bigdataanalytics

In this project, we have developed 'Smart Glove' - a sign language translator. It consists of both hardware and software modules for translation and prediction analysis. We perform real-time translation of hand gesture into speech and text. In this project, we have used different machine learning models for prediction analysis including KNN, SVM…

Scalable ETL Pipeline: Processing 5M+ retail records with PySpark on GCP Dataproc. Automated the extraction of global business KPIs and consumer trends. Includes an Ethical Data Framework to ensure privacy and fairness at scale

Open Standard for Metadata. A Single place to Discover, Collaborate and Get your data right.

KMeans Clustering using Spark on Uber's ride share data - Case Study (Big Data Analytics @uber)

Big Data in Action: a customer sentiment prediction initiative using PySpark and Databricks, tackling over 49,000 e-commerce orders and reviews.

Analyze fraudulent credit card transactions using Kafka, Spark Streaming, and Random Forest Classifier algorithms in PySpark

Explore Python para análise de dados com este repositório. Desenvolva um modelo de regressão linear para prever casos de dengue e utilize aprendizado de máquina para classificar dados do conjunto Iris.

Big Data Analysis on a Covid-19 Dataset

Near-real-time data warehouse prototype using Python and MySQL. Implements a HYBRIDJOIN-based ETL pipeline to process transactional streams and integrate master data into a star schema for efficient analytics and OLAP queries.

Flight delay prediction system using PySpark and machine learning, with cascade risk modeling and an interactive Streamlit dashboard.

The aim of the project is to gain insights into customers' booking behaviors, preferences, and decision-making processes when reserving hotel accommodations.The data analysis process involves cleaning and organizing the hotel reservation data and generating visualizations and reports to present the findings.