Applications of Machine Learning and Quantitative Research in Finance and Corporate Banking

jatindeep singh

Abstract:

This work summarizes professional and research contributions at the intersection of quantitative research, machine learning, and financial applications. Areas of expertise include Natural Language Processing for financial documents (e.g., transaction search using FinBERT), deep reinforcement learning for trading and portfolio optimization, ensemble learning for cash flow forecasting, and credit risk modeling using XGBoost and recurrent neural networks. Experience spans both corporate investment banking and consumer credit, with demonstrated ability to design, deploy, and scale AI/ML models in production environments. Research and applications emphasize quantitative rigor, risk modeling, and algorithmic decision-making, aiming to advance the integration of artificial intelligence within financial systems.

Key areas of interest: Quantitative Research, Machine Learning in Finance, Financial Engineering, Deep Reinforcement Learning, Natural Language Processing for Finance, Risk Modeling, Time Series Forecasting, Portfolio Optimization.