허정규 교수

The number of tailor-made hybrid structured products has risen more prominently to fit each investor’s preferences and requirements as they become more diversified. The structured products entail synthetic derivatives such as combinations of bonds and/or stocks conditional on how they are backed up by underlying securities, stochastic volatility, stochastic interest rates or exchanges rates. The complexity of these multi-asset structures yields lots of difficulties of pricing the products. Becau

Efficiently determining a price and optimal exercise boundary for an American option is a critical subject in the financial sector. This study introduces a novel application of long short-term memory neural networks to solve a relevant Volterra equation, enhancing the accuracy and efficiency of American option pricing. The proposed approach outperforms traditional numerical techniques, including finite difference methods, binomial trees, and Monte Carlo methods, delivering an impressive speed im

We present Pontryagin-Guided Direct Policy Optimization (PG-DPO), a framework for solving continuous-time portfolio optimization problems involving both consumption and investment decisions. Integrating Pontryagin's Maximum Principle (PMP) within a neural network pipeline, PG-DPO bypasses traditional value function approximation and directly optimizes policy parameters using adjoint processes associated with the current policy, computed via automatic differentiation. An optional alignment penalt

Under the Generalized Extreme Value (GEV) model, Markose and Alerton (2011) derived the analytic form solutions for vanilla options, and also removed the distortion of the market only with an additional parameter. In this paper, we use the technique in Rubinstein and Reiner (1991) to get the analytic form solutions for barrier options by introducing the Corrected BS (CBS) modelthe BS model close to the GEV model. By introducing CBS volatility we show that barrier option prices are continuous wit

We introduce the Pontryagin-Guided Direct Policy Optimization (PG-DPO) framework for high-dimensional continuous-time portfolio choice. Our approach combines Pontryagin's Maximum Principle (PMP) with backpropagation through time (BPTT) to directly inform neural network-based policy learning, enabling accurate recovery of both myopic and intertemporal hedging demands--an aspect often missed by existing methods. Building on this, we develop the Projected PG-DPO (P-PGDPO) variant, which achieves ne