M. Gavrilov, D. Anguelov, P. Indyk, and R. Motwani, "Mining the stock market: Cluster discovery," in Proc. Sixth ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, 2000.  Home/Search   Document Not in Database   Summary   Related Articles

....consecutive periods. The number of periods considered in one relationship is limited by the model order (one or two) Any relationships of higher order are ignored by the data mining process. Different similarity measures for clustering of time series are studied in a new paper by Gavrilov et al. [5]. The measures are evaluated on one year stock market data from the Standard Poor index. The dimensionality of the original dataset is reduced by two methods: principal component analysis and aggregation of the time domain into windows of fixed length. The main result of [5] is that 97.62 of ....

....by Gavrilov et al. 5] The measures are evaluated on one year stock market data from the Standard Poor index. The dimensionality of the original dataset is reduced by two methods: principal component analysis and aggregation of the time domain into windows of fixed length. The main result of [5] is that 97.62 of the im 1083 4419 01 10.00 2001 IEEE 2 IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS PART B: CYBERNETICS portant information about a time series can be found in five dimensions only. In this correspondence, we present, for the first time, a general methodology for the ....

[Article contains additional citation context not shown here]

M. Gavrilov, D. Anguelov, P. Indyk, and R. Motwani, "Mining the stock market: Cluster discovery," in Proc. Sixth ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, 2000.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC