scholarly journals A Comparative Study of Predicting Customer Churn and Lifetime

2020 ◽  
Vol 26 (1) ◽  
pp. 1-6
Author(s):  
O. Adesua ◽  
◽  
P.A. Danquah ◽  
O.B Longe
Keyword(s):  
Neural Networks ◽  
Comparative Analysis ◽  
Mobile Station ◽  
Signal Strength ◽  
Base Station ◽  
Churn Prediction ◽  
Customer Base ◽  
Customer Churn ◽  
Customer Lifetime ◽  
Station Mobile

The problem to be investigated in this research is that of predicting customers who are at risk of leaving the company, a term called churn prediction in telecommunication. The aim of this research is to predict customer churn and further focus on creating customer lifetime profiles. These profiles will allow the company to fit their customer base into n categories and make a long estimation on when a customer is potentially going to terminate their service with the company. The research then proceeds to provide a comparative analysis of neural networks and survival analysis in their capabilities of predicting customer churn and lifetime. . Key words: GSM networks, Base station, Mobile station, Signal strength, GSM service provider

scholarly journals Investigation of a New Handover Approach in LTE and WiMAX

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Mohammad Nour Hindia ◽  
Ahmed Wasif Reza ◽  
Kamarul Ariffin Noordin
Keyword(s):  
Mobile Station ◽  
Signal Strength ◽  
Received Signal Strength ◽  
Base Station ◽  
Multiple Criteria ◽  
Base Stations ◽  
Technology Selection ◽  
The Novel ◽  
Vertical Handovers ◽  
Minimum Number

Nowadays, one of the most important challenges in heterogeneous networks is the connection consistency between the mobile station and the base stations. Furthermore, along the roaming process between the mobile station and the base station, the system performance degrades significantly due to the interferences from neighboring base stations, handovers to inaccurate base station and inappropriate technology selection. In this paper, several algorithms are proposed to improve mobile station performance and seamless mobility across the long-term evolution (LTE) and Worldwide Interoperability for Microwave Access (WiMAX) technologies, along with a minimum number of redundant handovers. Firstly, the enhanced global positioning system (GPS) and the novel received signal strength (RSS) prediction approaches are suggested to predict the target base station accurately. Then, the multiple criteria with two thresholds algorithm is proposed to prioritize the selection between LTE and WiMAX as the target technology. In addition, this study also covers the intercell and cochannel interference reduction by adjusting the frequency reuse ratio 3 (FRR3) to work with LTE and WiMAX. The obtained results demonstrate high next base station prediction efficiency and high accuracy for both horizontal and vertical handovers. Moreover, the received signal strength is kept at levels higher than the threshold, while maintaining low connection cost and delay within acceptable levels. In order to highlight the combination of the proposed algorithms’ performance, it is compared with the existing RSS and multiple criteria handover decision algorithms.

CUSTOMER CHURN PREDICTION FOR FINTECH COMPANIES USING ARTIFICIAL NEURAL NETWORKS

2020 ◽  
Vol 7 (4) ◽  
pp. 46
Author(s):  
MALHOTRA POOJA ◽  
PATEL PUNIT ◽  
SHAH NEEL ◽  
VEERA RAJ ◽  
SANGHAVI RAJ ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Churn Prediction ◽  
Customer Churn ◽  
Customer Churn Prediction ◽  
Artificial Neural

Метод прогнозирования состояния радиоканала 4G и 5G

2019 ◽  
Author(s):  
A.V. Pestryakov ◽  
A.S. Konstantinov
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Comparative Analysis ◽  
Channel Model ◽  
Radio Channel ◽  
Learning Algorithms ◽  
Base Station ◽  
Coding Scheme ◽  
Lstm Network ◽  
Short Time

