• Led ML Ops productionalization for fraud detection models, enhancing model evaluation, tracking, and real-time deployment.

• Contributed to model development for fraud onboarding use cases—including point-of-payment, card cashing, and no-intent-to-ship fraud—covering feature engineering, model training, and real-time inference.

• Helped build transformer-encoder networks using Sequence data to identify fraud at different points of merchant journey.

• Teaching & providing industry perspective for MIT & UT Austin - Artificial Intelligence & Machine Learning courses with overall rating of 4.8/5.

• Manage a team of 4 data scientists and engineers for all data science needs for Cybersecurity, Fraud, Physical, Investigations, Supply Chain & Enterprise Resiliency.

• Setting up the Analytics Data Lake (Tools used - S3, Spark, PostGres Database, Airflow, Containers, Kubernetes) to incorporate data from multiple internal & cloud-based sources within Security Organization using APIs. Further, set up Spark Cluster environment using 60 Core, 300Gb RAM environment for processing security and email data each day.

• Classical imbalanced fraud risk scoring model refreshed hourly using PySpark for data ingestion & Tree based model building & deployment on Docker/Kubernetes. (Prec 41%, Rec 95%, $1M + saved).

• Identified characteristics of employees susceptible to phishing based on phishing simulations data (Prec 83% & Rec 89%). Logistic regression model used, and results shared on Power BI.

• Applied Anomaly Detection techniques to identify anomalous traffic using Producer Consumer Ratio, Session & Volume of traffic across network.

• Created infection risk KPI across countries and provided time to return using covid public datasets (RMSE 10 days). The model was shared across Security Executive Council and 500 companies across the globe.

• Led a team of 3 to set up an Analytical Data Lake in SQL with ETL pipelines using Python and a reporting platform on Tableau, providing a one customer centric view gathering multiple touch points data from pipeline, deal intake, engineering and factory validation, financials, supply chain and procurement.

• Built Metrics & KPI from ground up for Servers Business Unit on weekly operational performance (100+ attendees) and perform root cause analysis on the operational issues that come up each week.

• Customer market segmentation using K Prototype based on company attributes, and recency, frequency & monetary attributes, to label customers into different market segments for sales targeting.

• Estimate new & recurring revenue to meet annual plan based on metrics such as conversion, cycle time, acceptance and loss rates,

• Commodity data clustering to identify trends of most common vs least configurations using K Medoids with Jaccard similarity.

• Understand Customer Spend with Software Products at Dell based on company, and recency, frequency & monetary attributes for all customers. using methods such as KNN and Quantile Regression to predict total software revenues across different Lines of Business in Dell Software Group.

• Implemented a lead generation project to cross sell within Information Management portfolio with a Class Imbalance problem (5% of 1s) using Smote Sampling and Cost Sensitive Modeling approaches to help sales to identify better candidates for cold calling.