Kena Shah
About Kena Shah
Kena Shah is a Data Scientist at Lancer Insurance Company, where he has worked since 2016. He specializes in creating R Shiny dashboards and developing machine learning solutions to enhance insights for underwriters.
Work at Lancer Insurance Company
Kena Shah has been employed as a Data Scientist at Lancer Insurance Company since 2016. In this role, Shah has developed R Shiny dashboards that utilize data from SQL ETL processes, external APIs, and a machine learning backend. These dashboards provide critical insights to underwriters regarding policies and customers. Shah is also engaged in a deep learning project aimed at extracting valuable information from free-form notes generated by doctors, lawyers, and underwriters during the claims management process. Additionally, Shah designed a predictive pipeline that assesses policy-wise liability and physical damage losses, which assists in determining optimal premiums for trucking policies.
Education and Expertise
Kena Shah holds a Bachelor of Engineering (B.E.) in Electronics and Communications Engineering from Gujarat Technological University, where studies were completed from 2011 to 2015. Shah furthered expertise in data analytics by studying at INSOFE from 2013 to 2014, achieving a CPEE in Big Data and Optimization. This educational background has equipped Shah with the skills necessary for advanced data analysis and machine learning applications in the insurance sector.
Previous Experience at IBM
Prior to joining Lancer Insurance Company, Kena Shah worked at IBM as a Consultant (Data Scientist) for a total of 18 months. This experience included a one-year tenure from 2014 to 2015, followed by a six-month period from 2015 to 2016. During this time, Shah contributed to various data science projects, enhancing skills in data analysis and machine learning, which are now applied in the current role at Lancer Insurance Company.
Mentorship and Leadership
Kena Shah has demonstrated leadership by mentoring three computer engineering interns in machine learning. This mentorship involved advising and supervising the development of a machine learning pipeline that achieved an 80% precision rate in predicting the occurrence of a lawsuit within the first seven days of a claim being reported. This initiative reflects Shah's commitment to fostering talent and advancing the field of data science.