Currently leading 10+ ML/productized projects supporting Finance, Real Estate, Macrospace, and Assortment partners at Whole Foods market. Experience includes applications of predictive modeling, deep learning forecasting techniques, bayesian estimation, XAI and unsupervised methods as per different business needs.

Consulting on problems of sustainability, social and environmental innovation in a non-profit setting as part of Longhorn Impact Fellowship at Texas (LIFT)

As an Associate Consultant in ZS' Advanced Data Science team, I started Leading the experiment design in Algorithm-as-a-service and productized ML-driven projects. Additionally, I was also responsible for communicating directly with senior internal and client stakeholders to keep them informed about project milestones. I also started mentoring junior associates during the early stages of their careers. From a technical perspective, my client projects involved salesforce targeting and optimization problems, lookalike predictions, sequence analytics, market segmentation, survival analytics, etc. I also worked on multiple projects regarding Covid-19 related market changes such as cases vs sales forecasts, US states re-opening projections, hospital resource overuse, etc. Other responsibilities included :- Collaborating with multiple teams like database management, app development, and marketing experts while leading the Algorithm Development aspect in a product setting project- Mentoring junior associates in both technical and soft skills- Hiring entry-level associates in Advanced Data Science team

I joined ZS' data science team in its nascent stage and became a part of the teams' start-up within a company culture. My responsibilities were to learn, design, and code machine learning and deep learning models, often productized to solve contemporary business problems such as marketing mix, personalizing marketing, etc. for Fortune 500 companies, primarily in the US Pharma and Healthcare market. I worked primarily on predictive models to inform clients' sales and marketing vertical and coded recommender engines, bagging-boosting based models, visualization and insights automation Rshiny app, etc. for the sameOther key involvements include :- Learning and Development seminars for colleagues on R visualization and ML concepts - Building client relationships with weekly communication on project updates and insights

Increased variety of recommendations by 47% for the recommender engine of American luxury-based e-commerce client using non-negative matrix factorization, collaborative filtering, etc.