Chetan Jagadeesh
About Chetan Jagadeesh
Chetan Jagadeesh is a Data Analyst currently employed at Sezzle, where he has worked since 2022. He holds a Master's certificate in Machine Learning and Artificial Intelligence and has developed models for fraud detection and credit risk reduction.
Work at Sezzle
Chetan Jagadeesh is currently employed at Sezzle as a Data Analyst since 2022. In this role, he has designed and developed a fraud detection model that maintains an approval rate of 70-75% while managing risk. He has also created a credit risk model using machine learning algorithms, which successfully reduced risk by 9%. Additionally, he implemented a dynamic credit limit allocation system for users based on behavior analysis. Prior to his current position, he completed a Data Analyst Internship at Sezzle in 2021 for one month.
Education and Expertise
Chetan Jagadeesh holds a Master's certificate in Machine Learning and Artificial Intelligence from Univ.ai, which he completed from 2021 to 2022. He also earned a Bachelor's degree in Electronics and Communications Engineering from REVA University, studying from 2014 to 2018. His foundational education includes a Pre-University Course from Vidya Mandir Ind. PU College in Bangalore from 2012 to 2014, and he completed his Class 10 (CBSE) at Sindhi High School in 2012.
Background
Chetan Jagadeesh has a diverse background in data analysis and engineering. He began his career as a Summer Intern at Bharat Electronics Limited in 2017 for two months. Following this, he worked at IBM as an Associate System Engineer and Oracle Application Developer in 2018 for three months in Bengaluru, Karnataka, India. His experiences in these roles contributed to his expertise in data analytics and machine learning.
Achievements
Chetan Jagadeesh has made significant contributions in his field, particularly during his tenure at Sezzle. He designed a fraud detection model that effectively balances approval rates and risk management. His credit risk model, developed using machine learning algorithms, achieved a risk reduction of 9%. Additionally, he implemented a system for dynamic credit limit allocation based on user behavior analysis, showcasing his ability to apply machine learning techniques to real-world problems.