Projection-free Online Empirical Risk Minimization with Privacy-preserving and Privacy Expiration

Jian Lou, Yiu-ming Cheung

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Data analytic helps investors to make prediction of the financial market. Financial news or other related information is an invaluable asset for investors' accurate prediction and efficient decision. Most researchers focus on stock price prediction. Commodity market, and especially Spot Gold, has not been investigated deeply in literature. Spot Gold price prediction is proved to be an intractable task due to the complexity of market information and a huge amount of capital pool. This paper using financial sentiment analysis to transform text data into numerical data and using MLP model to predict Spot Gold price. The results show that using news and history price to predict Spot Gold prices is feasible and trustable.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2020
EditorsJing He, Hemant Purohit, Guangyan Huang, Xiaoying Gao, Ke Deng
PublisherIEEE
Pages758-763
Number of pages6
ISBN (Electronic)9781665419246
ISBN (Print)9781665430173
DOIs
Publication statusPublished - 14 Dec 2020
Event2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2020 (Virtual Conference) - Virtual, Online, Melbourne, Australia
Duration: 14 Dec 202017 Dec 2020

Publication series

NameProceedings - IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT

Conference

Conference2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2020 (Virtual Conference)
Country/TerritoryAustralia
CityMelbourne
Period14/12/2017/12/20

User-Defined Keywords

  • Online Convex optimization
  • Differential Privacy
  • Proximal Online Gradient Descent
  • Projection-free Online Gradient Descent

Fingerprint

Dive into the research topics of 'Projection-free Online Empirical Risk Minimization with Privacy-preserving and Privacy Expiration'. Together they form a unique fingerprint.

Cite this