Siranush Khrimian

Applied advanced statistical modeling and Python-based data processing to identify patterns and anomalies in large datasets - Developed complex data pipelines and optimized neural networks for autonomous driving, demonstrating an ability to audit and validate AI/ML algorithms - Managed data integrity and quality control processes for autonomous driving systems, ensuring compliance with strict technical specifications

- Internal Controls: Evaluated and tested internal control systems for clients in Oil & Gas and Metals sectors to ensure CEAVOP - Risk Assessment: Participated in risk-based audit planning, identifying key financial and operational risks across business processes - Reporting: Drafted audit findings and recommendations, focusing on process improvements and compliance with IFRS - Substantive Testing: Performed detailed analytical procedures and verification of financial statements

- Successful organizational work in preparing a number of conferences organized by the Media Group "Expert Ural" and the Ural Federal University; - Analysis of large massives of empirical data (micro- and macro-levels).

Master Thesis "Conventional and Machine Learning Techniques for Modeling of Extreme Events in Market Dynamics", (grade "excellent"). Developed predictive models for risk management, highly applicable to organizational risk forecasting. Successfully substituted a rigorous, but computationally expensive LPPLS model for market’s bubble detection with a NN based “surrogate” model, which was orders of magnitude faster than the original model, while still demonstrating significant predictive power.

Bachelor Thesis "Factors of demand for conspicuous consumption on the part of Russian households", grade "very good" (1.0). Specialised subjects: Econometrics, Statistics, Mathematical Analysis.