There are many data mining algorithms which exist today for searching patterns from transactional databases. Most of them work only on precise data. But there are also situations in which these conventional algorithms fail, situations in which Data is uncertain in nature. Uncertain data can be explained as the one where items have probabilistic values associated with them. These probabilities express the likelihood of these items to be present in the transactions. In mining, the search tree produced is also one of the major factor of concern. The search space produced when dealing with uncertain data is much larger due to the presence of existential probabilities. This problem worsens when dealing with Big data. Considering all the above factors and concerns, an algorithm is specified and explained ahead. It allows users to express the interest in terms of constraints and uses the Map Reduce programming model to mine uncertain Big data for frequent patterns that satisfy the user-specified constraints. By using these user-specified constraints as inputs, the algorithm greatly reduces the search space for Big data mining of uncertain data, and returns only those patterns the users are interested in.

Big data models and algorithms, Big data analytics, Uncertain data mining, Frequent pattern mining

[1] C.K.-S. Leung , R. K. MacKinnon, F. Jiang, “Reducing the Search Space for Big Data Mining for Interesting Pattern from Uncertain Data” , 2014 IEEE International Congress on Big Data, pp.315-322, 2014.
[2] J.V. Patel, K. J. Panchal, “A Modified Approach to Mine Frequent Patterns from Uncertain Data”, 2015 1st International Conference (NGCT), pp.612-615, 2015.
[3] C.K.-S. Leung, “Mining uncertain data”, WIREs Data Mining and Knowledge Discovery, Vol.1 ,Issue.4, pp.316–329, July-Aug. 2011.
[4] S. Madden, “From databases to big data,” IEEE Internet Computing, Vol.16, Issue.3, pp. 4–6, May–June 2012.
[5] Azzini, P. Ceravolo, “Consistent process mining over Big data triple stores”, IEEE Big Data Congress 2013, pp. 54–61, 2013.
[6] Ӧlmezoğullari, I. Ari, “Online association rule mining over fast data”, IEEE International Congress on Big Data 2013, pp.110–117, 2013.
[7] P. Agarwal, G. Shroff, P. Malhotra, “Approximate incremental big-data harmonization”, IEEE Big Data Congress 2013, pp.118–125, 2013.
[8] Yang , S. Fong, “Countering the concept-drift problem in big data using iOVFDT”, IEEE Big Data Congress 2013, pp.126–132, 2013.
[9] C.K.Chui, B.Kao, E.Hung, “Mining Frequent Itemsets from Uncertain Data”, LNCS 2007, pp.47-58, 2007.
[10] C.K.-S. Leung , F. Jiang, “Frequent itemset mining of uncertain data streams using the damped window model”, ACM SAC 2011, pp.950–955, 2011.
[11] C.K.-S. Leung , F. Jiang, “Frequent pattern mining from time-fading streams of uncertain data”, DaWaK 2011 (LNCS 6862), pp. 252-264, 2011.
[12] Y. Tong, L. Chen, Y. Cheng, P.S. Yu, “Mining frequent itemsets over uncertain databases”, PVLDB, Vol.5, Issue.11, pp.1650–1661, July 2012.
[13] C.K.-S. Leung, M.A.F. Mateo, D.A. Brajczuk, “A tree-based approach for frequent pattern mining from uncertain data”, PAKDD 2008 (LNAI 5012), pp. 653–661, 2008.
[14] C.K.-S. Leung , S.K. Tanbeer, “Fast tree-based mining of frequent itemsets from uncertain data”, DASFAA 2012 (LNCS 7238), pp. 272–287, 2012.
[15] C.K.-S. Leung, S.K. Tanbeer, “PUF-tree: A compact tree structure for frequent pattern mining of uncertain data”, PAKDD 2013 (LNCS 7818), pp.13–25, 2013.
[16] D.N. Goswami, Anshu Chaturvedi., C.S. Raghuvanshi,”An Algorithm for Frequent Pattern Mining Based On Apriori”, International Journal on Computer Science and Engineering(IJCSE), Vol.2, Issue.4, pp.942-947, 2010.
[17] J.Dean, S.Ghemawat, “MapReduce: simplified data processing on large clusters”, CACM, Vol.51, Issue.1, pp.107-113, Jan. 2008.
[18] M.Y.Lin, P.Y.Lee, S. C. Hsueh, “Apriori based frequent itemset mining algorithms on MapReduce”, ICUIMC 2012, art.76, 2012.