Predictive to Prescriptive Analysis for Customer Churn in Telecom Industry Using Hybrid Data Mining Techniques

Abstract

Classification techniques take issue primarily within the accuracy of their models, that depends on the tactic adopted throughout the training section. In this work an attempt is created to create a data processing approaches for churn prediction in telecom business, that face substantial loss of income, because of client in danger of departure from a corporation. The projected model is capable of predicting subscriber churn pattern well in prior. We have proposed, hybrid Classification techniques that have shown their superiorities over single technique. Our approach is to compare 2 kinds of hybrid methods by classification with classification and clustering with classification hybrid methods. This paper gives the implementation details of decision tree and logistic regression to predict the customer churn in telecom industry. We implement Hybrid Decision Tree and Logistic Regression Classifier. These techniques provide better results, but it takes lot of time for execution. To tackle this problem; we proposed hybrid Fuzzy unordered rule induction algorithm (FURIA) with Fuzzy C-Means Clustering for predicting customer churn.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 14 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.