scholarly journals A Customer Churn Detection Model for the Pay-TV Sector

2021 ◽  
Author(s):  
Vicente López ◽  
Rebeca Egea ◽  
Lledó Museros ◽  
Ismael Sanz
Keyword(s):  
Business Environment ◽  
Data Set ◽  
Detection Model ◽  
Customer Churn ◽  
Telecommunication Companies ◽  
Pay Tv ◽  
The Cost

The business environment today is characterized by high competition and saturated markets. Pay-tv platforms there are not an exception. Because of that, the cost to acquire new customers is much higher than the cost of retaining the existing customers. Therefore, it is important for Pay-TV platforms to keep controlled the Customer Churn. Therefore, the paper studies existing models used to predict Customer Churn in other context -like telecommunication companies customer Churn-and adapts them to the Pay-TV context. Another big problem faced in the paper is the fact that, in the data set udes in the paper there are not personal metrics, which are indispensables to solve the problem. Therefore this approach has defined new metrics in order to be able to predict customer churn.

scholarly journals Telecom Churn Prediction System Based on Ensemble Learning Using Feature Grouping

2021 ◽  
Vol 11 (11) ◽  
pp. 4742
Author(s):  
Tianpei Xu ◽  
Ying Ma ◽  
Kangchul Kim
Keyword(s):  
Ensemble Learning ◽  
Machine Learning Algorithms ◽  
Customer Relationship ◽  
Prediction System ◽  
Churn Prediction ◽  
Customer Churn ◽  
Feature Grouping ◽  
Recognition Systems ◽  
The Cost ◽  
Better Than

In recent years, the telecom market has been very competitive. The cost of retaining existing telecom customers is lower than attracting new customers. It is necessary for a telecom company to understand customer churn through customer relationship management (CRM). Therefore, CRM analyzers are required to predict which customers will churn. This study proposes a customer-churn prediction system that uses an ensemble-learning technique consisting of stacking models and soft voting. Xgboost, Logistic regression, Decision tree, and Naïve Bayes machine-learning algorithms are selected to build a stacking model with two levels, and the three outputs of the second level are used for soft voting. Feature construction of the churn dataset includes equidistant grouping of customer behavior features to expand the space of features and discover latent information from the churn dataset. The original and new churn datasets are analyzed in the stacking ensemble model with four evaluation metrics. The experimental results show that the proposed customer churn predictions have accuracies of 96.12% and 98.09% for the original and new churn datasets, respectively. These results are better than state-of-the-art churn recognition systems.

scholarly journals Aggregation of cohorts for histopathological diagnosis with deep morphological analysis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jeonghyuk Park ◽  
Yul Ri Chung ◽  
Seo Taek Kong ◽  
Yeong Won Kim ◽  
Hyunho Park ◽  
...  
Keyword(s):  
Cancer Detection ◽  
Morphological Analysis ◽  
Deep Neural Networks ◽  
Large Datasets ◽  
Histopathological Diagnosis ◽  
Single Model ◽  
Trade Off ◽  
Detection Model ◽  
Optimal Behavior ◽  
The Cost

AbstractThere have been substantial efforts in using deep learning (DL) to diagnose cancer from digital images of pathology slides. Existing algorithms typically operate by training deep neural networks either specialized in specific cohorts or an aggregate of all cohorts when there are only a few images available for the target cohort. A trade-off between decreasing the number of models and their cancer detection performance was evident in our experiments with The Cancer Genomic Atlas dataset, with the former approach achieving higher performance at the cost of having to acquire large datasets from the cohort of interest. Constructing annotated datasets for individual cohorts is extremely time-consuming, with the acquisition cost of such datasets growing linearly with the number of cohorts. Another issue associated with developing cohort-specific models is the difficulty of maintenance: all cohort-specific models may need to be adjusted when a new DL algorithm is to be used, where training even a single model may require a non-negligible amount of computation, or when more data is added to some cohorts. In resolving the sub-optimal behavior of a universal cancer detection model trained on an aggregate of cohorts, we investigated how cohorts can be grouped to augment a dataset without increasing the number of models linearly with the number of cohorts. This study introduces several metrics which measure the morphological similarities between cohort pairs and demonstrates how the metrics can be used to control the trade-off between performance and the number of models.