The paper presents a developed framework based on several neural networks for predicting the state of a radio channel in order to select the best modulation and coding scheme on the base station, taking into account the fading in the radio channel. Comparative analysis of the efficiency of modern architectures in the prediction of time series is carried out. Neural Long Short Time Memory (LSTM) network is defined as a framework core. The learning algorithms of the architectures under consideration are investigated. The choice of the radio channel model is justified. The framework efficiency is evaluated. Представлен разработанный на основе нескольких нейронных сетей фреймворк для прогнозирования состояния радиоканала с целью выбора наилучшей модуляционно-кодовой схемы на стороне базовой станции (с учетом замираний в нисходящей линии связи). Проведен сравнительный анализ эффективности современных архитектур при прогнозировании временных рядов и определена нейронная сеть LSTM в качестве ядра фреймворка. Исследованы алгоритмы обучения рассма- триваемых архитектур. Обоснован выбор модели радиоканала, параметров и проведена оценка эффективности фреймворка.

scholarly journals Customer Churn Prediction and Upselling using MRF (Modified Random Forest) technique

2020 ◽  
Vol 9 (3) ◽  
pp. 475-482
Keyword(s):  
Data Mining ◽  
Comparative Analysis ◽  
Random Forest ◽  
Prediction Model ◽  
Classification Accuracy ◽  
Churn Prediction ◽  
Customer Churn ◽  
Customer Churn Prediction ◽  
Telecom Industry ◽  
Fierce Competition

Customer Churn Prediction has become one of the eminent topic in the telecom industry, it has gained a lot of attention in the research industry due to fierce competition from the various, and hence companies have focused on the larger size of the data for churning and upselling prediction. The model of customer churn prediction detects and identify the customer who are willing to terminate the subscription, customer churn prediction and upselling can be done through the data mining process. Hence, In this paper we have introduce a model Named MRF(Modified Random Forest), this model helps in enhancing the accuracy and also helps in ignoring the regression issue. Our methodology has been performed on the provided orange Datasets. For the evaluation of our algorithm comparative analysis between the existing and proposed methodology is done considering the two scenario i.e. churn and upselling. Later our model is compared with the various existing churn prediction model, the result of the analysis indicates that our model outperforms the existing method including the standard random forest in terms of AUC and classification accuracy.

Customer Churn Prediction with Feature Embedded Convolutional Neural Network: An Empirical Study in the Internet Funds Industry

2019 ◽  
Vol 18 (01) ◽  
pp. 1950003 ◽  
Author(s):  
Chongren Wang ◽  
Dongmei Han ◽  
Weiguo Fan ◽  
Qigang Liu
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Demographic Data ◽  
Support Vector ◽  
The Internet ◽  
Churn Prediction ◽  
Operating Characteristics ◽  
Customer Churn ◽  
Static Data ◽  
Customer Churn Prediction

In this paper, we investigated the customer churn prediction problem in the Internet funds industry. We designed a novel feature embedded convolutional neural networks (FE-CNN) method that can automatically learn features from both the dynamic customer behavioral data and static customer demographic data and can utilize the advantage of convolutional neural networks to automatically learn features that capture the structured information. Our results show that our FE-CNN model outperforms the other traditional machine learning models with hand-crafted features, such as logistic regression (LR), support vector machines (SVM), random forests (RF) and neural networks (NN) in terms of accuracy, area under the receiver operating characteristics curve (AUC) and top-decile lift. Furthermore, we found that after adding the demographic data feature to the basic CNN model, the performance of the FE-CNN model improved. Overall, we found that the FE-CNN is the most powerful way to solve the problem of customer churn prediction in the Internet funds industry. Our FE-CNN method can also be applied to other fields that have both dynamic data and static data.

scholarly journals Deep Convolutional Neural Networks for Customer Churn Prediction Analysis

2020 ◽  
Vol 14 (1) ◽  
pp. 1-16
Author(s):  
Alae Chouiekh ◽  
El Hassane Ibn El Haj
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Support Vector ◽  
Use Case ◽  
Churn Prediction ◽  
Deep Convolutional Neural Networks ◽  
Customer Churn

