International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 49 - Issue 12 |
Published: July 2012 |
Authors: D. Sujatha, Priti Chandra, B. L. Deekshatulu |
![]() |
D. Sujatha, Priti Chandra, B. L. Deekshatulu . Transition in Time Series Data Mining on Correlated Items. International Journal of Computer Applications. 49, 12 (July 2012), 42-44. DOI=10.5120/7683-0989
@article{ 10.5120/7683-0989, author = { D. Sujatha,Priti Chandra,B. L. Deekshatulu }, title = { Transition in Time Series Data Mining on Correlated Items }, journal = { International Journal of Computer Applications }, year = { 2012 }, volume = { 49 }, number = { 12 }, pages = { 42-44 }, doi = { 10.5120/7683-0989 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2012 %A D. Sujatha %A Priti Chandra %A B. L. Deekshatulu %T Transition in Time Series Data Mining on Correlated Items%T %J International Journal of Computer Applications %V 49 %N 12 %P 42-44 %R 10.5120/7683-0989 %I Foundation of Computer Science (FCS), NY, USA
We are given a large database of customer transactions, where each transaction consists of transaction-id, the items bought in the transaction and the transaction time. The whole set of transaction is divided into a number of segments called durations (intervals) based on transaction time. And the dividing standard can be monthly, quarterly or yearly. We introduce the problem of mining strong association rules between consecutive durations using FP-tree and correlation coefficient, which is used to quantitatively describe the strength and sign of a relationship between two variables. This paper deals with the changes in the correlation between any two itemsets at the transition of the consecutive duration. Milestone is a change over point between durations. The transition may be positive or negative which are time points at which the pattern is either positively or negatively correlated. Also the method provides rare items, whose support is poor but are highly correlated.