Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Data mining in telecommunication industry
1. Data Mining in Telecommunication Industry
Professor : Vinay Mistry
Presented By:
● Shilpa Sawant - MIM 17
● Harshal Pawar - MIM 13
2. Introduction
● Telecommunications industry is known as an early adopter of data mining techniques, due
to enormous amount of high-quality data it generates.
● Huge volume of data is generated from various operational systems and these are used for
solving many business problems that required urgent handling.
● Data Mining methods and business intelligence technology are widely used for handling the
business problems in this industry.
● Telecommunication companies utilize data mining to improve their marketing efforts, identify fraud,
and better manage their telecommunication networks.
● Cortes and Pregibon (2001) developed signature based methods which was applied to data
streams of call detail records for fraud detection in Telecommunication Industry.
● A more traditional approach involves generating customer profiles (i.e., signatures) from call detail
records and then mining these profiles for marketing purposes. This approach has been used to
identify whether a phone line is being used for voice or fax (Kaplan, Strauss & Szegedy, 1999)
3. 1. Call Detail Data 2. Network Data 3. Customer Detail Data
● Information about call which
store as call detail data.
● Telecommunication networks contain
thousands of components, which are
interconnected.
● Database of information of
customers
● Includes information like
originating and terminating
phone numbers, date, time
and duration of call
● Used for network management
functions like fault detection.
● Name,Age,Address,
Telephone Type,
Subscription Type,
Payment History
● Average call duration
● Average call generated
● Call Period
● Originated Calls
● Data Mining technologies are used in
identification of network faults by
automatically extracting knowledge
from network data.
Types Of Telecommunication Data
4. Data Mining Applications
● Fraud Detection
➢ Common method to identify fraud is to build customer’s profile of calling behaviour.
➢ Recent activity is compared against this behavior,so if suspicious activity is seen then that
fraud is caught.
➢ Data mining application depends on deviation detection.
➢ Call detail summaries are updated in real time.
5. Data Mining Applications Cont..
● Marketing and Customer Profiling
➢ Companies maintains huge amount of data about their customers
➢ Data mining tools are applied and segmentations is done on this large amount of data.
➢ Used to build customer’s profile ,build marketing strategies, planning for the future decisions,
performance measurement, result tracking, etc
6. Data Mining Applications Cont..
● Network Fault Isolation
➢ Extremely complex configuration and consist of many interconnected components..
➢ Network components generate status as well as alarm messages every time.
➢ In order to identify the network faults the alarms should be analyzed automatically.
➢ Data mining helps to automatically analyze and detect the faults so that they can be resolved.
7. Mining algorithm used in telecommunication industry
1.THE k-MEANS CLUSTERING METHOD
Commonly used data mining techniques include association analysis, classification and prediction, cluster
analysis, outlier analysis and evolution analysis. Among them, the cluster analysis can be used to solve
the problem of customer grouping.
Clustering is the process of grouping the data into classes or clusters so that objects within a cluster have
high similarity in comparison to one another but are very dissimilar to objects in other clusters. Clustering
techniques are organized into the following categories: partitioning methods, hierarchical methods,
density-based methods, grid-based methods and model-based methods
9. Use case of k-MEANS algorithm
● Call Record Detail Analysis
A call detail record (CDR) is the information captured by telecom companies during the call, SMS, and internet activity of
a customer. This information provides greater insights about the customer’s needs when used with customer
demographics. we can cluster customer activities for 24 hours by using the unsupervised k-means clustering algorithm.
● Customer Segmentation
Clustering helps marketers improve their customer base, work on target areas, and segment customers based on
purchase history, interests, or activity monitoring. Telecom providers can cluster prepaid customers to identify patterns
in terms of money spent in recharging, sending SMS, and browsing the internet. The classification would help the
company target specific clusters of customers for specific campaigns.
11. ● Google
● Research Paper - A State of Art Analysis of Telecommunication Data by k-Means
and k-Medoids Clustering Algorithms. By T. Velmurugan
● Research Paper - Mobile Customer Clustering Analysis Based on Call Detail Records
References