The Optimal Diversification Strategy in Pharmaceutical Industry: Balance-centred or Hetero-centred?

2021 ◽  
pp. 097172182110056
Author(s):  
Keungoui Kim ◽  
Junseok Hwang ◽  
Sungdo Jung ◽  
Eungdo Kim
Keyword(s):  
Business Performance ◽  
Business Environment ◽  
Product Diversification ◽  
Diversification Strategy ◽  
Firm Level ◽  
Data Set ◽  
Pharmaceutical Firms ◽  
Level Data ◽  
Market Product ◽  
High Uncertainty

Due to high uncertainty of product development and business environment, firm-level diversification has been regarded as one of the most effective methods in pharmaceutical firms. In previous study, firm-level diversification was discussed by different value chains of market, product, and technology. However, in most cases, the diversification itself was adopted in a simple manner although its property contains different aspects and the results varies depending on the diversity property of selected index. In addition, the existing approach for measuring firm’s product/market diversification using sales information distinguished by standard industry classification cannot provide direct implication as different strategies are made for market and product diversification. Therefore, this study examines the effects of firm-level diversification on business and innovation performances in pharmaceutical firms by considering (1) three diversification types: market, product, and technology, (2) clear separation between market and product diversification, and (3) two diversification perspectives: balance-centred and hetero-centred. For empirical analysis, an integrated firm-level data set combining from Medtrack, Orange Book, Compustat and Total Patent database is used. From the result, in case of market diversification, less market heterogeneity causes significant influence on business performance. For product and technology, a concentrated and greater heterogeneity of product diversification are turned out to promote business performance, while the more intensive and heterogeneous technology diversification has been shown to improve innovation performance.

Demographic life history traits of reproductive natterjack toads (Bufo calamita) vary between northern and southern latitudes

2006 ◽  
Vol 27 (3) ◽  
pp. 365-375 ◽  
Author(s):  
Delfi Sanuy ◽  
Christoph Leskovar ◽  
Neus Oromi ◽  
Ulrich Sinsch
Keyword(s):  
Life History ◽  
Life History Traits ◽  
Large Female ◽  
Breeding Period ◽  
Female Size ◽  
Data Set ◽  
Bufo Calamita ◽  
Trade Offs ◽  
Age Variation ◽  
The Cost

AbstractDemographic life history traits were investigated in three Bufo calamita populations in Germany (Rhineland-Palatinate: Urmitz, 50°N; 1998-2000) and Spain (Catalonia: Balaguer, Mas de Melons, 41°N; 2004). We used skeletochronology to estimate the age as number of lines of arrested growth in breeding adults collected during the spring breeding period (all localities) and during the summer breeding period (only Urmitz). A data set including the variables sex, age and size of 185 males and of 87 females was analyzed with respect to seven life history traits (age and size at maturity of the youngest first breeders, age variation in first breeders, longevity, potential reproductive lifespan, median lifespan, age-size relationship). Spring and summer cohorts at the German locality differed with respect to longevity and potential reproductive lifespan by one year in favour of the early breeders. The potential consequences on fitness and stability of cohorts are discussed. Latitudinal variation of life history traits was mainly limited to female natterjacks in which along a south-north gradient longevity and potential reproductive lifespan increased while size decreased. These results and a review of published information on natterjack demography suggest that lifetime number of offspring seem to be optimized by locally different trade-offs: large female size at the cost of longevity in southern populations and increased longevity at the cost of size in northern ones.

