A Modified Artificial Neural Network Learning Algorithm for Imbalanced Data Set Problem

2010 ◽  
Author(s):  
Asrul Adam ◽  
Ibrahim Shapiai ◽  
Zuwairie Ibrahim ◽  
Marzuki Khalid ◽  
Lim Chun Chew ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Learning Algorithm ◽  
Imbalanced Data ◽  
Data Set ◽  
Neural Network Learning ◽  
Network Learning ◽  
Artificial Neural

COMPARATIVE ANALYSIS OF PREDICTION TECHNIQUES ON THE BASIS OF TELECOM CUSTOMER CHURN

2021 ◽  
Vol 16 (9) ◽  
Author(s):  
Yasser Khan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Performance Metrics ◽  
Learning Algorithm ◽  
Data Sets ◽  
Data Set ◽  
Broadband Service ◽  
Customer Churn ◽  
Artificial Neural ◽  
Prediction Techniques

Telecommunication customer churn is considered as major cause for dropped revenue and customer baseline of voice, multimedia and broadband service provider. There is strong need on focusing to understand the contributory factors of churn. Now considering factors from data sets obtained from Pakistan major telecom operators are applied for modeling. On the basis of results obtained from the optimal techniques, comparative technical evaluation is carried out. This research study is comprised mainly of proposition of conceptual frame work for telecom customer churn that lead to creation of predictive model. This is trained tested and evaluated on given data set taken from Pakistan Telecom industry that has provided accurate & reliable outcomes. Out of four prevailing statistical and machine learning algorithm, artificial neural network is declared the most reliable model, followed by decision tree. The logistic regression is placed at last position by considering the performance metrics like accuracy, recall, precision and ROC curve. The results from research has revealed main parameters found responsible for customer churn were data rate, call failure rate, mean time to repair and monthly billing amount. On the basis of these parameter artificial neural network has achieved 79% more efficiency as compare to low performing statistical techniques.

scholarly journals Comparative investigation of artificial neural network learning algorithms for modeling solar still production

2015 ◽  
Vol 5 (4) ◽  
pp. 480-493 ◽  
Author(s):  
Ahmed F. Mashaly ◽  
A. A. Alazba
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Learning Algorithms ◽  
Ambient Air ◽  
Feed Water ◽  
Solar Still ◽  
Neural Network Learning ◽  
Network Learning ◽  
Artificial Neural ◽  
Lm Algorithm

Three artificial neural network learning algorithms were utilized to forecast the productivity (MD) of a solar still operating in a hyper-arid environment. The learning algorithms were the Levenberg–Marquardt (LM), the conjugate gradient backpropagation with Fletcher–Reeves restarts, and the resilient backpropagation. The Julian day, ambient air temperature, relative humidity, wind speed, solar radiation, temperature of feed water, temperature of brine water, total dissolved solids (TDS) of feed water, and TDS of brine water were used in the input layer of the developed neural network model. The MD was located in the output layer. The developed model for each algorithm was trained, tested, and validated with experimental data obtained from field experimental work. Findings revealed the developed model could be utilized to predict the MD with excellent accuracy. The LM algorithm (with a minimum root mean squared error and a maximum overall index of model performance) was found to be the best in the training, testing, and validation stages. Relative errors in the predicted MD values of the developed model using the LM algorithm were mostly in the vicinity of ±10%. These results indicated that the LM algorithm is the most ideal and accurate algorithm for the prediction of the MD with the developed model.

Sign in / Sign up

Export Citation Format

Share Document