Actuarial Analyst specializing in financial risk management, valuations, and scenario-based testing within the insurance and financial sectors. With a demonstrated history of optimizing financial models and implementing regulatory frameworks like IFRS17, my approach combines technical expertise with a commitment to strategic solutions.

Currently a graduate student of Actuarial Science at Simon Fraser University working on Collective Defined Contribution Pension Plans and benefit smoothing mechanisms.

• Updated VTPs (Valuation Technique Principles) with worked examples of LC (Loss Component) amortization.
• Redesigned IFRS17 Financial Disclosure Notes clarifying accountability between Finance and Actuarial teams.
• Revised the IFRS17 transition issue logs for Q1 2023 highlighting high risk items to be reported to senior management.
• Calculated Risk Adjustment (RA) release amounts by Insurance type and Measurement model for Q2 2023 leveraging IFRS17 KDAs (Key Disclosure Analysis) and SAP AfO (Analysis for Office).
• Reviewed OSFI SegFunds LICAT submissions template for US, Canada, and Bermuda for Q1 and Q2 2023.

• Optimized a predictive modelling tool using R to predict AOCI for upcoming 3 months by assessing the impact on FM - AFS (Fixed Maturity - Available for Sale) assets based on their credit spreads according to FAS157.
• Discovered issues in datasets and improved model efficiency by 40%, resulting in positive movement of over $119M towards actual value.
• Projected asset cashflows under various stochastic economic scenarios for complex derivatives & synthetic securities on a portfolio of $230B using Prophet.
• Decreased pre and post processing time by 20% and 80% respectively, for Prophet seriatim level output data by writing and updating automation scripts in Python and DCS.
• Lead the testing of the new ALS Library-based asset projection Prophet model.
• Oversaw Azure Synapse-based SQL database for data ingestion/upload errors while working as a liaison between actuarial and IT teams

• Built a mixed machine learning model using Numerical and Textual analysis to predict stock prices
• Analysed historical stock price data and news headlines and ran time series analysis, sentiment analysis and random forest regression algorithms
• Achieved almost perfect fit on model which was able to explain 99.94% of variability present in data
• Forecasted the selected stock price with less than 1.2% error

• Designed a stochastic economic scenario generator, with an intuitive cascade structure encompassing short-term interest rate, long-term interest rate, inflation, equity yields, and equity dividend yields over a 90-year horizon.
• Economic Scenario Generator - Github

• Implemented an Unscented Kalman Filter (UFK) and smoother (UKS) to Heston stochastic volatility model as a 6x faster alternative to Particle Filter/Smoothers with only about 4-8% loss in accuracy and 1% loss in persistence.
• UKF - Github

• Developed and deployed a live web app that takes an image of a bird and returns its species (or genus), along with the top 5 probable options and their probability at an R-squared value of 92.76% on the kaggle.com bird species dataset.
• Live Demo: Bird Identifier App

• Exam FM, Society of Actuaries, USA, Jun 2023
• Exam P, Society of Actuaries, USA, Mar 2022
• CS1 (Exam p + VEE MS), Institute and Faculty of Actuaries, UK (IFoA), Sep 2020
• CB3 (Part of FAP modules), Institute of Actuaries of Actuaries, India (IAI), Aug 2018
• ACET (Membership Exam), Institute of Actuaries of Actuaries, India (IAI), Jan 2018

• MSc - Actuarial Science, Simon Fraser University, Sep 2024, GPA - 3.67
• BSc - Statistics, St. Xavier's College, Jun 2021, GPA - 3.36
• Class 12th, Gujarat Board, G K Dholakiya High School, Mar 2014 - Percentage 81.00/100.00
• Class 10th, Gujarat Board, Divine High School, Mar 2012 - Percentage 92.60/100.00