01
PySpark Machine Learning FastAPI Docker

Fraud Detection Pipeline & ML System

End-to-end fraud detection system processing 284,807 real credit card transactions. Built a PySpark ETL pipeline with behavioral feature engineering, trained Random Forest and XGBoost classifiers, and deployed predictions via a FastAPI REST endpoint containerized with Docker.

0.98
ROC-AUC
284K
Rows
5
Features Built
02
NLP HuggingFace FinBERT FastAPI

LLM Financial Report Analyzer

NLP pipeline that automatically summarizes earnings call transcripts and analyzes financial sentiment using open source language models. BART for abstractive summarization, FinBERT for domain-specific financial sentiment, and YAKE for keyword extraction. Correctly identified Apple as the only negative report in the test set.

94%
Confidence
5
Companies
3
NLP Models
03
Statistics Python FastAPI PostgreSQL

A/B Testing & Experimentation Pipeline

End-to-end experimentation platform simulating an e-commerce checkout button A/B test across 10,000 users over 14 days. Applied z-test for statistical significance, computed confidence intervals and lift metrics, and exposed results via a REST API with on-demand simulation capabilities.

26%
Conversion Lift
10K
Users
0.000007
P-value
04 In Development
React Native LLMs Vector Search Node.js

AI Companion Application

A full-stack mobile and web AI application built around memory, emotional awareness, and continuity — designed to feel fundamentally different from a standard chatbot. Features a semantic memory system, multi-layer emotion detection pipeline, and proactive engagement. Currently in active development.

4
Platforms
3
AI Layers
🔒
Private