• Dr. Sukrit Mittal (Senior Research Scientist, Franklin Templeton) visits us on 19/02/2025 to give the following talk.

Title: Harnessing Reinforcement Learning for Goals-based Wealth Management

Abstract: Goals-based Wealth Management (GBWM) is a financial planning framework that prioritizes achieving specific investor goals -- such as purchasing a home, funding education, or securing retirement -- rather than simply maximizing portfolio returns. Unlike traditional wealth management, which focuses on benchmarks and risk-adjusted returns, GBWM tailors investment strategies to align with an investor's unique objectives and risk preferences. A key tool for modeling the uncertain future of financial markets is Monte Carlo simulation, which evaluates thousands of possible future scenarios to estimate the probability of one achieving their financial goals. A great analogy comes from 'Doctor Strange' in 'Avengers: Infinity War', when he analyzes 14,000,605 possible futures to determine the path where the Avengers win. In finance, we do the same -- simulating countless market trajectories to assess the likelihood of success for different investment strategies. However, Monte Carlo simulations only estimate probabilities -- they don't prescribe the best actions to take.  This talk explores the transformative role of reinforcement learning in bridging that gap. We begin by introducing the fundamentals of GBWM and Monte Carlo simulations (widely used in the finance industry). We then shift focus to the power of Reinforcement Learning (RL) in optimizing the financial decision-making for complex, multi-goal financial planning scenarios. 

•  Prof. Anand Deo (Assistant Professor, Decision Sciences, IIM Bangalore) visited us on 16/02/24. Here are the details of his talk.

Title: Efficient Importance Scenario Generation for Optimization with Rare Events

Abstract:  This talk provides an overview of how one may employ importance sampling effectively as a tool for solving stochastic optimization formulations incorporating tail risk measures such as Conditional Value-at-Risk. Approximating the tail risk measure by its sample average approximation, while appealing due to its simplicity and universality in use, requires a large number of samples to be able to arrive at risk-minimizing decisions with high confidence. This is primarily due to the rarity with which the relevant tail events get observed in the samples. In simulation, Importance Sampling is among the most prominent methods for substantially reducing the sample requirement while estimating probabilities of rare events. Can importance sampling be used for optimization as well? If so, what are the ingredients required for making importance sampling an effective tool for optimization formulations involving rare events? We provide an introductory overview of the two key ingredients in this regard, namely, (i) how one may arrive at a change of measure prescription at every decision, and (ii) the prominent techniques available for integrating such a prescription within a solution paradigm for stochastic optimization formulations. The talk is based on several joint works with Karthyek Murthy.

• Prof. Shashi Jain (Associate Professor, Dept. of Management Studies, IISc) visited us on 09/02/24 !