About

I have more than 4 years of experience in Data Analysis and Science. I have solid skills and experience in data handling, ETL using SQL; building and implementing machine learning models in Python, understanding of ML algorithms and deep neural networks. I have worked in projects and experiments and developing business recommendations.

At present I am scrum master for the agile team working on experiments on convergence and efficiency of different gradient boosted trees – XGBoost, Catboost and LightGBM on varied datasets on virtual machines. I have solid knowledge of cloud technologies – Google Cloud Platform and Azure and have hands on experience in utilizing SQL and spark for ETL operations.

In my past roles I have worked with Tata Trusts in India and I bring over 3 years of experience working towards analysis of mass data quantities for the public welfare sector. Over the years I have acquired knowledge and experience to understand the complexities in gaining insights by interpreting data from multiple sources. In my career since 2014, I have held multiple positions with Tata Trusts to provide business recommendations for community support programs. I have handled identification of patterns and trends from data for the projects by building meaningful dashboards and performance reports. I used to work extensively with SQL and SAS for data manipulation. My role in Nokia Siemens was on building technical solutions for telecom sector as a part of pre-sales team.

I have great liking to documentation and creating articles on data science and modelling which have also been published in popular data science portals.