I love turning complex challenges into smart, working AI systems.
My background is rooted in FinTech and Gaming Technology, where I’ve developed AI solutions for anomaly detection, fraud prevention, and Anti-Money Laundering (AML).
I focus on data models that not only predict—but protect.
What I Do
Build end-to-end ML pipelines emphasizing Anomaly Detection, Fraud Detection, and AML.
Develop agentic architectures using LangChain, LangGraph, and LLM orchestration.
Experiment with Generative AI for real-time analytics, monitoring, and automation.
Contribute to open-source AI and FinTech projects; active on Kaggle and Zindi solving real-world data challenges.
Active on HuggingFace — exploring model-sharing and community-driven innovation.
“I believe in AI that works with people, not against them — technology that serves fairness, transparency, and purpose.”
Current Focus:
Developing an Anti-Money Laundering (AML) pipeline that detects suspicious transaction patterns using feature engineering, anomaly detection, and hybrid ML–LLM methods.
The system is built with MLflow and DVC and follows MLOps principles for continuous improvement and scalability.
Dynamic Pricing for ATM Transactions
Designed a system using customer segmentation (KMeans) and demand modeling (XGBoost) to optimize transaction fees, increasing revenue by 10–12% while maintaining transaction volume.
ATM Cash Demand Forecasting
Built an XGBoost forecasting model predicting daily demand per ATM cassette ($1, $5, $20, $100), reducing cash-out incidents by 15% and improving uptime.
Defect Detection from ATM Telemetry Logs
Created a BERT-based anomaly detection model identifying software/hardware defects early. Integrated with LangGraph orchestration for LLM-based root-cause analysis, increasing detection from 30% to 80%.
Consulting & Applied AI Projects
Speech Analytics for Compliance Monitoring in Call Center
Designed an AI-driven speech analytics system using an orchestrator–worker pattern built on LangGraph to analyze interactions between human agents and customers.
The agent evaluates compliance adherence, sentiment neutrality, and conversational quality, generating real-time recommendations for call improvement.
Integrated with MLflow for full observability and prompt tracking, enabling model auditability and continuous optimization.
Financial Coaching through Document Intelligence
Developed a financial coaching system that classifies expenses from invoices using Docling for document parsing and LangChain for intelligent categorization.
Each invoice is processed to extract item-level data and automatically assign spending categories, helping users track and understand their financial habits.
The solution connects to an AWS S3 bucket for document storage, exposes microservices through AWS ECR, and uses MongoDB Atlas as the central repository for semi-structured financial data.
