scholarly journals Case Studies in Applying Data Mining for Churn Analysis

2017 ◽  
Vol 5 (2) ◽  
pp. 22-33
Author(s):  
Susan Lomax ◽  
Sunil Vadera
Keyword(s):  
Data Mining ◽  
Decision Tree ◽  
Case Studies ◽  
Decision Tree Learning ◽  
Customer Churn ◽  
Use Of Data ◽  
Churn Analysis ◽  
First Case ◽  
Product Comparison

The advent of price and product comparison sites now makes it even more important to retain customers and identify those that might be at risk of leaving. The use of data mining methods has been widely advocated for predicting customer churn. This paper presents two case studies that utilize decision tree learning methods to develop models for predicting churn for a software company. The first case study aims to predict churn for organizations which currently have an ongoing project, to determine if organizations are likely to continue with other projects. While the second case study presents a more traditional example, where the aim is to predict organizations likely to cease being a subscriber to a service. The case studies include presentation of the accuracy of the models using a standard methodology as well as comparing the results with what happened in practice. Both case studies show the significant savings that can be made, plus potential increase in revenue by using decision tree learning for churn analysis.

scholarly journals PENERAPAN DATA MINING MENGGUNAKAN ALGORITMA C4.5 TEHADAP PENGARUH PENJUALAN KOPI PADA PT. JPW INDONESIA

2020 ◽  
Vol 3 (1) ◽  
pp. 40-54
Author(s):  
Ikong Ifongki
Keyword(s):  
Data Mining ◽  
Decision Tree ◽  
Decision Rules ◽  
Large Data ◽  
Added Value ◽  
Data Set ◽  
Use Of Data ◽  
Decision Tree Classification ◽  
C4.5 Algorithm

Data mining is a series of processes to explore the added value of a data set in the form of knowledge that has not been known manually. The use of data mining techniques is expected to provide knowledge - knowledge that was previously hidden in the data warehouse, so that it becomes valuable information. C4.5 algorithm is a decision tree classification algorithm that is widely used because it has the main advantages of other algorithms. The advantages of the C4.5 algorithm can produce decision trees that are easily interpreted, have an acceptable level of accuracy, are efficient in handling discrete type attributes and can handle discrete and numeric type attributes. The output of the C4.5 algorithm is a decision tree like other classification techniques, a decision tree is a structure that can be used to divide a large data set into smaller sets of records by applying a series of decision rules, with each series of division members of the resulting set become similar to each other. In this case study what is discussed is the effect of coffee sales by processing 106 data from 1087 coffee sales data at PT. JPW Indonesia. Data samples taken will be calculated manually using Microsoft Excel and Rapidminer software. The results of the calculation of the C4.5 algorithm method show that the Quantity and Price attributes greatly affect coffee sales so that sales at PT. JPW Indonesia is still often unstable.

Penerapan Metode Klasifikasi Decision Tree dan Algoritma C4.5 dalam Memprediksi Kriteria Nasabah Kredit Mega Auto Finance

2020 ◽  
Vol 7 (2) ◽  
pp. 200
Author(s):  
Puji Santoso ◽  
Rudy Setiawan
Keyword(s):  
Data Mining ◽  
Decision Tree ◽  
Microsoft Excel ◽  
Customer Data ◽  
Data Mining Techniques ◽  
C4.5 Algorithm ◽  
Marketing Costs ◽  
Excel Format ◽  
Data Mining Application

One of the tasks in the field of marketing finance is to analyze customer data to find out which customers have the potential to do credit again. The method used to analyze customer data is by classifying all customers who have completed their credit installments into marketing targets, so this method causes high operational marketing costs. Therefore this research was conducted to help solve the above problems by designing a data mining application that serves to predict the criteria of credit customers with the potential to lend (credit) to Mega Auto Finance. The Mega Auto finance Fund Section located in Kotim Regency is a place chosen by researchers as a case study, assuming the Mega Auto finance Fund Section has experienced the same problems as described above. Data mining techniques that are applied to the application built is a classification while the classification method used is the Decision Tree (decision tree). While the algorithm used as a decision tree forming algorithm is the C4.5 Algorithm. The data processed in this study is the installment data of Mega Auto finance loan customers in July 2018 in Microsoft Excel format. The results of this study are an application that can facilitate the Mega Auto finance Funds Section in obtaining credit marketing targets in the future

Investigating the potential of redundant manipulators in narrow channels

2020 ◽  
pp. 095440622096451
Author(s):  
Ashish Singla ◽  
Jyotindra Narayan ◽  
Himanshu Arora
Keyword(s):  
Case Studies ◽  
Fuzzy Inference ◽  
Redundant Manipulators ◽  
Redundancy Resolution ◽  
Inference System ◽  
Narrow Channels ◽  
First Case ◽  
Task Priority ◽  
Patient Side

In this paper, an attempt has been made to investigate the potential of redundant manipulators, while tracking trajectories in narrow channels. The behavior of redundant manipulators is important in many challenging applications like under-water welding in narrow tanks, checking the blockage in sewerage pipes, performing a laparoscopy operation etc. To demonstrate this snake-like behavior, redundancy resolution scheme is utilized using two different approaches. The first approach is based on the concept of task priority, where a given task is split and prioritize into several subtasks like singularity avoidance, obstacle avoidance, torque minimization, and position preference over orientation etc. The second approach is based on Adaptive Neuro Fuzzy Inference System (ANFIS), where the training is provided through given datasets and the results are back-propagated using augmentation of neural networks with fuzzy logics. Three case studies are considered in this work to demonstrate the redundancy resolution of serial manipulators. The first case study of 3-link manipulator is attempted with both the approaches, where the objective is to track the desired trajectory while avoiding multiple obstacles. The second case study of 7-link manipulator, tracking trajectory in a narrow channel, is investigated using the concept of task priority. The realistic application of minimum-invasive surgery (MIS) based trajectory tracking is considered as the third case study, which is attempted using ANFIS approach. The 5-link spatial redundant manipulator, also known as a patient-side manipulator being developed at CSIR-CSIO, Chandigarh is used to track the desired surgical cuts. Through the three case studies, it is well demonstrated that both the approaches are giving satisfactory results.