Cost effectiveness in palliative care setting

2018 ◽  
Vol 21 (2) ◽  
pp. 62-71
Author(s):  
Henry O’Lawrence ◽  
Rohan Chowlkar
Keyword(s):  
Quality Of Life ◽  
Palliative Care ◽  
End Of Life ◽  
Hospice Care ◽  
Home Health ◽  
Data Set ◽  
Content Type ◽  
Care Services ◽  
The Cost

Purpose The purpose of this paper is to determine the cost effectiveness of palliative care on patients in a home health and hospice setting. Secondary data set was utilized to test the hypotheses of this study. Home health care and hospice care services have the potential to avert hospital admissions in patients requiring palliative care, which significantly affects medicare spending. With the aging population, it has become evident that demand of palliative care will increase four-fold. It was determined that current spending on end-of-life care is radically emptying medicare funds and fiscally weakening numerous families who have patients under palliative care during life-threatening illnesses. The study found that a majority of people registering for palliative and hospice care settings are above the age group of 55 years old. Design/methodology/approach Different variables like length of stay, mode of payment and disease diagnosis were used to filter the available data set. Secondary data were utilized to test the hypothesis of this study. There are very few studies on hospice and palliative care services and no study focuses on the cost associated with this care. Since a very large number of the USA, population is turning 65 and over, it is very important to analyze the cost of care for palliative and hospice care. For the purpose of this analysis, data were utilized from the National Home and Hospice Care Survey (NHHCS), which has been conducted periodically by the Centers for Disease Control and Prevention’s National Center for Health Statistics. Descriptive statistics, χ2 tests and t-tests were used to test for statistical significance at the p<0.05 level. Findings The Statistical Package for Social Sciences (SPSS) was utilized for this result. H1 predicted that patients in the age group of 65 years and up have the highest utilization of home and hospice care. This study examined various demographic variables in hospice and home health care which may help to evaluate the cost of care and the modes of payments. This section of the result presents the descriptive analysis of dependent, independent and covariate variables that provide the overall national estimates on differences in use of home and hospice care in various age groups and sex. Research limitations/implications The data set used was from the 2007 NHHCS survey, no data have been collected thereafter, and therefore, gap in data analysis may give inaccurate findings. To compensate for this gap in the data set, recent studies were reviewed which analyzed cost in palliative care in the USA. There has been a lack of evidence to prove the cost savings and improved quality of life in palliative/hospice care. There is a need for new research on the various cost factors affecting palliative care services as well as considering the quality of life. Although, it is evident that palliative care treatment is less expensive as compared to the regular care, since it eliminates the direct hospitalization cost, but there is inadequate research to prove that it improves the quality of life. A detailed research is required considering the additional cost incurred in palliative/hospice care services and a cost-benefit analysis of the same. Practical implications While various studies reporting information applicable to the expenses and effect of family caregiving toward the end-of-life were distinguished, none of the previous research discussed this issue as their central focus. Most studies addressed more extensive financial effect of palliative and end-of-life care, including expenses borne by the patients themselves, the medicinal services framework and safety net providers or beneficent/willful suppliers. This shows a significant hole in the current writing. Social implications With the aging population, it has become evident that demand of palliative/hospice care will increase four-fold. The NHHCS have stopped keeping track of the palliative care requirements after 2007, which has a negative impact on the growing needs. Cost analysis can only be performed by analyzing existing data. This review has recognized a huge niche in the evidence base with respect to the cost cares of giving care and supporting a relative inside a palliative/hospice care setting. Originality/value The study exhibited that cost diminishments in aggressive medications can take care of the expenses of palliative/hospice care services. The issue of evaluating result in such a physically measurable way is complicated by the impalpable nature of large portions of the individual components of outcome. Although physical and mental well-being can be evaluated to a certain degree, it is significantly more difficult to gauge in a quantifiable way, the social and profound measurements of care that help fundamentally to general quality of care.

