SIG-FIN-012-05

第12回研究会

Optimized Stock Factors Prediction Model Based on LSA and Multiple SVM Models†

著者†

Wang Peng, Kiyoshi Izumi(Department of Systems Innovations, School of Engineering, the Univ. of Tokyo)

概要†

We put forward an optimized method of stock factors prediction model which can be easily extended to realtime prediction system., based on the new version of Yahoo Financial text board of 2012.11~2013.6 with about 4000 companies. Preceding studies have verified that BBS text can be used to forecast trade volume and return. On this basis, LSA (Latent Semantic Analysis) and multi-SVM model are put forward in our framework to improve the accuracy of natural language processing and the prediction.

論文†

SIG-FIN-012-05.pdf