Naman Jain

Embark on a journey towards a greener future with this comprehensive Tableau dashboard focused on energy efficiency and emissions analysis. This powerful visualization tool provides a detailed look at the environmental landscape across different regions, offering invaluable insights for sustainability initiatives and policy-making.

Key aspects of this analysis include:

• Geospatial mapping of energy consumption patterns and emission hotspots
• Comparative analysis of waste generation and recycling rates across regions
• Trend analysis of renewable energy adoption and its impact on overall emissions
• Identification of areas with high potential for sustainability improvements
• Predictive modeling for future energy efficiency scenarios

This dashboard serves as a crucial resource for environmental scientists, urban planners, and policymakers, providing the data-driven insights needed to shape effective strategies for a sustainable future. By highlighting areas of concern and opportunity, it paves the way for targeted interventions and informed decision-making in the ongoing battle against climate change.

• Discover Insights

Dive into the fascinating world of cryptocurrency's influence on the PC hardware market with this comprehensive Power BI dashboard. This project meticulously analyzes the intricate relationship between cryptocurrency price trends, focusing on major players like Bitcoin and Ethereum, and their ripple effects on GPU pricing and availability.

Key features of this dashboard include:

• Real-time correlation analysis between crypto prices and GPU market dynamics
• Interactive filters for in-depth exploration of specific processors and time periods
• Visual representations of supply-demand fluctuations in the GPU market
• Predictive insights on potential market trends based on historical data

This tool is invaluable for tech enthusiasts, market analysts, and decision-makers in the PC hardware industry, offering a data-driven approach to understanding and anticipating market shifts influenced by the volatile world of cryptocurrencies.

• Explore the Dashboard

This project demonstrates the development of a sales forecasting model for pharmaceutical products using advanced analytics and machine learning techniques within the Databricks platform. Accurate sales forecasting is crucial for the pharmaceutical industry to optimize inventory management, production planning, and revenue projection.

Key features of this project include:

• Data Cleaning: Handles missing values, inconsistent formats, and outliers.
• Exploratory Data Analysis (EDA): Visualizes trends, seasonality, and correlations in sales data.
• Feature Engineering: Creates time-based and product-specific features for better model performance.
• Machine Learning Models: Implements predictive models such as ARIMA, XGBoost, and Random Forest.
• Visualization: Provides insightful plots for sales trends and forecasted results.

This project offers valuable insights for businesses seeking to improve sales forecasting accuracy and optimize resource planning.

• View on GitHub

Embark on a comprehensive journey through Arizona's traffic safety landscape with this cutting-edge Tableau dashboard. This project offers an in-depth analysis of traffic accidents across the state from 2016 to 2020, providing crucial insights for enhancing road safety and reducing accident rates.

Key features of this analysis include:

• Interactive heat maps highlighting high-risk zones and accident hotspots
• Temporal analysis showing accident patterns by time of day, day of week, and seasonality
• Correlation studies between weather conditions and accident frequency
• Detailed breakdown of accident types, including DUI incidents
• Trend analysis for identifying long-term patterns and emerging risk factors

This powerful tool is designed to support data-driven decision-making for traffic authorities, urban planners, and public safety officials. By providing a clear, visual representation of accident data, it enables targeted interventions, resource allocation, and policy formulation to significantly enhance road safety across Arizona.

• Analyze Safety Data

Predict customer churn using machine learning models to help a telecom company identify at-risk customers and implement retention strategies. The project leverages Logistic Regression, Random Forest, and XGBoost models, with the highest accuracy achieved using XGBoost.

Key highlights of the project:

• Data preprocessing: Handled missing values, encoded categorical features, and scaled numerical features.
• Exploratory Data Analysis: Identified key patterns such as the high churn rate for month-to-month customers and users with fiber optic internet.
• Model performance: XGBoost model achieved an ROC-AUC score of 81.7%.
• Model Deployment: The final model was deployed using Flask with a REST API endpoint for real-time predictions.

This project offers valuable insights for businesses seeking to reduce customer churn and enhance retention strategies.

• View on GitHub

This project focuses on building a machine learning model to predict the mortality risk of COVID-19 patients. By leveraging supervised learning techniques, the model aims to identify high-risk patients, enabling timely interventions to save lives and optimize healthcare resources.

Key features of this project include:

• Comprehensive data cleaning and preprocessing, including handling missing values, standardizing binary variables, and normalizing numerical features.
• Application of multiple supervised learning models: logistic regression, K-nearest neighbors (KNN), Naive Bayes, decision tree, and random forest.
• Comparative model evaluation to identify the best-performing algorithm.
• Visualization of key findings for interpretability and decision-making.

This project provides actionable insights for healthcare providers to prioritize resources and design targeted intervention strategies.

• View on GitHub