Fault Diagnosis of Automobile ECUs with Data Mining Technologies

2010 ◽  
Vol 40-41 ◽  
pp. 156-161 ◽  
Author(s):  
Yang Li ◽  
Yan Qiang Li ◽  
Zhi Xue Wang
Keyword(s):  
Data Mining ◽  
Fault Diagnosis ◽  
Decision Tree ◽  
Data Stream ◽  
Electronic Control Unit ◽  
Rapid Development ◽  
Reliability And Validity ◽  
Control Unit ◽  
Use Of Data ◽  
The Cost

With the rapid development of automotive ECUs(Electronic Control Unit), the fault diagnosis becomes increasingly complicated. And the link between fault and symptom becomes less obvious. In order to improve the maintenance quality and efficiency, the paper proposes a fault diagnosis approach based on data mining technologies. By making full use of data stream, we firstly extract fault symptom vectors by processing data stream, and then establish a diagnosis decision tree through the ID3 decision tree algorithm, and finally store the link rules between faults and the related symptoms into historical fault database as a foundation for the fault diagnosis. The database provides the basis of trend judgments for a future fault. To verify this approach, an example of diagnosing faults of entertainment ECU is showed. The test result testifies the reliability and validity of this diagnostic method and reduces the cost of ECU diagnosis.

Predicting customer churn in mobile industry using data mining technology

2017 ◽  
Vol 117 (1) ◽  
pp. 90-109 ◽  
Author(s):  
Eui-Bang Lee ◽  
Jinwha Kim ◽  
Sang-Gun Lee
Keyword(s):  
Data Mining ◽  
Decision Tree ◽  
Online News ◽  
Partial Least Square ◽  
Churn Prediction ◽  
Mining Technology ◽  
Content Type ◽  
Customer Churn ◽  
Mobile Industry ◽  
Using Data

Purpose The purpose of this paper is to identify the influence of the frequency of word exposure on online news based on the availability heuristic concept. So that this is different from most churn prediction studies that focus on subscriber data. Design/methodology/approach This study examined the churn prediction through words presented the previous studies and additionally identified words what churn generate using data mining technology in combination with logistic regression, decision tree graphing, neural network models, and a partial least square (PLS) model. Findings This study found prediction rates similar to those delivered by subscriber data-based analyses. In addition, because previous studies do not clearly suggest the effects of the factors, this study uses decision tree graphing and PLS modeling to identify which words deliver positive or negative influences. Originality/value These findings imply an expansion of churn prediction, advertising effect, and various psychological studies. It also proposes concrete ideas to advance the competitive advantage of companies, which not only helps corporate development, but also improves industry-wide efficiency.

scholarly journals Systemic Design: Two Canadian Case Studies

2014 ◽  
Vol 7 (3) ◽  
Author(s):  
Alex Ryan ◽  
Mark Leung
Keyword(s):  
Resource Management ◽  
Case Studies ◽  
Systems Thinking ◽  
Management System ◽  
Design Thinking ◽  
Clean Energy ◽  
Resource Management System ◽  
First Case ◽  
Systemic Design

This paper introduces two novel applications of systemic design to facilitate a comparison of alternative methodologies that integrate systems thinking and design. In the first case study, systemic design helped the Procurement Department at the University of Toronto re-envision how public policy is implemented and how value is created in the broader university purchasing ecosystem. This resulted in an estimated $1.5 million in savings in the first year, and a rise in user retention rates from 40% to 99%. In the second case study, systemic design helped the clean energy and natural resources group within the Government of Alberta to design a more efficient and effective resource management system and shift the way that natural resource departments work together. This resulted in the formation of a standing systemic design team and contributed to the creation of an integrated resource management system. A comparative analysis of the two projects identifies a shared set of core principles for systemic design as well as areas of differentiation that reveal potential for learning across methodologies. Together, these case studies demonstrate the complementarity of systems thinking and design thinking, and show how they may be integrated to guide positive change within complex sociotechnical systems.

scholarly journals Análise do banco de atendimentos da Defesa Civil do Estado de São Paulo

2010 ◽  
Vol 33 (1) ◽  
pp. 35-43
Author(s):  
Diego José Chagas ◽  
Chou Sin Chan ◽  
Alessandra Cristina Corsi
Keyword(s):  
Data Mining ◽  
Sao Paulo ◽  
Data Organization ◽  
São Paulo ◽  
Data Mining Technique ◽  
Landslide Occurrence ◽  
Serra Do Mar ◽  
Use Of Data ◽  
Relevant Factors

In recent years the simple data organization is no longer a differential factor for institutions, since, depending on their volume, the traditional method of analysis and interpretation is extremely slow and costly. The use of data mining techniques is an alternative to allow this process semi-automatic. The objective of this work is to carry out a case study of data mining technique based on the WEKA software applied to hydrometeorological and geomorphological data which were collected in the Serra do Mar region of São Paulo State. Results obtained from the application of the association technique indicate that the presence of rock and boulders at terrains with scars and high declivity are relevant factors for the landslide occurrence.

Sign in / Sign up

Export Citation Format

Share Document