clustering to analyze competitive balance in soccer/football
Scraping Data Science jobs, performing EDA, building a regression model and productionizing it.
Notebook and presentation on setting up a Big Data processing chain for image classification on AWS (EC2, EMR, S3, IAM, PySpark).
A simple and intuitive web application that predicts house prices based on user input (location, total square feet, number of bathrooms, and number of bedrooms). This app is built using Flask on the backend and a trained Linear Regression model pipeline using scikit-learn.
This is a machine learning web application built with Flask that predicts house prices in Lahore. It uses an XGBoost model trained on custom data and a clean frontend with HTML, CSS, and JavaScript.
So, market size analysis is a crucial aspect of market research that determines the potential sales volume within a given market
A machine learning python project on analyzing airline flight prices from different routes. A data science learning project taught by Shan Singh.
Time Series Analysis of Stock Prices. A data science practice real world project taught by Shan Singh
Forecasting stockout-aware category-level demand on FreshRetailNet‑50K using a 2-stage pipeline
The following insights are expected from this project. 1. Department wise performances 2. Top 3 Important Factors effecting employee performance 3. A trained model which can predict the employee performance based on factors as inputs. This will be used to hire employees 4. Recommendations to improve the employee performance based on insights from C
GLM with sklearn, joblib and SHAP project
A growing collection of data analytics projects by me—a former Business Analyst turned data storyteller. From SQL to Python, dashboards to predictions, each case study reflects real-world impact, curiosity, and a passion for turning data into decisions.
A modular Python project for trend classification and order fill modelling on financial time series.
Forecasted book sales using classical, ML, and DL models (e.g. ARIMA, XGBoost, LSTM)
This project explores a comprehensive movie dataset to uncover trends and insights related to runtime, genre popularity, IMDb ratings, director performance, and box office earnings. Using Python (Pandas, Matplotlib, Seaborn), we visualize patterns across thousands of movies, highlighting key factors influencing commercial and critical success.
A simple content-based movie recommender system using TF-IDF and cosine similarity, built with Streamlit.
Developed an interactive machine learning-based web application to predict customer churn using the Telco Customer Churn dataset. Implemented data preprocessing, model training techniques to handle categorical variables, missing values, and scaling.Built and deployed a Random Forest Classifier with a user-friendly Streamlit interface.
A 7-day hands-on journey into advanced ML techniques including XGBoost, LightGBM, SHAP, LIME, GridSearchCV, and API integration.
📊 Student Marks Analysis using Python and Pandas. Reads CSV data, calculates average & max marks, filters high scorers, and saves results to a new CSV file.