About Me
Data Scientist and Analytics Engineer with a passion for uncovering insights in complex datasets
I'm a passionate Data Scientist and Analytics Engineer with a deep curiosity for uncovering patterns and insights hidden within complex datasets. My background in physics has shaped a rigorous analytical mindset and a strong foundation in quantitative modelling, enabling me to approach problems from first principles and to understand systems at both theoretical and empirical levels.
I specialise in building data-driven applications and analytical tools that solve complex problems. My work combines technical expertise with curiosity and creative problem-solving to deliver meaningful solutions in data science and analytics.
Data Science & AI
Expert in Machine Learning, Deep Learning, and Agentic AI. Proficient with Python, PyCharm, Cursor, PySpark, SKLearn, and cutting-edge AI frameworks including OpenAI, LangGraph, and multiple LLM platforms.
Data Engineering
Extensive experience building ETL pipelines, working with SQL, PostgreSQL, MongoDB, GraphDB, and Neo4j. Skilled in cloud computing with AWS and data visualization using Tableau and Plotly.
Analytics & Research
Strong foundation in statistical analysis, quantitative modeling, and research. Ph.D. in Physics with extensive experience in particle physics research at CERN, Fermilab, and leading international collaborations.
Recent Successes
Trader Contextual Surveillance
At Credit Suisse, contributed to the design and implementation of the Trader Contextual Surveillance (TCS) process — a Foundry- and PySpark-based data analytics solution developed to monitor trading activities across the firm's global trading platforms. The system was designed to detect patterns of potential insider dealing and market manipulation by generating alerts for trades requiring further scrutiny. Over thirty distinct surveillance scenarios were implemented, covering a wide range of behaviors and market conditions. The project not only strengthened compliance and risk management capabilities but also identified potential regulatory loopholes that had not yet been formally recognized by market authorities.
Predictive Time Series Analytics
Developed a machine learning–based trading application designed to scan a broad universe of approximately 800 publicly listed companies to identify favorable trade entry conditions. The system integrates a suite of advanced algorithms trained to detect local highs and lows within stock time series data and to estimate the probability of sustained trend reversals. Its predictive engine calculates the likelihood of a 10% price movement within a ten-day horizon, enabling a systematic and data-driven approach to short-term trading opportunities.
Holistic Risk Management
At Credit Suisse, contributed to the design and implementation of the Holistic Risk Management Framework (HRMF)— a Foundry- and PySpark-based data analytics solution developed to identify, quantify, and highlight actionable risk across the organization. The framework integrated diverse datasets from multiple business and security domains to provide a comprehensive, data-driven view of the bank's risk landscape. It implemented key metrics to evaluate the effectiveness of the bank's cybersecurity programs and enabled proactive monitoring of emerging vulnerabilities and operational risks.
