MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202631018220 A) filed by National Institute Of Technology, Rourkela, Orissa, on Feb. 18, for 'integrated physics informed regularization in least square support vector machine for option pricing.'
Inventor(s) include Mishra, Ms. Bhubaneswari; and Chakraverty, Dr. Snehashish.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a computer-implemented system (900) and method (100) for pricing financial options. The system (900) comprises a processing module (902), a memory storage module (904), an input module (906) configured to receive market data. The processing module (902) is configured to construct a least squares support vector machine (LS-SVM) model which is based on an option-pricing function by using a kernel representation, wherein the kernel representation is generated from a plurality of collocation points, evaluate a residual of a Black-Scholes equation corresponding to the option-pricing function, incorporate the evaluated residuals and a terminal payoff condition as regularization constraints within an LS-SVM optimization process, and optimize the pricing function such that the pricing function simultaneously fits in the received market data and satisfies the Black-Scholes equation, thereby generating a physics-informed option price estimate."
Disclaimer: Curated by HT Syndication.