scholarly journals Farm Gate Prices for Non-Varietal Wine in Argentina: A Multilevel Comparison of the Prices Paid by Cooperatives and Investor-Oriented Firms

2017 ◽  
Vol 16 (1) ◽  
Author(s):  
Agustina Malvido Perez Carletti ◽  
Markus Hanisch ◽  
Jens Rommel ◽  
Murray Fulton
Keyword(s):  
Multilevel Regression ◽  
Data Set ◽  
Unique Data ◽  
Market Shares ◽  
Price Effects ◽  
Theoretical Predictions ◽  
The One ◽  
The Cost ◽  
Price Differences ◽  
Multilevel Regression Model

AbstractIn this paper, we use a unique data set of the prices paid to farmers in Argentina for grapes to examine the prices paid by non-varietal wine processing cooperatives and investor-oriented firms (IOFs). Motivated by contrasting theoretical predictions of cooperative price effects generated by the yardstick of competition and property rights theories, we apply a multilevel regression model to identify price differences at the transaction level and the departmental level. On average, farmers selling to cooperatives receive a 3.4 % lower price than farmers selling to IOFs. However, we find cooperatives pay approximately 2.4 % more in departments where cooperatives have larger market shares. We suggest that the inability of cooperatives to pay a price equal to or greater than the one paid by IOFs can be explained by the market structure for non-varietal wine in Argentina. Specifically, there is evidence that cooperative members differ from other farmers in terms of size, assets and the cost of accessing the market. We conclude that the analysis of cooperative pricing cannot solely focus on the price differential between cooperatives and IOFs, but instead must consider other factors that are important to the members.

Towards a framework for measuring creative economy: evidence from Balkan countries

2019 ◽  
Vol 23 (1) ◽  
pp. 41-62 ◽  
Author(s):  
Valentina Ndou ◽  
Giovanni Schiuma ◽  
Giuseppina Passiante
Keyword(s):  
Business Environment ◽  
Creative Economy ◽  
Data Set ◽  
Content Type ◽  
Balkan Countries ◽  
World Economic ◽  
And Performance ◽  
Diverse Data ◽  
The Relationship ◽  
Performance Dimension

PurposeThe creative process through which the territorial resources, knowledge and culture are used, exploited and configured to match needs and to achieve congruence with the changing business environment has become a crucial process for competitiveness. This is even more relevant for economies of developing countries which are continuously struggling to reap the benefits of globalisation, as well as to grasp the new opportunities for competitiveness. As such, this paper aims to try to concentrate on the dynamic perspectives of the creative economy of countries by distinguishing between the potentialities and performance. The paper tackles the influence that creativity capacities might have on performance of countries.Design/methodology/approachThe methodology consists in identifying creative economy indicators from a diverse data set of the World Economic Forum and distinguish them between potential and performance indicators.FindingsData reveal as good progress and emphasis is being devoted to increasing the level of creativity; however, the Balkan countries still holdup in their capacity to boost innovation.Practical implicationsThe paper provide a new focus of research on creativity measurement that is significant for understanding what creative capacities territories possess and the ability to make proficient use for growth and innovation.Originality/valueThis paper proposes a new operational framework for measuring and interpreting the creative economy indicators by identifying not only indicators that gauge the potentialities of a country, but also indicators that are linked with the performance dimension, as well as the relationship amongst them.

scholarly journals Availability analysis of selected mining machinery

2017 ◽  
Vol 27 (2) ◽  
pp. 197-209 ◽  
Author(s):  
Jarosław Brodny ◽  
Sara Alszer ◽  
Jolanta Krystek ◽  
Magdalena Tutak
Keyword(s):  
Process Mining ◽  
Underground Mining ◽  
Automation System ◽  
Data Set ◽  
Availability Analysis ◽  
Geological Conditions ◽  
Mining Machinery ◽  
Coal Market ◽  
The Cost ◽  
Source Of Information

