AI Projects

AI Project Portfolio (Key projects in past 4 years - AI + DL + GenAI)

• Bundle Recommendations Project #1 - Bundle recommendations for a specialty retailer of children’s apparel, from newborns to pre-teens (2020) Work/Impact - Transitioned from automated merchandiser-based recommendations to ML-based bundle recommendations. Achieved a 100% match with the ML approach. For a category level, we analyzed 6 months of transactions, comprising 1.5 million orders, and generated recommendations in 15 minutes. (Customer - The Children's place)

• Performance Optimization Project #2 (2021) - For a multinational mining company, optimized an existing app, more akin to a trading app, deployed between OLAP vs. OLTP. Applied a blend of DB/user and usage analysis/patterns/ML-based techniques to provide a list of recommendations to optimize. (Customer - Anglo American)

• GenAI + Vision Project #3 (2023-2024) - For a British multinational fast-moving consumer goods company, My key contribution is solution architecture based on Vision + GenAI for product detection and personalized recommendations, for its customers' products and brands. Stain Detection / Product Recommendations. (Customer - Unilever)

• Plants Classification Project #4 - Developing vision-based state-of-the-art classification models for the world's leading gardening charity. This work involved data curation, augmentation, and training, and ended as a paper :). Vision - Achieved SOTA numbers in similar projects 80% plus (Customer - RHS UK). I served as Solution Architect for developing state-of-the-art classification models for the Royal Horticultural Society in the UK, achieving over 80% accuracy in plant identification. 

• GenAI and CX improvement Project #5 - For a US-based leading specialty retailer of organizing solutions, custom spaces, and in-home services, leveraging GenAI + Vision to improve the customer journey. Pitched/deployed selected use cases. This is similar to what you see in Amazon/Swiggy GenAI Changes. (Customer - The Container Store)

• Forecasting Project #6 - Domain played a key role for me to contribute. For a leading South American beauty retailer, developing forecast models. I had a mix of responsibilities as a Solution Architect, DB, and ML Engineer. I relied mostly on SA/DB/ML. In all projects, The team was a mix of platform, MLOps, and ML engineers. Sometimes the platform is a vendor cloud or an in-prem solution. Forecast - Built ML database integrating marketing, sales, holiday, external info. Achieved 5-15% higher accuracy than client models. (Customer - Belcorp)

• GenAI for food waste reduction (2024) #7 - Hellmann’s has introduced a new AI-powered tool called "Meal Reveal" to combat the issue of food waste. Using Google Cloud's advanced AI technologies, Meal Reveal scans the contents of a fridge to suggest recipes, thereby reducing household food waste and promoting sustainability. How have we solved ? - Vision LLMs, Text Models, Guardrails, Proprietary Algorithms. My role = Solution Architect partnering Google + Unilever. (Customer - Unilever). I collaborated with Google and Unilever to architect a Vision AI and Generative AI solution for Unilever, enhancing product detection and personalized recommendations in the fast-moving consumer goods sector. His work on "Meal Reveal," an AI-powered tool for Hellmann’s, demonstrated his ability to reduce food waste by suggesting recipes based on fridge contents

• Smartplaner (2021) – Retail Planogram layout and optimization tool, Route optimization, Linear programming-based optimization both solutions hosted in Bodhi Accelerator

Earlier Key Projects

• Retail store traffic forecasting solution (2013) feature implementation in Sensormatic solutions offerings. Sensormatic has solutions deployed at more than 80 percent of the world’s top 200 retailers in 70+ countries

• Microsoft XBOX Supply chain platform (2008) – One of two key architects to build Data-Driven Warranty Engine with complete traceability over refurbishment, fulfillment, repairs. Migrating from console to customer level as well as migrating the existing dataset of 220M consoles

Retail and Supply Chain Focused Key Projects across multiple companies

• Developed and implemented computer vision and GenAI solutions for smart retail and CX improvement – The Container Store (2023)

• Bundle recommendation – Production implementation for US Children’s clothes retailer (Deep learning image based with Sales data and recommending potential bundles) (2021)

• Retail Forecasting: Achieved 5-15% higher accuracy than client models by integrating marketing, sales, and external data, Clients – Belcorp, Tesco (2022 / 2023)

• Smartplaner – Retail Planogram layout and optimization tool, Route optimization, Linear programming-based optimization both solutions hosted in Bodhi Accelerator (2022)

• Retail store traffic forecasting solution feature implementation in Sensormatic solutions offerings. Sensormatic has solutions deployed at more than 80 percent of the world’s top 200 retailers in 70+ countries  (2013)

• Microsoft XBOX Supply chain platform – One of two key architects to build Data-Driven Warranty Engine with complete traceability over refurbishment, fulfillment, repairs. Migrating from console to customer level as well as migrating the existing dataset of 220M consoles (2008)

• Smart Exit Implementation: Reduced merchandise theft by bridging offline and online touchpoints for a major US retailer (2018)

SaaS-based models - Experiments

• GCP, Azure, AWS leverage leverage existing high performance DB's Redshift, Big Query, Azure Data Lake

• Deploy Custom stack API based solutions

• No code / Lowcode / Reduce your time for Insights / Actionable Decisions