Somsuvro Mandal
About Somsuvro Mandal
Somsuvro Mandal is an Associate Software Engineer at HighRadius, specializing in machine learning and forecasting methods. He has contributed to improving forecasting accuracy and code integrity through various innovative approaches during his tenure at the company.
Work at HighRadius
Somsuvro Mandal has been associated with HighRadius since 2019. He began his journey as a Summer Intern, followed by a Machine Learning Internship from 2019 to 2020. During this time, he developed a new modeling method that improved forecasting accuracy for accounts with consistent cash flow. After completing his internship, he transitioned to an Associate Software Engineer -1 role from 2020 to 2021, where he consolidated heuristic forecasting methods for sparse time series data and initiated auto ML processes, significantly reducing modeling turnaround time. Currently, he holds the position of Associate Software Engineer -2, a role he has occupied since 2021.
Education and Expertise
Somsuvro Mandal earned a Bachelor of Technology (BTech) degree in Computer Science and System Engineering from KiiT University, where he studied from 2016 to 2020. His academic background has provided him with a strong foundation in software engineering principles and machine learning techniques. His expertise includes developing forecasting models, implementing regression tests, and enhancing code integrity, which are critical in the field of data science and software development.
Background
Somsuvro Mandal is based in Hyderabad, Telangana, India. He has accumulated significant experience in the software engineering domain, particularly in machine learning and data forecasting. His professional journey at HighRadius has allowed him to work on various projects that focus on improving forecasting accuracy and code quality. His background in computer science has equipped him with the skills necessary to address complex problems in software development.
Achievements
During his tenure at HighRadius, Somsuvro Mandal has made notable contributions to the company's machine learning initiatives. He developed a modeling method that improved forecasting accuracy by 5-10% for accounts with consistent cash flow. Additionally, he initiated the creation of smoke and regression tests to enhance code integrity. His work on redistributing forecasted values at day/week levels has further improved forecasting precision, showcasing his ability to implement effective solutions in data analysis.