Dinank Chitkara

• Authored quantitative research across equities, futures, and options, providing actionable insights to support informed decision-making for institutional investors.
• Developed a framework to incorporate derivatives into ESG and climate reporting, improving transparency and understanding of climate-related risks and exposures
• Conducted training sessions on index derivatives for coverage and sales, showcasing use cases for index futures and options, and engaging with clients regarding their potential use cases in their portfolios
• Supported clients in integrating MSCI analytics tools like Barra Portfolio Manager and leveraging ESG, Climate, Factor, and Thematic datasets to enhance portfolio construction, risk management, and active management strategies
• Spearheaded AI-driven initiatives to enhance research efficiency, automating workflows and boosting productivity across MSCI research teams

• Developed quantitative models using regression analysis and time series techniques to calibrate macroeconomic factors for stress-testing scenarios.
• Automated workflows with Python, streamlining processes and delivering user-friendly templates and dynamic presentation tools resulting in a monthly saving of 15+ man-hours and significantly enhancing operational efficiency.
• Built interactive RShiny dashboards to enable real-time macroeconomic scenario analysis, improving accuracy and efficiency of stress-testing frameworks.

• Designed a portfolio optimization algorithm, leveraging advanced techniques such as genetic algorithms and moving block bootstrapping to generate tailored, risk-adjusted investment portfolios for high-net-worth and retail clients.
• Researched and analyzed diverse financial instruments, including single-stock equities and ETFs across various asset classes and geographies, managing a total AUM exceeding $200 million. Delivered data-driven insights to support portfolio management decisions, risk assessments, rebalancing strategies, and performance evaluations, ensuring alignment with client objectives and risk tolerance.

• Deployed ensemble techniques (regression, machine learning, time series techniques) using R and Python to forecast Walmart and Sam's Club distribution center cases and trailers improving forecast accuracy by 80 basis points.
• Built a Tableau dashboard to categorize forecast exceptions by error drivers, providing stakeholders with actionable insights to improve forecasting accuracy by 108 basis points, optimize inventory levels, and contributing to $40M in annual savings.

Supported the Life Actuarial Team in valuing US insurance policies by developing a STAT reserve calculation model for accurate reserve estimations.

Conducted research on challenges in India's agricultural marketing system, analyzing government initiatives and proposing areas for improvement.