Multi-Task Learning For Option Pricing

نویسندگان

  • Joumana Ghosn
  • Yoshua Bengio
چکیده

Reproduction partielle permise avec citation du document source, incluant la notice ©. Short sections may be quoted without explicit permission, if full credit, including © notice, is given to the source. Les cahiers de la série scientifique (CS) visent à rendre accessibles des résultats de recherche effectuée au CIRANO afin de susciter échanges et commentaires. Ces cahiers sont écrits dans le style des publications scientifiques. Les idées et les opinions émises sont sous l'unique responsabilité des auteurs et ne représentent pas nécessairement les positions du CIRANO ou de ses partenaires. This paper presents research carried out at CIRANO and aims at encouraging discussion and comment. The observations and viewpoints expressed are the sole responsibility of the authors. They do not necessarily represent positions of CIRANO or its partners. Résumé / Abstract L'apprentissage multi-tâches est une manière d'apprendre des particularités d'un domaine (le biais) qui comprend plusieurs tâches possibles. On entraîne simultanément plusieurs modèles, un par tâche, en imposant des contraintes sur les paramètres de manière à capturer ce qui est en commun entre les tâches, afin d'obtenir une meilleure généralisation sur chaque tâche, et pour pouvoir rapidement généraliser (avec peu d'exemples) sur une nouvelle tâche provenant du même domaine. Ici cette commonalité est définie par une variété affine dans l'espace des paramètres. Dans cet article, nous appliquons ces méthodes à la prédiction du prix d'options d'achat de l'indice S&P 500 entre 1987 et 1993. Une analyse de la variance des résultats est présentée, démontrant des améliorations significatives de la prédiction hors-échantillon. Multi-task learning is a process used to learn domain-specific bias. It consists in simultaneously training models on different tasks derived from the same domain and forcing them to exchange domain information. This transfer of knowledge is performed by imposing constraints on the parameters defining the models and can lead to improved generalization performance. In this paper, we explore a particular multi-task learning method that forces the parameters of the models to lie on an affine manifold defined in parameter space and embedding domain information. We apply this method to the prediction of the prices of call options on the S&P index for a period of time ranging from 1987 to 1993. An analysis of variance of the results is presented that shows significant improvements of the generalization performance.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Numerical Solutions for Fractional Black-Scholes Option Pricing Equation

In this article we have applied a numerical finite difference method to solve the Black-Scholes European and American option pricing both presented by fractional differential equations in time and asset.

متن کامل

Option Pricing on Commodity Prices Using Jump Diffusion Models

In this paper, we aim at developing a model for option pricing to reduce the risks associated with Ethiopian commodity prices fluctuations. We used the daily closed Unwashed Lekempti grade 5 (ULK5) coffee and Whitish Wollega Sesame Seed Grade3 (WWSS3) prices obtained from Ethiopia commodity exchange (ECX) market to analyse the prices fluctuations.The natures of log-returns of the prices exhibit a...

متن کامل

How Does Pricing of Day-ahead Electricity Market Affect Put Option Pricing?

In this paper, impacts of day-ahead market pricing on behavior of producers and consumers in option and day-ahead markets and on option pricing are studied. To this end, two comprehensive equilibrium models for joint put option and day-ahead markets under pay-as-bid and uniform pricing in day-ahead market are presented, respectively. Interaction between put option and day-ahead markets, uncerta...

متن کامل

A New Stock Model for Option Pricing in Uncertain Environment

The option-pricing problem is always an important part in modern finance. Assuming that the stock diffusion is a constant, some literature has introduced many stock models and given corresponding option pricing formulas within the framework of the uncertainty theory. In this paper, we propose a new stock model with uncertain stock diffusion for uncertain markets. Some option pricing formulas on...

متن کامل

Numerical algorithm for discrete barrier option pricing in a Black-Scholes model with stationary process

In this article, we propose a numerical algorithm for computing price of discrete single and double barrier option under the emph{Black-Scholes} model. In virtue of some general transformations, the partial differential equations of option pricing in different monitoring dates are converted into simple diffusion equations. The present method is fast compared to alterna...

متن کامل

European option pricing of fractional Black-Scholes model with new Lagrange multipliers

In this paper, a new identification of the Lagrange multipliers by means of the Sumudu transform, is employed to  btain a quick and accurate solution to the fractional Black-Scholes equation with the initial condition for a European option pricing problem. Undoubtedly this model is the most well known model for pricing financial derivatives. The fractional derivatives is described in Caputo sen...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2002