Customer Churn Prediction in Telecommunication Industry Having Data Certainty

Customer Churn Prediction is a challenging activity for decision makers because most of the time, churn and non-churn customers have similar features. It is one of the major concerns for large companies, especially in the field of telecommunication field. Churn can be considered as a binary classification. The classifiers shows different accuracy levels at different zones of data. In such cases, a correlation can easily be observed in the level of classifier's accuracy and certainty of its prediction. So a mechanism to estimate the classifier’s certainty for different zones within the data is needed so that the expected classifier’s accuracy can be estimated. Here the classifier’s certainty estimation is done using six sigma rule of normal distribution applied on the correlation values of all features in the dataset. Based on this the dataset is grouped into two categories such as (i) data having high certainty, and (ii) data having low certainty. Based on these criteria, classifier accuracy is estimated in the high distance zone. From the different evaluation measures like accuracy, f-measure, precision, recall and Receiving Operating Characteristics (ROC) area, the performance of classifier is evaluated. Then by applying a k fold approach the certainty of the classifier decision is estimated.

Customer Churn Prediction in Telecommunication Industry Using Data Certainty

Customer churn is a major problem affecting large companies, especially in telecommunication field. So the telecom industries have to take the necessary steps to retain their customers, to maintain their market value. So companies are seeking to develop methods that predict potential churned customers. We have to find out the factors that increase customer churn for making necessary actions to reduce churn. In the past, different data mining techniques have been used for predicting the churners. Here the most popular machine learning algorithms used for churn predicting are analysed. The conclusions are stated with the help of suitable tables.

Visualizing Data Certainty: A Case Study Using Graduated Circle Maps

Several techniques have been proposed for displaying data certainty on maps, but few have been empirically tested for effectiveness. While it is important to make data certainty information easily accessible, the addition of such data should not unduly increase map complexity. Thus, it becomes important for cartographers to examine the available methods for displaying this aspect of metadata and to test each for its effectiveness. The focus of this study was the display of data certainty information on graduated circle maps. Four types of accuracy indicators were evaluated for their effectiveness in communicating data certainty information. Two were traditional accuracy indicators: reliability diagrams and legend statements. Two were bivariate in form, one using a value-size combination and the other mimicking the idea of focus byn varying the line value of the graduated circles to suggest a fading of symbolization for least certain data. The study was designed to assess whether subjects could identify data certainty information on test maps, and evaluate how accurately and confidently they could extract and interpret both thematic and data certainty information. Mean accuracy and confidence rates were compared for maps using different accuracy indicators to evaluate their relative effectiveness. Results suggest that subjects had most difficulty identifying and extracting data certainty information using maps that employed legend statements. They were most successful when data certainty was wedded to thematic data on the map using the bivariate accuracy indicator that mimicked the concept of focus. Identification and extraction of thematic data values were not significantly affected by choice of accuracy indicator.