Himanshu Ravishankar

Currently pursuing a Master’s in Data Analytics at Queensland University of Technology, complemented by a Postgraduate Diploma in Data Science and Engineering from the Great Lakes Institute of Management. Brings foundational IT sector experience along with strong analytical training and project involvement. Proficient in utilizing modern data analysis tools and techniques to interpret and manage data. Eager to leverage academic insights in a practical setting to drive business decision-making and enhance organizational outcomes.

• Google Data Analytics Professional
• Python Programming
• Automation Anywhere Certified Advanced RPA Professional

• Spearheaded the development and testing of the CITIKYC project, aiming to standardize the KYC process across various CITICORP sectors.
• Played a key role in the design, implementation, and validation phases, ensuring the application's functionality met diverse client needs.
• Conducted comprehensive testing of both the application and the associated websites, identifying and resolving issues to enhance user experience and system reliability.
• Collaborated with cross-functional teams to integrate feedback and refine testing strategies, contributing to the project's success by ensuring high-quality deliverables.
• Utilized a range of testing tools and methodologies to ensure rigorous quality checks and compliance with CITICORP’s operational standards.

• Developed and implemented a sophisticated machine learning-based fraud detection system to analyze historical credit card transactions and predict fraudulent activities.
• Engineered robust predictive models using advanced algorithms such as Random Forests and Gradient Boosting to accurately identify potential fraud with high precision and recall.
• Integrated a blend of expert-driven rules and machine learning insights to automate transaction blocks and trigger alerts for suspicious activities, enhancing real-time response capabilities.
• Employed statistical techniques and anomaly detection methods to adapt to evolving fraudulent tactics, ensuring the system remains effective against new and emerging fraud strategies.
• Designed a scalable solution that supports dynamic updating of detection models, facilitating continuous learning and improvement from new transaction data, thus bolstering defense mechanisms against fraud in banking systems.
• Contributed to a significant reduction in financial losses for banks and financial institutions by proactively identifying and preventing fraudulent transactions.