Tomoya Suzuki

Professor of computer science at Ibaraki University, Japan

Tomoya Suzuki is a professor of computer science at Ibaraki University, Japan.
Tomoya won the John Brooks Memorial award for the best MFTA paper for 2016.
He received his B.S., M.S., and Ph.D. degrees in physics from the Tokyo University of Science in 2000, 2002, and 2005, respectively. Then, he joined Tokyo Denki University as an assistant in 2005 to teach electric circuits. From 2006 to 2009, he was a lecturer of Doshisha University, teaching computer languages and computer engineering. Since 2009, Dr. Suzuki has been an associate professor and then a professor of Ibaraki University, teaching mathematics, statistics, and computer science.
His research interest is the physics of complex systems, especially financial markets, and his research methods are time-series analysis, prediction, machine learning, and data mining with computers. In particular, his recent research involved the integration of technical analysis, physics, and computer science. Moreover, he also has a great interest in evidence-based technical analysis and has been giving seminars for Nippon Technical Analysts Association (NTAA) members on this topic.

 

 

ABSTRACT

Collective Artificial Intelligence for Mechanical Technical Analysis

Because technical analysis uses only historical price data, it has affinity with machine learning approach and is often called modern technical analysis or mechanical technical analysis. In general, machine learning method is categorized as an artificial intelligence (AI), which is really a hot topic in the world since Google’s Al (AlphaGo) beat the world Go champion. Then, it has been called FinTech to apply Al for financial business intelligence.
In his presentation, Professor Suzuki introduces some ideas to develop Al algorithms for technical analysis, such as collective intelligence and abnormally detection. The collective intelligence can enhance the predictive power by integrating many neural networks and can select the most reliable stock by following their consensus. Then, the autoencoder is a new neural network used for the deep neural network, and he applies it to the abnormally detection of noisy financial markets. To confirm the validity of these ideas, Professor Suzuki performs investment simulations and statistical significance tests with real stock price data.
Some parts of his presentation are based on his MFTA’s paper that won the John Brooks Memorial Award 2016.