Pruthviraj Chavan Email & Phone Number

I have a natural gift of making confident decisions under uncertainty! (and sometimes I give credit to mathematics and statistics as well :P). Responsibilities don’t intimidate me—once I take something on, I bring an unwavering determination, much like Steve Rogers! I embrace challenges with a strategic mind, and watching me engineer innovative solutions to complex problems would remind you Tony for sure! When teamwork is required, I approach it with the collaborative spirit and humor of Peter Parker, knowing that great things are achieved together. Whether it’s leading cost-saving initiatives, optimizing supply chains, or developing creative solutions, I bring super innovative ideas to the table.

Listed skills include Leadership, Sap S/4Hana, R, Lean Manufacturing, and 50 others.

• 

  Senior Logistics Data Analyst

  Tesla

  Aug 2024 - Present - Fremont, California, United States

  • Directing a cross-department program targeting a 5% improvement improve the trucking load factor in 6 months saving $1.13M annually. Leveraging Lean Six Sigma methodology to drive measurable outcomes and progress tracking.• Spearheading a cost improvement initiative by collaborating with finance partners to analyze the $35M cost center and develop a tableau cost tracking report to identify and track cost improvement opportunities.• Developing an analytical method using mathematical modeling to calculate axle weight distribution for a 9-car hauler to identify overloading of trucks which minimizes overweight violations, creates safer driving conditions while maximizing loading efficiency of trucks. The current accuracy of the model is 85-90%.• Developed and implemented a driver performance scorecard in Tableau, creating a data pipeline to extract, transform, and load data from three databases using SQL. Generated 15+ KPIs across three driver categories, producing an unbiased 0-100 performance rating to help supervisors evaluate driver performance.• Explored potential governing factors behind logistics drivers' estimated arrival times, employing optimized data pipelines, data cleaning, advanced variable selection (Best Subset, Regularization), and fitting multiple predictive models (GLMs, Second-Order models, PCR, Regression trees and Ensemble Models) in R to enhance accuracy and interpretability, resulting in highlighting most impactful factors for the arrival times.• Advocated a system change by simulating the process bottleneck using a Stochastic approach that reduces the variance in vehicle batching, ensures faster lane fill time and a significant reduction in the strain on the buffer system – Logistics yard – by 10-15 % (est.)• Redefined performance expectations from the operations team by statistically analyzing 260,000 possible vehicle configurations in a lane and establishing a theoretical maximum expected throughput for the trucking operation.