Srivathsan K

- Work at the intersection of academic research and applied quantitative trading - Read and interpret cutting-edge financial research papers - Transform research insights into actionable high- and mid-frequency trading strategies - Convert academic models into real-world trading logic - Build and backtest predictive models using market microstructure data (OHLCV, options, order book) - Preprocess data: clean, align, and engineer features across diverse datasets - Apply dimensionality reduction techniques like PCA and UMAP for signal extraction - Use clustering methods to identify tradable market regimes - Develop and test statistical and machine learning models (e.g., tree-based, regression, regime-switching) - Perform iterative experimentation and model refinement - Evaluate performance using walk-forward testing, validation metrics, and risk-adjusted returns - Combine deep technical modeling with the rapid feedback loops of live trading

– Collaborated with cross-functional teams in risk, trading, and data to automate curve validation, pricing workflows, and exposure accuracy. – Comment Classifier: NLP tool grouped unstructured trader comments, improved data tagging efficiency by 30%. – Settlement Query Engine: Built tool to extract settlement timings and anomalies, enhanced analyst productivity by 5%. – Discrepancy Checker: Identified mismatches in CFD, DLF, MTM (Mark-to-Market) vs. aggregator values, boosted reconciliation efficiency by 20%. – Argus Scraper: Built correction validator pipeline (CODE ID, timestamps) for dynamic curve updating , used in business critical workflows.

– Participated in daily 3-hour strategy sessions to discuss, validate, and refine trading ideas. – Explained complex trading concepts and provided real-time consulting on strategy development. – Developed custom scripts in Python and Pine Script to calculate position sizes based on dynamic risk management rules. – Advised on capital allocation, risk control, and position sizing techniques. – Consulted on the design and potential implementation of neural networks for predictive trading, covering data preparation and model structure.

- Focused on practical applications of AI/ML for business analysis and automation. - Strengthened foundations in linear algebra, probability,Calculus and TensorFlow through real-world project exposure. - Understanding of Business analytics.