Prudhvi Kiran Chinta

Project:

• Developed and optimized machine learning models for various business applications using Python, NumPy, Pandas, Scikit-learn, TensorFlow, and PyTorch.
• Designed and implemented end-to-end solutions, including data preprocessing, feature engineering, model training, evaluation, and deployment.
• Integrated models into Flask and FastAPI applications for batch testing and seamless accessibility. Deployed models to SharePoint, AWS, and Azure, enabling real-time decision-making and collaboration.
• Utilized Power BI for data visualization, SQL for database management, and Docker for containerized deployment.
• Still working on NLP and generative AI techniques to enhance automation and AI-driven solutions, ensuring scalability, and operational efficiency.

Project: Customer Churn Risk Analysis and Retention.

• Designed and implemented a SQL-based data pipeline to extract, clean, and process customer transaction and engagement data for churn analysis.
• Collaborated with stakeholders to define churn risk indicators based on historical patterns, segmenting customers into low, medium, and high-risk categories using SQL-based logic.
• Developed an interactive Power BI dashboard to visualize churn trends, risk segmentation, and retention effectiveness, incorporating drill-down views for in-depth customer analysis.
• Automated weekly and monthly reports using Python and SQL, streamlining reporting processes, and reducing manual efforts.
• Implemented data validation checks to enhance reporting accuracy and consistency.
• Enabled the sales team to proactively engage at-risk customers, improving retention, and optimizing business performance through real-time tracking of retention strategies.

Project: Customer Order Behavior Tracker.

• Designed and developed an SQL-based tracking system to analyze customer order patterns and identify delayed deliveries.
• Optimized SQL queries to extract order data from multiple sources, including order processing systems, shipment tracking, and warehouse logs.
• Built data pipelines to process and aggregate real-time order statuses, ensuring continuous visibility into delays.
• Implemented an order status categorization system using business rules in SQL, classifying orders as On-Time, Delayed, or Exception Cases.
• Developed an interactive Power BI dashboard to monitor daily, weekly, and monthly order trends, enabling real-time tracking of delays vs. On-time deliveries. Utilized Python (NumPy, Pandas, Matplotlib, Seaborn, Statistics) for data analysis, trend identification, and root cause detection of order delays.
• Provided insights into delivery performance across different locations, product categories, and vendors, helping to optimize logistics planning and improve overall supply chain efficiency.