Title :
Law discovery from financial data using neural networks
Author :
Saito, Kazumi ; Ueda, Naonori ; Katagiri, Shigeru ; Fukai, Yutaka ; Fujimaru, Hiroshi ; Fujinawa, Masayuki
Author_Institution :
NTT Commun. Sci. Labs., Japan
Abstract :
We describe an experimental study for discovering underlying laws of market capitalization using BS (Balance Sheet) items. For this purpose, we apply law discovery methods based on neural networks: RF5 (Rule Finder) discovers a single numeric law from data containing only numeric values, RF6 discovers a set of nominally conditioned polynomials from data containing both nominal and numeric values, and MCV regularizer is used to improve both the generalization performance and the readability. Our preliminary experimental results show that these methods are promising for discovering underlying laws from financial data
Keywords :
data mining; financial data processing; generalisation (artificial intelligence); neural nets; polynomials; Balance Sheet items; MCV regularizer; RF5; RF6; Rule Finder; experimental study; financial data; generalization; law discovery; market capitalization; neural networks; nominally conditioned polynomials; Artificial intelligence; Asset management; Degradation; Explosions; Laboratories; Neural networks; Polynomials; Radio frequency; Robustness; Training data;
Conference_Titel :
Computational Intelligence for Financial Engineering, 2000. (CIFEr) Proceedings of the IEEE/IAFE/INFORMS 2000 Conference on
Conference_Location :
New York, NY
Print_ISBN :
0-7803-6429-5
DOI :
10.1109/CIFER.2000.844627