Abstract Underground extraction of coal is characterized by high variability of mining and geological conditions in which it is conducted. Despite ever more effective methods and tools, used to identify the factors influencing this process, mining machinery, used in mining underground, work in difficult and not always foreseeable conditions, which means that these machines should be very universal and reliable. Additionally, a big competition, occurring on the coal market, causes that it is necessary to take action in order to reduce the cost of its production, e.g. by increasing the efficiency of utilization machines. To meet this objective it should be pro-ceed with analysis presented in this paper. The analysis concerns to availability of utilization selected mining machinery, conducted using the model of OEE, which is a tool for quantitative estimate strategy TPM. In this article we considered the machines being part of the mechanized longwall complex and the basis of analysis was the data recording by the industrial automation system. Using this data set we evaluated the availability of studied machines and the structure of registered breaks in their work. The results should be an important source of information for maintenance staff and management of mining plants, needed to improve the economic efficiency of underground mining.

scholarly journals Embedding Undersampling Rotation Forest for Imbalanced Problem

2018 ◽  
Vol 2018 ◽  
pp. 1-15 ◽  
Author(s):  
Huaping Guo ◽  
Xiaoyu Diao ◽  
Hongbing Liu
Keyword(s):  
Imbalanced Data ◽  
Feature Space ◽  
Original Data ◽  
Training Set ◽  
Data Set ◽  
Minority Class ◽  
Rotation Forest ◽  
Novel Method ◽  
Individual Classifier ◽  
The Cost

Rotation Forest is an ensemble learning approach achieving better performance comparing to Bagging and Boosting through building accurate and diverse classifiers using rotated feature space. However, like other conventional classifiers, Rotation Forest does not work well on the imbalanced data which are characterized as having much less examples of one class (minority class) than the other (majority class), and the cost of misclassifying minority class examples is often much more expensive than the contrary cases. This paper proposes a novel method called Embedding Undersampling Rotation Forest (EURF) to handle this problem (1) sampling subsets from the majority class and learning a projection matrix from each subset and (2) obtaining training sets by projecting re-undersampling subsets of the original data set to new spaces defined by the matrices and constructing an individual classifier from each training set. For the first method, undersampling is to force the rotation matrix to better capture the features of the minority class without harming the diversity between individual classifiers. With respect to the second method, the undersampling technique aims to improve the performance of individual classifiers on the minority class. The experimental results show that EURF achieves significantly better performance comparing to other state-of-the-art methods.

scholarly journals Key Parts of Transmission Line Detection Using Improved YOLO v3

2021 ◽  
Vol 18 (6) ◽  
Author(s):  
Tu Renwei ◽  
Zhu Zhongjie ◽  
Bai Yongqiang ◽  
Gao Ming ◽  
Ge Zhifeng
Keyword(s):  
Transmission Line ◽  
Detection Accuracy ◽  
Data Sets ◽  
Feature Maps ◽  
Data Set ◽  
Detection Model ◽  
The Neural Network ◽  
Low Efficiency ◽  
The One ◽  
Detection Speed

Unmanned Aerial Vehicle (UAV) inspection has become one of main methods for current transmission line inspection, but there are still some shortcomings such as slow detection speed, low efficiency, and inability for low light environment. To address these issues, this paper proposes a deep learning detection model based on You Only Look Once (YOLO) v3. On the one hand, the neural network structure is simplified, that is the three feature maps of YOLO v3 are pruned into two to meet specific detection requirements. Meanwhile, the K-means++ clustering method is used to calculate the anchor value of the data set to improve the detection accuracy. On the other hand, 1000 sets of power tower and insulator data sets are collected, which are inverted and scaled to expand the data set, and are fully optimized by adding different illumination and viewing angles. The experimental results show that this model using improved YOLO v3 can effectively improve the detection accuracy by 6.0%, flops by 8.4%, and the detection speed by about 6.0%.

Sign in / Sign up

Export Citation Format

Share Document