scholarly journals A Hybrid Swarm Intelligent Neural Network Model for Customer Churn Prediction and Identifying the Influencing Factors

Information ◽  
2018 ◽  
Vol 9 (11) ◽  
pp. 288 ◽  
Author(s):  
Hossam Faris
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Churn Prediction ◽  
Hybrid Swarm ◽  
Customer Churn ◽  
The Neural Network ◽  
Proposed Model ◽  
Telecommunication Companies ◽  
Technique Evaluation ◽  
Imbalanced Class Distribution

Customer churn is one of the most challenging problems for telecommunication companies. In fact, this is because customers are considered as the real asset for the companies. Therefore, more companies are increasing their investments in developing practical solutions that aim at predicting customer churn before it happens. Identifying which customer is about to churn will significantly help the companies in providing solutions to keep their customers and optimize their marketing campaigns. In this work, an intelligent hybrid model based on Particle Swarm Optimization and Feedforward neural network is proposed for churn prediction. PSO is used to tune the weights of the input features and optimize the structure of the neural network simultaneously to increase the prediction power. In addition, the proposed model handles the imbalanced class distribution of the data using an advanced oversampling technique. Evaluation results show that the proposed model can significantly improve the coverage rate of churn customers in comparison with other state-of-the-art classifiers. Moreover, the model has high interpretability, where the assigned feature weights can give an indicator about the importance of their corresponding features in the classification process.

Enhanced Churn Prediction Using Stacked Heuristic Incorporated Ensemble Model

2021 ◽  
Vol 14 (2) ◽  
pp. 174-186
Author(s):  
Sivasankar Karuppaiah ◽  
N. P. Gopalan
Keyword(s):  
State Of The Art ◽  
Experimental Results ◽  
Ensemble Model ◽  
Churn Prediction ◽  
Customer Churn ◽  
Proposed Model ◽  
Customer Churn Prediction ◽  
Effective Models

In a rapidly growing industry like telecommunications, customer churn prediction is a crucial challenge affecting the sustainability of the business as a whole. The fact that retaining a customer is more profitable than acquiring new customers is important to predict potential churners and present them with offers to prevent them from churning. This work presents a stacked CLV-based heuristic incorporated ensemble (SCHIE) to enable identification of potential churners so as to provide them with offers that can eventually aid in retaining them. The proposed model is composed of two levels of prediction followed by a recommendation to reduce customer churn. The first level involves identifying effective models to predict potential churners. This is followed by result segregation, CLV-based prediction, and user shortlisting for offers. Experimental results indicate high efficiencies in predicting potential churners and non-churners. The proposed model is found to reduce the overall loss by up to 50% in comparison to state-of-the-art models.

scholarly journals Performance Comparison of Neural Network Training Algorithms for Modeling Customer Churn Prediction

2018 ◽  
Vol 7 (2.15) ◽  
pp. 35 ◽  
Author(s):  
Mohd Khalid Awang ◽  
Mohammad Ridwan Ismail ◽  
Mokhairi Makhtar ◽  
M Nordin A Rahman ◽  
Abd Rasid Mamat
Keyword(s):  
Neural Network ◽  
Conjugate Gradient ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Telecommunication Service ◽  
Churn Prediction ◽  
Data Set ◽  
Customer Churn ◽  
The Neural Network ◽  
Customer Churn Prediction

Predicting customer churn has become the priority of every telecommunication service provider as the market  is becoming more saturated and competitive. This paper presents a comparison of neural network learning algorithms for customer churn prediction.  The data set used to train and test the neural network algorithms was provided by one of the leading telecommunication company in Malaysia. The Multilayer Perceptron (MLP) networks are trained using nine (9) types of learning algorithms, which are Levenberg Marquardt backpropagation (trainlm), BFGS Quasi-Newton backpropagation (trainbfg), Conjugate Gradient backpropagation with Fletcher-Reeves Updates (traincgf), Conjugate Gradient backpropagation with Polak-Ribiere Updates (traincgp), Conjugate Gradient backpropagation with Powell-Beale Restarts (traincgb), Scaled Conjugate Gradient backpropagation (trainscg), One Step Secant backpropagation (trainoss), Bayesian Regularization backpropagation (trainbr), and Resilient backpropagation (trainrp). The performance of the Neural Network is measured based on the prediction accuracy of the learning and testing phases. LM learning algorithm is found to be the optimum model of a neural network model consisting of fourteen input units, one hidden node and one output node. The best result of the experiment indicated that this model is able to produce the performance accuracy of 94.82%. 

