aniketraut18 Goto Github PK

adventure-work-bike-shop

This project involved utilizing Microsoft Power BI to clean, process, transform, and visualize the Adventure Works Bike Shop dataset. The primary objective was to create an insightful and interactive dashboard to present key findings and support data-driven decision-making for the bike shop.

aws-sagemaker-ml-mobile-price-prediction-model

This project demonstrates the full lifecycle of a machine learning model on AWS SageMaker, from training and deployment to endpoint management, ensuring cost efficiency and proper resource utilization.

car-rental-management-system

dine-smart

This project analyzes a FoodHub dataset to uncover insights into order trends, customer preferences, and service efficiency. Using Python's Pandas, NumPy, Matplotlib, and Seaborn, it aims to enhance service quality, customer satisfaction, and business growth through data-driven decisions.

end-to-end-zillow-data-engineering-pipeline-with-aws-and-airflow

Data Engineering pipeline that automates ETL of Zillow real estate data using AWS (IAM, S3, Lambda, Redshift) and Apache Airflow. This workflow efficiently processes and stores data for analysis. Additionally, I utilized Amazon QuickSight to create interactive dashboards and visualizations, transforming raw data into actionable insights.

fake-and-real-news-detection

Natural Language Processing Techniques for Distinguishing Between Fake and Real News: A Comparative Study of Machine Learning Models

finalyear_project

I have developed a model, by extracting sentiments and historical data to predict the future price of Bitcoin cryptocurrency using Keras API

frequent-flier-management-system

ibm-watson-dataanalysis

An IBM Watson script for analyzing marketing effectiveness, featuring data preprocessing, exploratory analysis, and predictive modeling with logistic regression and SVM. Includes cross-validation and feature importance visualization for insights

k-means-clustering-with-dimensionality-reduction-for-iris-and-image-data

movie-analytics

This project focuses on using hypothesis testing to determine if differences between sample and population movie ratings are statistically significant, utilizing Python for data analysis and visualization to uncover meaningful insights.

olympic-de-project

spark-based-advanced-movie-recommendation

spark-based-text-data-analysis

titaniceda

Exploratory Data Analysis of Titanic dataset