首页|Researchers from Hang Seng University of Hong Kong Publish Findings in Machine L earning (Deterministic modelling of implied volatility in cryptocurrency options with underlying multiple resolution momentum indicator and non-linear machine . ..)
Researchers from Hang Seng University of Hong Kong Publish Findings in Machine L earning (Deterministic modelling of implied volatility in cryptocurrency options with underlying multiple resolution momentum indicator and non-linear machine . ..)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Investigators publish new report on artificial in telligence. According to news reporting from Hang Seng University of Hong Kong b y NewsRx journalists, research stated, “Modeling implied volatility (IV) is impo rtant for option pricing, hedging, and risk management. Previous studies of dete rministic implied volatility functions (DIVFs) propose two parameters, moneyness and time to maturity, to estimate implied volatility.” Our news reporters obtained a quote from the research from Hang Seng University of Hong Kong: “Recent DIVF models have included factors such as a moving average ratio and relative bid-ask spread but fail to enhance modeling accuracy. The cu rrent study offers a generalized DIVF model by including a momentum indicator fo r the underlying asset using a relative strength index (RSI) covering multiple t ime resolutions as a factor, as momentum is often used by investors and speculat ors in their trading decisions, and in contrast to volatility, RSI can distingui sh between bull and bear markets. To the best of our knowledge, prior studies ha ve not included RSI as a predictive factor in modeling IV. Instead of using a si mple linear regression as in previous studies, we use a machine learning regress ion algorithm, namely random forest, to model a nonlinear IV. Previous studies a pply DVIF modeling to options on traditional financial assets, such as stock and foreign exchange markets. Here, we study options on the largest cryptocurrency, Bitcoin, which poses greater modeling challenges due to its extreme volatility and the fact that it is not as well studied as traditional financial assets. Rec ent Bitcoin option chain data were collected from a leading cryptocurrency optio n exchange over a four-month period for model development and validation. Our da taset includes short-maturity options with expiry in less than six days, as well as a full range of moneyness, both of which are often excluded in existing stud ies as prices for options with these characteristics are often highly volatile a nd pose challenges to model building. Our in-sample and out-sample results indic ate that including our proposed momentum indicator significantly enhances the mo del’s accuracy in pricing options. The nonlinear machine learning random forest algorithm also performed better than a simple linear regression. Compared to pre vailing option pricing models that employ stochastic variables, our DIVF model d oes not include stochastic factors but exhibits reasonably good performance.”
Hang Seng University of Hong KongAlgor ithmsCyborgsEmerging TechnologiesInvestment and FinanceMachine Learning
NETL
NSTL
