Post by Ajinkya Khalikar

A little late to announce, but i have successfully completed my internship at IIT Bombay. It was a wonderful experience or should i say a "crash course" on learning and implementing technical skills. Working there with such a brilliant minds and on the real world problem of "synthetic data generation" was really outstanding experience. What I actually worked in my internship? Well the problem statement was to create a system which will generate synthetic data for sensitive sectors like finance and medical. I worked on: 📄 A document processing pipeline for credit card statements (HDFC, SBI) and medical reports — using OCR, regex pattern matching, and PDF parsing libraries like Tabula and PDFPlumber. 🔐 Automated password detection and decryption workflows for protected documents. 🗄️ A MongoDB database architecture to store demographic patterns, transaction behaviors, and income-based spending profiles. And ultimately packaged it into a Streamlit web application. Six months taught me that research doesn't always go the way you planned and that's okay. The debugging, the dead ends, the 'why is this not working' moments? That's where the real learning happens. I'm really grateful for all the phd scholars and mtech seniors for their help and guidance throughout🙏🙏. #IITBombay #ResearchInternship #SyntheticDataGeneration #OCR #MachineLearning