Several machine learning models have been proposed to address customer churn problems. In this work, the authors used a novel method by applying deep convolutional neural networks on a labeled dataset of 18,000 prepaid subscribers to classify/identify customer churn. The learning technique was based on call detail records (CDR) describing customers activity during two-month traffic from a real telecommunication provider. The authors use this method to identify new business use case by considering each subscriber as a single input image describing the churning state. Different experiments were performed to evaluate the performance of the method. The authors found that deep convolutional neural networks (DCNN) outperformed other traditional machine learning algorithms (support vector machines, random forest, and gradient boosting classifier) with F1 score of 91%. Thus, the use of this approach can reduce the cost related to customer loss and fits better the churn prediction business use case.

scholarly journals Mobile 4G LTE Networks Mobility and Coverage for Some Locations in Ibadan Using Path Loss Analysis

2020 ◽  
Vol 26 (1) ◽  
pp. 7-22
Author(s):  
O.E. Ogunsola ◽  
◽  
O. Adeleke ◽  
O.I. Olaluwoye
Keyword(s):  
Service Provider ◽  
Service Providers ◽  
Mobile Station ◽  
Path Loss ◽  
Signal Strength ◽  
Base Station ◽  
Base Stations ◽  
Negative Consequences ◽  
Suburban Areas ◽  
Reference Distance

The recent migration of most GSM service providers’ networks in Ibadan from 3G to 4G, in preparation for the deployment of 5G technology in the nation necessitated the need to re-examine the GSM networks’ mobility and coverage within the micro cells in-between a Base Station and a Mobile Station. This attempt is aimed at using existing Path Loss Propagation Models in proffering solutions to the negative consequences usually associated with call drops in the Urban and Suburban Areas of Ibadan due to inability of channels to handover as a result of path loss. The path loss (dB) analysis was carried out by measuring the Received Signal Strength RSS (dBm) at distances ranging from 0.05 km to 4 km in-between Base Stations and Mobile Stations using the factory fitted installed RSS software on Android phones. These measurements were taken for three weeks within the urban and suburban areas of the University of Ibadan campus, and its neighborhood community of Agbowo for ten selected existing Base Stations from four of the nationwide GSM Service Providers (SP1, SP2, SP3 and SP4) in Nigeria. The variation of path loss with the RSS for GSM Service Provider (SP1) propagating at 955MHz (reference distance of 0.05km), 1850MHz and 2120MHz, were 66.03 dB, 71.77 dB and 72.96 dB, respectively. However, at 4 km the path loss had risen to 101.59dB for 955MHz, 103.81dB for 1850MHz and 105dB for 2120MHz. Also, the path loss for the GSM service provider (SP2) propagating at 960MHz (reference distance of 0.05km), 1865MHz and 2150MHz were 66.07 dB, 71.84 dB and 73.08 dB, respectively. Moreover, in a similar manner to the SP1 service provider, at 4 km the path loss had risen to 104.14dB for 960MHz, 109.9dB for 1865MHz and 111.14dB for 2150MHz. Furthermore, the path loss for the GSM service provider (SP3) propagating at 950MHz (reference distance of 0.05km), 1835MHz and 2130MHz were 65.98 dB, 71.70 dB and 73.00 dB, respectively. Likewise, as was in the case of the SP1 and SP2 Service providers, the path loss at 4 km had risen to 104.05dB for 950MHz, 109.76dB for 1835MHz and 111.06dB for 2130MHz. Also, the path loss for the GSM service provider (SP4) propagating at 940MHz (reference distance of 0.05km), 1880MHz and 2140MHz, were 65.47 dB, 71.46 dB and 72.23 dB, respectively. Moreover, the path loss at 4 km had risen to 103.53dB for 940MHz, 109.52dB for 1880MHz and 110.29dB for 2140 MHz as was the case with the other GSM Service providers (SP!, SP2 and SP3) considered .Thus, the path loss increases with distance within the microcells of base stations. However, the path loss model with minimum path loss (dB) at a given distance enhances good coverage and handover postponement. Moreover, the mean square error values used in obtaining the accuracy between the measured and the Empirical models were 17.15dB, 59.69dB, 48.46dB, 60.52dB and 40.07dB for the C-model, Cost-OH, Sub-O, Lee-model and experimental model, respectively. . Key words: GSM networks, Base station, Mobile station, Signal strength, GSM service provider

Sign in / Sign up

Export Citation Format

Share Document