I am an AI/ML specialist with a Masters degree in Analytics. My main focus is on applying Statistical Modelling and Machine Learning solutions in Big Data scenarios using PySpark. I have worked on projects that span the entire spectrum of data analytics. This includes statistical modelling like Markov chain modelling, mainstream supervised learning techniques like Generalized Linear Models, Tree ensemble models like Random Forest, GBT, XGBoost, unsupervised learning techniques like Conjoint Analysis, PCA & Clustering, Simulation techniques like Monte Carlo and Time Series modelling. I have also worked on Deep Learning architectures like 1-D CNN & UNet for NLP and Computer Vision solutions. Please find here a glimpse of the work I have done in the recent pastAll the mentioned Machine Learning applications are designed & developed at scale using Apache Spark:- Product Recommendation: Built an engine using Matrix factorization algorithm leveraging Alternating Least Squares to provide real time product recommendations to B2B clients- CLTV: Developed discounted cash flow models to compute Lifetime Value and expected lifetime of customers- Churn Modelling: Developed Gradient Boosted Tree models to predict the propensity of churn for each customer in the immediate future- Product Bundling: Analyzed sales orders and performed Market Basket Analysis using FPGrowth algorithm to bundle products together and to generate association rules- Segmentation: Implemented unsupervised ML techniques like PCA and K-Means to segment customers based on their purchase behavior - Marketing ROI: Developed Markov chain modelling for revenue attribution and ROI estimation across marketing activity and channels