Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View praveensatyarv's full-sized avatar

Block or report praveensatyarv

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
praveensatyarv/README.md

๐Ÿ‘‹ Hi there, I'm Praveen Satya

I'm a Data Analyst & AI-Powered BI Engineer passionate about transforming complex data into actionable insights. I recently graduated from UT Dallas with a Masterโ€™s in Business Analytics & AI and bring 3+ years of experience solving business problems with data.

From anomaly detection to AI-driven insights tools, I enjoy building solutions that scale decision-making, save time, and unlock business value.


๐Ÿš€ What I Do

  • ๐Ÿ’ก AI-Powered Analytics: Built the AI Data Assist tool that reduced ad-hoc analysis from days to 5 seconds.
  • ๐Ÿ›ก๏ธ Anomaly Detection: Prevented $100K+ in revenue loss by automating anomaly detection across 70+ metrics.
  • ๐Ÿ“Š Dashboard Optimization: Cut Tableau dashboard load time from 20s to <5s using SQL tuning & best practices.
  • ๐Ÿค– AI Root-Cause Agent: Built Gemini-powered RCA agent that eliminated 40+ hours of manual investigation per case.
  • ๐Ÿ“ˆ Business Benchmarking: Delivered $325K in potential savings via subhauler cost analysis dashboard.

๐Ÿ›  Tools & Technologies

  • Languages: Python, SQL, R
  • BI & Visualization: Power BI, Tableau, Looker Studio
  • ML & Modeling: XGBoost, Random Forests, Regression, PyTorch, SMOTE
  • Data Engineering: BigQuery, Airflow, Hadoop, Spark, Hive, Alteryx
  • Cloud Platforms: Google Cloud Platform (GCP)
  • Certifications: Tableau Desktop Specialist, Alteryx Designer Core, Data Analyst in Power BI (Datacamp)

๐Ÿ“š Education

  • ๐ŸŽ“ UT Dallas โ€“ M.S. in Business Analytics & Artificial Intelligence
  • ๐ŸŽ“ BITS Pilani โ€“ B.E. in Manufacturing Engineering

๐Ÿ† Highlights

  • ๐Ÿฅ‡ Winner, Alteryx SparkED Hackathon ($16K prize)
  • ๐Ÿง‘โ€๐Ÿซ Mentor, Business Analytics Leadership Council
  • ๐Ÿง  Deanโ€™s Scholar (Top 5% at UTD, twice)

๐Ÿ“ซ Letโ€™s Connect


โ€œBuilding tools that make data speak, so businesses donโ€™t have to guess.โ€

Pinned Loading

  1. brazilian_ecommerce_project brazilian_ecommerce_project Public

    This project uses e-commerce logistics data from Olist to analyze freight costs, shipment delays, and delivery cycle times. It uncovers bottlenecks in last-mile delivery, seller performance, and geโ€ฆ

  2. vehicle_auction_analysis vehicle_auction_analysis Public

    This project uses vehicle auction data to identify key factors affecting sale prices and auction timelines, uncovering insights and strategies to optimize auction efficiency, inventory management, โ€ฆ

    Jupyter Notebook

  3. customer_churn_analysis customer_churn_analysis Public

    Databel is an internet service provider experiencing a loss of customers. The company wants to know why the customers are churning. In this case study, we will analyze the company data using Power โ€ฆ

  4. uk_flights_anomaly_detection uk_flights_anomaly_detection Public

    This project uses Prophet model to detect anomalies in the UK flight numbers. Early detection can help the stakeholders in better decision making and resource management.

    Jupyter Notebook

  5. seoul_bike_sharing_demand seoul_bike_sharing_demand Public

    This project utilizes time series forecasting models, such as VAR and ARIMAX, to predict the bike share demand in Seoul. In turn, ensuring availability and minimizing waiting times for customers.

    R

  6. Online_Shoppers_Purchasing_Intent Online_Shoppers_Purchasing_Intent Public

    E-commerce faces low conversion rates due to the lack of in-store personalization. This project aims to build a machine learning model to predict purchase behavior, addressing challenges like classโ€ฆ

    Jupyter Notebook