PROJECT TITLE :

Sparse Coding-Inspired Optimal Trading System for HFT Industry

ABSTRACT:

The monetary trade has witnessed an exceptionally fast progress of incorporating info processing techniques in designing knowledge-primarily based automated systems for high-frequency trading (HFT). This paper proposes a sparse coding-impressed optimal trading (SCOT) system for real-time high-frequency monetary signal representation and trading. Mathematically, SCOT simultaneously learns the dictionary, sparse features, and the trading strategy in a very joint optimization, yielding optimal feature representations for the specific trading objective. The learning method is modeled as a bilevel optimization and solved by the online gradient descend methodology with quick convergence. During this dynamic context, the system is tested on the $64000 money market to trade the index futures in the Shanghai exchange center.