Work Experience

Led ML-powered advertising solutions, increasing ad engagement, platform profitability, and merchant satisfaction. Collaborated with engineering, sales, and data science teams to optimize programmatic ad strategies and enhance predictive modeling.

AI/ML Personalization: Orchestrated the development of a Hybrid LSTM model with TensorFlow, elevating CTR by 20% and increasing user engagement across B2C campaigns.

Programmatic Advertising Platform: Championed the creation of a machine learning-powered goal-based advertising platform. Utilized TensorFlow for predictive modeling and SQL for data management, driving a 25% increase in ROAS and a 15% boost in conversion rates across 30+ global ad campaigns.

Ad Optimization: Directed big data projects with PySpark and Hadoop, enhancing ad targeting precision by 10% and cutting processing costs by 40% through the Merchant-Cube platform’s optimized data pipelines.

Predictive Bidding & Ad Performance: Engineered predictive analytics solutions using Prophet and PySpark, resulting in a 25% increase in revenue and improved ad placement efficiency.

Merchant Profitability: Forecasted merchant ad spend trends using Prophet, improving profitability by 15% through enhanced budget allocation for 10,000+ merchants globally.

Revenue and Inventory Optimization: Designed and implemented advanced inventory management strategies leveraging ML-driven insights, improving ad fill rates by 20% and increasing ad revenue by 18% across campaigns.

• Conducted Customer Cohort Analysis for different LeanData products to help identify Y-o-Y ARR growth and lifetime value of the Customers – communicated findings to the C-level executives

• Applied data modelling to all-time product usage and sales data to build a detailed buyer persona – delivered results to the customer acquisition team to have a data-oriented approach towards targeting the market segment

• Implemented numerical analysis and designed ETL flows for pulling data from visitors’ databases, using complex SQL queries, to understand behavioral patterns in customers’ purchase click, that boosted session duration by 15%

• Engineered scalable machine learning model that predicted relation between revenue-per-click and cost-per-click, across the different industries (Retail, Financial Services, Telecommunications), that increased ad-revenue by 20%

• Improved CPA (Cost Per Acquisition) for Marketing Campaigns by 30%, by tracking KPIs across the consumer business and developing strategies to optimize landing pages’ designs to maximize customer conversion rate

• Collaborated with internal stakeholders (Product Managers, Software Engineers, Customer Success) through DevOps lifecycle to help develop, deploy, and optimize system features in Media.net’s Display-to-Search (D2S) product