A Big Data Clustering Algorithm for Mitigating the Risk of Customer Churn

Bi, Wenjie; Cai, Meiling; Liu, Mengqi; Guo, Li

doi:10.1109/tii.2016.2547584

Cited by 106 publications

(39 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The authors suggest RST approach using GA outperforms other rule generation techniques. Wenjie Bi et al [12] proposed a new clustering algorithm called Semantic Driven Subtractive Clustering Method (SDSCM) that provides effective data analysis through its parallel implementation. It also increases the accuracy and decreases the risk of inaccurate operations.…”

Section: Related Workmentioning

confidence: 99%

A Hybrid Approach for Class Imbalance Problem in Customer Churn Prediction: A Novel Extension to Under-sampling

Salunkhe¹,

Mali²

2018

IJISA

View full text Add to dashboard Cite

Abstract-Customer retention is becoming a key success factor for many business applications due to increasing market competition. Especially telecom companies are facing this challenge with a rapidly increasing number of service providers. Hence there is need to focus on customer churn prediction in order to detect the customers that are likely to churn i.e. switch from one service provider to another. Several data mining techniques are applied for classifying customers into the churn and non-churn category. But churn prediction applications comprise an imbalanced distribution of the dataset.One of the commonly used techniques to handle imbalanced data is re-sampling of data as it is independent of the classifier being used. In this paper, we develop a hybrid re-sampling approach named SOS-BUS by combining well known oversampling technique SMOTE with our novel under-sampling technique. Our methodology aims to focus on the necessary data of majority class and avoid their removal in order to overcome the limitation of random under-sampling. Experimental results show that the proposed approach outperforms the other reference techniques in terms of Area under ROC Curve (AUC).

show abstract

Section: Related Workmentioning

confidence: 99%

A Hybrid Approach for Class Imbalance Problem in Customer Churn Prediction: A Novel Extension to Under-sampling

Salunkhe¹,

Mali²

2018

IJISA

View full text Add to dashboard Cite

show abstract

“…In the past years, the AFS theory has been used with great success in various fields. This section discusses various applications based on AFS theory in the area of business intelligence (Bi et al, ; Ebonzo & Liu, ; Ebonzo et al, ; Y. Li et al, , , ; Tao et al, ; Y. Wang et al, , ; Xu et al, ), computer vision (Q. Li et al, ; Z. Li, Duan, et al, ; Z. Li, Zhang, Duan, Wang, et al, ; Ren et al, ; Sarkhel et al, ), financial data analysis (Guo et al, ; Tao et al, ; W. Wang & Liu, ), and clinical data analysis (Silva et al, ). The AFS theory provides us a useful tool to study the knowledge representation and inference that is significant in knowledge engineering, decision‐making, and intelligent systems.…”

Section: Applicationsmentioning

confidence: 99%

Knowledge discovery and semantic learning in the framework of axiomatic fuzzy set theory

Liu

Jia

Wang

et al. 2018

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Axiomatic fuzzy set (AFS) theory facilitates a way on how to transform data into fuzzy sets (membership functions) and implement their fuzzy logic operations, which provides a flexible and powerful tool for representing human knowledge and emulate human recognition process. In recent years, AFS theory has received increasing interest. In this survey, we report the current developments of theoretical research and practical advances in the AFS theory. We first review some notion and foundations of the theory with an illustrative example, then, we focus on the various extensions of AFS theory for knowledge discovery, including clustering, classification, rough sets, formal concept analysis, and other learning tasks. Due to its unique characteristics of semantic representation, AFS theory has been applied in multiple domains, such as business intelligence, computer vision, financial analysis, and clinical data analysis. This survey provides a comprehensive view of these advances in AFS theory and its potential perspectives. This article is categorized under: Technologies > Computational Intelligence

show abstract

“…It involves removing noisy data, performing some advanced analytics such as social network analysis, opinion mining, trend analysis, sentiment analysis. The final step is presentation of the analysis [6]. It involves summarizing and evaluating the findings from the above step and presenting those findings.…”

Section: Related Workmentioning

confidence: 99%

Location Aware Social Networks User Profiling Using Big Data Analytics

Mukkamula¹,

Nangunuri²

2017

IJIES

View full text Add to dashboard Cite

Social Network Analytics (SNA), on the other hand, provides insights of many perspectives of the society through the sample users participated in social network. The exponential growth of the social network and correspondingly its data leads to the demand for big data computational environments. One such popular and useful big data in SNA is GIS (Geographical Information System) data that provides geographical location data of the record generated in social networks. In order to profile a user in social networks according to GIS data, the existing methodologies uses the centroid measures such as mean, median of the GIS data available for the user. These methods failed to mention and solve the serious issues such as cold user as well does not able to consider the weightage of the data item in analytics. The proposed method in this paper focuses to define the weightage of a data item in the available GIS data according to the application and also proposed a method to identify and solve cold user problem. The experiments carried on cutting edge technologies of the big data analytics shown significance of the proposed method in profiling user w.r.t. GIS data. The results of the proposed user profiling is measured with Within Sum of Squares (WSS) measure and compared over exiting profiling methodologies shown consistent improvement for any number of clusters formed over benchmark datasets.

show abstract

A Big Data Clustering Algorithm for Mitigating the Risk of Customer Churn

Cited by 106 publications

References 21 publications

A Hybrid Approach for Class Imbalance Problem in Customer Churn Prediction: A Novel Extension to Under-sampling

A Hybrid Approach for Class Imbalance Problem in Customer Churn Prediction: A Novel Extension to Under-sampling

Knowledge discovery and semantic learning in the framework of axiomatic fuzzy set theory

Location Aware Social Networks User Profiling Using Big Data Analytics

Contact Info

Product

Resources

About