Mobile Miner

Preview:

DESCRIPTION

Mobile Miner is a tool using community mining algorithm for mining mobile data.

Citation preview

ByKanchan Jadhav

MESS06

Guided byProf. R.N. Phursule

Computer Engg Dept.Jspm’s

Imperial College Of Engineering & Research

MOBILE MINER

Introduction

Architecture

Concentric Circle Model

Community Mining

Algorithm

Example

Application in Mobile Miner

Outline

Mobile Miner, a data mining tool for mobile data analysis and business strategy development.

It uses state-of-the-art data mining techniques.

Mobile Miner adaptively profiles users' behavior from their calling and moving record streams.

In a large mobile communication companies like Idea, Airtel, Reliance, there are many analytical tasks where data mining can help to address the business interests of the company.

Introduction

Architecture

Customer records are collected by the mobile communication base stations and fed into Mobile Miner as data streams.

In the profile mining part, customers' moving profiles or their frequent moving patterns are constructed based on their moving records continuously.

The mobile user segmentation module clusters customers according to their profiles.

Contd..

Contd… In social community discovery module a

social network among customers is constructed.

In this application, the connection weights on edges in graphs should is considered.

The algorithm using concentric circle model for community mining is used to discover communities.

Concentric Circle Model For Community

Affiliated objects(3rd class)

Affiliated objects(2nd class)

Affiliated objects(1st class)

Core objects

At the center of the circle there are core objects.

Affiliated objects are related to the core objects.

With this model, a community is defined as a four-tuple <C, A, F, Va>◦ C : core object set◦ A : affiliated object Set◦ F : affiliation definition function◦ Va : importance vector for A

Contd…

Basic Algorithm:

1) Generate 1-itemsets IS1 with minimal support S k 2

2) while k m do //generate up to m-itemsets, m is the length of the longest itemset

3) Generate k-itemsets ISk using (k-1)-itemsets IS(k-1) with S

4) Prun IS(k-1) using ISk k k +1

5) End

Put IS1 to ISm to itemsets set IS

COMMUNITY MINING

1)for every itemset I in IS

Put objects in I to community C

2)Do

Add objects not in C but having links to objects in C to CCalculate ranking value of new added objects

3)until No more objects could be addedPut a copy of C to communities set CSClear C

4)end

Contd…

Core Set Merging:-◦Core set merging means to combine two

similar core sets.

Tuning Granularity

AB

C

D E

F

Community Merging:-◦ Communities have different core sets but their

affiliated objects are coincident. So they are merged onto one community.

Tuning Granularity

Year Communities related to Data Mining (no. of papers)

2001 •Association Rule(33)

• Clustering (19)

•Web mining (7)•…

1998 ….

1994 •Knowledge discovery and data mining (13)

Example•BIRCH: an efficient data clustering method for very large databases (Core)•CURE: an efficient clustering algorithm for large databases (Core)•Efficient discovery of error-tolerant frequent itemsets in highdimensions

•Mining association rules between sets of items in large databases (Core)•Knowledge Discovery in Databases: An Attribute- Oriented Approach (Core)•Tutorial database mining

Yearly Communities Related To Data Mining

The algorithm is used to discover communities in the weighted graph in two steps:

1) Generate a core set and then expand the core set with affiliated customers.

2) To control the granularity of the discovering communities, a merging schema is used to merge similar communities to get coarser results.

Application in Mobile Miner

Mobile Miner provides an interface for analyzing the social communities found from the social network.

A business analyst can interact with the social community formed.

The user interface can help business analysts to tune the underlying data mining methods.

Contd…

The User Interface

Data mining techniques need to be tuned to make business analysis effective.

To understand how well the data mining techniques in Mobile Miner work in practice, real mobile communication data sets are used to show interesting mining results.

Conclusion

[1] L. Chang, T. Wang, D. Yang, and H. Luan. Seqstream: Mining closed sequential patterns over stream sliding windows. In Proceeding of ICDM'08, Pisa, Italy, December 2008.

 

[2] Y. Cheng and G. M. Church. Biclustering of expression data. In Proceedings of ISMB'00. Menlo Park, USA: AAAI, pages 93{108, 2000.

 

[3] W. Zhou, J. Wen, W. Ma, and H. Zhang. A concentric-circle model for community mining in graph structures. In Microsoft Research, Seattle, Technical. Report MSR-TR-2002-123, 2002.

 

[4] Rakesh Agrawal, Tomasz Imielinski, Arun Swami, Mining Association Rules between Sets of Items in Large Databases, in Proceedings of the International Conference on Management of Data (ACM SIGMOD), 1993.

References

THANK YOU……

Questions ? ? ?