Alen K Johnson

Data Scientist with hands-on experience in machine learning, computer vision, OCR, LLM-based systems, and time-series forecasting. Strong in Python, SQL and end-to-end data pipelines, including data extraction, feature engineering and API-based deployment. Experienced in translating unstructured visual and textual data into scalable analytical and AI-driven solutions for real-world business use cases.

Data Scientist Intern at PropMarker Design Direct Web Solutions Ltd (2025-04 – 2025-12)

Data science internship focused on processing floorplans and building data pipelines for property analytics

• Processed 500+ floorplans using optimized OCR & OpenCV to generate structured datasets for property analytics
• Designed end-to-end Python APIs and MongoDB-based data pipelines to enable analytics-ready datasets
• Built LLM-powered RAG pipelines with vector databases to automate document analysis and data extraction

Data Science and Machine Learning Intern at GeeksForGeeks (2024-08 – 2024-12)

Data science internship focused on data quality improvement and business insights generation

• Improved dataset quality and model reliability through systematic data cleaning, preprocessing, and feature engineering
• Transformed raw metrics into business-ready insights using Power BI dashboards for KPI tracking
• Supported segmentation and prediction tasks that enhanced operational understanding and planning

Professional Certificate in Data Science and Machine Learning – GeeksForGeeks (2024-08 – 2024-12)

Bachelor of Technology in Electronics and Communication – APJ Abdul Kalam Technological University (2020 – 2024)