Distributed model for customer churn prediction using convolutional neural network

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Muhammad Usman Tariq ◽  
Muhammad Babar ◽  
Marc Poulin ◽  
Akmal Saeed Khattak
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
False Negative ◽  
Accuracy Score ◽  
Churn Prediction ◽  
Data Set ◽  
Content Type ◽  
Customer Churn ◽  
Proposed Model ◽  
Customer Churn Prediction

Purpose The purpose of the proposed model is to assist the e-business to predict the churned users using machine learning. This paper aims to monitor the customer behavior and to perform decision-making accordingly. Design/methodology/approach The proposed model uses the 2-D convolutional neural network (CNN; a technique of deep learning). The proposed model is a layered architecture that comprises two different phases that are data load and preprocessing layer and 2-D CNN layer. In addition, the Apache Spark parallel and distributed framework is used to process the data in a parallel environment. Training data is captured from Kaggle by using Telco Customer Churn. Findings The proposed model is accurate and has an accuracy score of 0.963 out of 1. In addition, the training and validation loss is extremely less, which is 0.004. The confusion matric results show the true-positive values are 95% and the true-negative values are 94%. However, the false-negative is only 5% and the false-positive is only 6%, which is effective. Originality/value This paper highlights an inclusive description of preprocessing required for the CNN model. The data set is addressed more carefully for the successful customer churn prediction.

scholarly journals Enhancing the performance of cancer text classification model based on cancer hallmarks

2021 ◽  
Vol 10 (2) ◽  
pp. 316
Author(s):  
Noha Ali ◽  
Ahmed H. AbuEl-Atta ◽  
Hala H. Zayed
Keyword(s):  
Neural Network ◽  
Language Processing ◽  
Text Classification ◽  
State Of The Art ◽  
Classification Model ◽  
Biomedical Text ◽  
Cancer Hallmarks ◽  
Embedding Technique ◽  
Proposed Model ◽  
Biomedical Text Classification

<span id="docs-internal-guid-cb130a3a-7fff-3e11-ae3d-ad2310e265f8"><span>Deep learning (DL) algorithms achieved state-of-the-art performance in computer vision, speech recognition, and natural language processing (NLP). In this paper, we enhance the convolutional neural network (CNN) algorithm to classify cancer articles according to cancer hallmarks. The model implements a recent word embedding technique in the embedding layer. This technique uses the concept of distributed phrase representation and multi-word phrases embedding. The proposed model enhances the performance of the existing model used for biomedical text classification. The result of the proposed model overcomes the previous model by achieving an F-score equal to 83.87% using an unsupervised technique that trained on PubMed abstracts called PMC vectors (PMCVec) embedding. Also, we made another experiment on the same dataset using the recurrent neural network (RNN) algorithm with two different word embeddings Google news and PMCVec which achieving F-score equal to 74.9% and 76.26%, respectively.</span></span>

scholarly journals Remanent battery capacity estimation for autonomous ground industrial vehicles

2019 ◽  
Vol 290 ◽  
pp. 02009
Author(s):  
Tom Savu ◽  
Bogdan Alexandru Jugravu
Keyword(s):  
Neural Network ◽  
Industrial System ◽  
Ground Vehicles ◽  
Future Developments ◽  
Capacity Loss ◽  
The Neural Network ◽  
Proposed Model ◽  
Battery Capacity ◽  
Data Volume ◽  
Remaining Capacity

When travelling in an industrial system for completing their assigned tasks, autonomous ground vehicles must estimate the remanent capacity of their batteries and decide if they are able to assume the next task and afterward travel to the charging or replacement station. The amount of energy needed for moving on a certain distance depends on a set of parameters belonging to the vehicle, to the runway and to the vehicle’s trajectory. The paper proposes a model for estimating the remaining capacity of the batteries after a certain distance would be covered by a vehicle. Parameters values were obtained by simulation, capacity loss was computed using the proposed model and then a neural network was taught to perform the estimation. The neural network was further used to simulate the situation when a vehicle is estimating the needed capacity before accepting a task to be performed. The results proved that the model and the network, even developed using low data volume and processing time, are able to provide accurate enough estimations and are able to allow future developments.

scholarly journals Relational Graph Neural Network with Hierarchical Attention for Knowledge Graph Completion

2020 ◽  
Vol 34 (05) ◽  
pp. 9612-9619
Author(s):  
Zhao Zhang ◽  
Fuzhen Zhuang ◽  
Hengshu Zhu ◽  
Zhiping Shi ◽  
Hui Xiong ◽  
...  
Keyword(s):  
Neural Network ◽  
Missing Values ◽  
State Of The Art ◽  
Attention Mechanism ◽  
Knowledge Graph ◽  
Incomplete Knowledge ◽  
Neighborhood Information ◽  
Local Neighborhood ◽  
Proposed Model ◽  
Knowledge Graphs

