High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

A Framework for Correlated Pattern Mining in Intraday Stock Trading Transactions


Rajeshwari.K.Gundla , Walchand Institute of Technology, Solapur, MH; R.V. Argiddi, Walchand Institute of Technology, Solapur, MH


Stock Market, Association Rule Mining, Intraday Transactions, Hadoop


The search for association rules in market is one of the most prominent studied problems in Data Mining. This problem often referred as association rule mining and also roughly as correlation mining. Association rules are intended to identify patterns of the type: "A customer purchasing item X often also purchases item Y." These associations identified further can be generalized as correlations and dependencies among the item sets. Highly motivated by the inferential nature of association rule mining and its implementation feasible nature for applications beyond market basket data, we develop the notion of correlated patterns in Stock Market Trading and further focus around trading patterns during In traday period. A typical Inter transaction association rule mining in Stock Market is of form "If company ABC's stocks go up on day one then company XYZ's stocks goes down on day two", these inter transaction rules highlight associations between different transactions. We in our work propose a framework which would find and describe relevance of inter-transaction associations mined as intraday patterns to transactions with inter transaction associations mined across inter day patterns. We use modular approach for designing the system for its easy integration and scalability. This proposed modular framework will be put to test by using data obtained from Indian Stock Market using stock feed extractors for Intraday Trading volume data for Stocks.

Other Details

Paper ID: IJSRDV2I9438
Published in: Volume : 2, Issue : 9
Publication Date: 01/12/2014
Page(s): 713-716

Article Preview

Download Article