Automated Social Media Monitoring with AI-Powered Image Recognition
Built a neural network–based system to detect product placement across social media in real time. The solution identifies brands, objects, and context, enabling automated marketing reports, influencer tracking, and competitor analysis for global marketing teams.
Automated Invoice Processing Cuts Manual Work, Speeds Up Payments
Nestlé moved to automated invoice processing, enabling 100+ users across Finance, Accounting, and Sales to improve compliance, eliminate manual entry, streamline invoice approvals, budgeting, and mass payouts.
Time-to-Insight Reduced from 1 Week to Under 1 Day for 100+ Users
Built a scalable Azure-based BI solution for Hochland, replacing Excel with Power BI and Azure Analysis Services. By integrating 26 data sources into a unified model, we reduced time-to-insight from 1 week to hours, advancing decision-making across sales, planning, and operations.
Unified BI Platform Across 11 Countries Powers Sales & Financial Insights
Modernized Danone's analytics, consolidating data from SAP, Navision, and external sources into an Azure-based BI platform. Spanning four product lines and 11 countries, the solution improved sales planning, inventory, and margin analysis, supporting short and long-term decisions.
Achieved 85%+ Forecast Accuracy with AI-Powered Sales Predictions
Built a regression-based forecasting model using Gradient Boosting and time-series analysis to predict hourly sales, returns, and restocking efficiency. The solution improved inventory planning and operational effectiveness across stores using Python, R, and SQL-based analytics.
Automated Market Data Integration Saves Days of Manual Work Monthly
Built a centralized BI platform, consolidating Nielsen data and internal Sell-In data into a unified reporting layer. The solution eliminated manual file consolidation - enabling faster insights, improved marketing responsiveness, and self-service reporting across markets.
Scalable RFID Data Lake Processes 3M+ Events Daily For Stores & Warehouses
Developed a real-time RFID data integration platform for LPP, capturing over 3 million daily events across warehouses, showrooms, and stores. Built on Azure Data Lake and Power BI, it delivers live alerts on product exposure and enables granular movement tracking, supporting loss prevention & inventory optimization.
Global Sales & Merchandising Platform for 3,000+ Users Across 50+ Markets
Delivered a scalable, automated analytics solution for a global FMCG company, integrating sales & merchandising data across global teams. With Power BI dashboards and predictive data quality tools, the solution empowers 3,000+ users with informed decisions in 50+ markets.
Modern Azure-Based BI Platform Serving 200+ Sales, eCommerce & Logistics Users
Built a scalable, centralized data & BI platform on Azure, covering eCommerce, logistics, and sales. With Azure-hosted SQL, Power BI, and Analysis Services, it enables self-service dashboards, master data unification, and real-time access to business-critical insights for 200+ users.
Logo Recognition Model Achieves 90%+ Accuracy in Global Field Use
Developed a deep learning-based image recognition model for Cheil to validate Samsung's logo consistency across global retail locations. Achieved over 90% balanced accuracy; even in poor lighting or angles, and integrated the model into a mobile tool used by sales teams worldwide with <3s response time.
LPP Uses Computer Vision to Analyze In-Store Traffic and Product Exposure
Delivered a machine learning solution that processes CCTV footage in milliseconds to detect queues, count customers, and analyze shelf space in retail stores. The system helps LPP validate in-store behavior patterns and boosts demand forecasting with ground truth data.
.svg){kind=small}
.svg){kind=small}
_Fidelity_National_Information_Services_Inc._Corporate_Logo.avif){kind=logo}