The rapid proliferation of knowledge graphs (KGs) has changed the paradigm for various AI-related applications. Despite their large sizes, modern KGs are far from complete and comprehensive. This has motivated the research in knowledge graph completion (KGC), which aims to infer missing values in incomplete knowledge triples. However, most existing KGC models treat the triples in KGs independently without leveraging the inherent and valuable information from the local neighborhood surrounding an entity. To this end, we propose a Relational Graph neural network with Hierarchical ATtention (RGHAT) for the KGC task. The proposed model is equipped with a two-level attention mechanism: (i) the first level is the relation-level attention, which is inspired by the intuition that different relations have different weights for indicating an entity; (ii) the second level is the entity-level attention, which enables our model to highlight the importance of different neighboring entities under the same relation. The hierarchical attention mechanism makes our model more effective to utilize the neighborhood information of an entity. Finally, we extensively validate the superiority of RGHAT against various state-of-the-art baselines.

scholarly journals Graph Dilated Network with Rejection Mechanism

2020 ◽  
Vol 10 (7) ◽  
pp. 2421
Author(s):  
Bencheng Yan ◽  
Chaokun Wang ◽  
Gaoyang Guo
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Great Success ◽  
Convolution Kernel ◽  
Graph Structure ◽  
Proposed Model ◽  
Rejection Mechanism ◽  
Laplacian Smoothing ◽  
Graph Neural Networks ◽  
High Level

Recently, graph neural networks (GNNs) have achieved great success in dealing with graph-based data. The basic idea of GNNs is iteratively aggregating the information from neighbors, which is a special form of Laplacian smoothing. However, most of GNNs fall into the over-smoothing problem, i.e., when the model goes deeper, the learned representations become indistinguishable. This reflects the inability of the current GNNs to explore the global graph structure. In this paper, we propose a novel graph neural network to address this problem. A rejection mechanism is designed to address the over-smoothing problem, and a dilated graph convolution kernel is presented to capture the high-level graph structure. A number of experimental results demonstrate that the proposed model outperforms the state-of-the-art GNNs, and can effectively overcome the over-smoothing problem.

scholarly journals An Efficient Neural Network for Shape from Focus with Weight Passing Method

2018 ◽  
Vol 8 (9) ◽  
pp. 1648 ◽  
Author(s):  
Hyo-Jong Kim ◽  
Muhammad Mahmood ◽  
Tae-Sun Choi
Keyword(s):  
Neural Network ◽  
Convergence Rate ◽  
Network Model ◽  
Neural Network Model ◽  
Image Sequences ◽  
Depth Maps ◽  
The Neural Network ◽  
Proposed Model ◽  
Real Objects ◽  
Shape From Focus

In this paper, we suggest an efficient neural network model for shape from focus along with weight passing (WP) method. The neural network model is simplified by reducing the input data dimensions and eliminating the redundancies in the conventional model. It helps for decreasing computational complexity without compromising on accuracy. In order to increase the convergence rate and efficiency, WP method is suggested. It selects appropriate initial weights for the first pixel randomly from the neighborhood of the reference depth and it chooses the initial weights for the next pixel by passing the updated weights from the present pixel. WP method not only expedites the convergence rate, but also is effective in avoiding the local minimization problem. Moreover, this proposed method may also be applied to neural networks with diverse configurations for better depth maps. The proposed system is evaluated using image sequences of synthetic and real objects. Experimental results demonstrate that the proposed model is considerably efficient and is able to improve the convergence rate significantly while the accuracy is comparable with the existing systems.

An Optimizing Design Approach for the Fiber Manufacturing Based on the Immune Genetic Algorithm-Optimized Neural Network

2011 ◽  
Vol 267 ◽  
pp. 19-24
Author(s):  
Hui Zhong Zhu ◽  
Yong Sheng Ding ◽  
Xiao Liang ◽  
Kuang Rong Hao ◽  
Hua Ping Wang
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Immune Genetic Algorithm ◽  
System A ◽  
The Neural Network ◽  
Proposed Model ◽  
Optimizing Design ◽  
Spinning Process ◽  
Fiber Manufacturing ◽  
Network Component

A novel neural network-based approach with immune genetic algorithm is proposed to conduct the optimizing design for the industrial filament manufacturing system. A new model is proposed in this paper to acquire better filament quality during such process. The proposed model was a combination of two components, namely, a traditional neural network which is used to simulate and an immune genetic algorithm-based part which is to improve the performance of the neural network component. Simulation results demonstrate that the proposed method can efficiently demonstrate the spinning process of filament and conduct the prediction of the filament quality with the production parameters as input data. Meanwhile, the proposed method enjoys faster speed and more precise accuracy, compared with traditional methods.

Sign in / Sign up

Export Citation Format

Share Document