Modelagem de probabilidade de churn

Clientes podem abandonar uma organização ainda que altos investimentos em prospecção e retenção sejam realizados, o que requer diagnóstico e compreensão. Este artigo objetiva modelar a probabilidade de clientes abandonarem o relacionamento com uma organização, fenômeno conhecido como churn, utilizando dados do histórico de relacionamento cliente/empresa, validar o modelo em uma segunda amostra e descrever as possíveis variáveis que influenciam o abandono/permanência do cliente. Utilizou-se o modelo de regressão logística em uma amostra de calibração de 70.000 clientes que possuíam cartão de crédito próprio de uma grande rede varejista. Dezesseis variáveis explicativas (14 características individuais e duas variáveis comportamentais) foram usadas e o modelo foi validado em uma amostra de 30.000 clientes, usando-se o teste de KS (Kolmogorov-Smirnov) e a curva ROC (Receiver Operating Characteristic), que demonstraram a boa adequação do modelo à amostra de validação. Implicações da pesquisa e sugestões para futuras investigações são discutidas à luz da gestão do relacionamento com o cliente.

Classificação de Churn no seguro automóvel.

Relatório de projecto apresentado como requisito parcial para obtenção do grau de mestre em Estatística e Gestão de Informação.

Understanding churn and its reasons: The GuestU case

In the age of computerisation, entrepreneurs around the world aim to revolutionise their field with ground-breaking ICTs. GuestU is one of those offering mobile application development to small and medium-sized tourism enterprises. To assure the young start-ups steady growth this paper aims to identify reasons for the high customer churn risk. Primary data is used to analyse end-user behaviour and particularly the success of acquisition and activation. Results show troubling download quantities as well as retention rates leading to the recommendations for GuestU to incentivise and guide their customers in increasing promotion for the applications.

Modelagem de churn a partir de registros de solicitações de reparo de clientes

O objetivo deste trabalho é criar um modelo que permita predizer quais clientes possuem tendência a abandonar a empresa (churn) através da base de dados de solicitações de reparo dos clientes de banda larga. Este tema ganha importância à medida que a concorrência neste mercado se acirra e novas tecnologias para acesso à banda larga são disponibilizadas aos clientes. Para este estudo foram utilizadas as bases de dados de solicitações de reparo e de solicitações de desligamento do serviço. O primeiro modelo criado utilizou as variáveis tempo até o reparo e a quantidade de solicitações de reparo. Na busca por um modelo com maior nível de acerto, foi criado um segundo modelo no qual se consideraram as variáveis motivo da reclamação e causa do defeito. O resultados do estudo indicam que as variáveis tempo até o reparo e quantidade de solicitações de reparo influenciam na taxa de solicitações de desligamento, assim como alguns motivos de solicitação de reparo e causa de defeito são mais relevantes para a decisão de desligamento. No entanto, o nível de acerto dos modelos criados é baixo. Portanto, a utilização destes modelos para identificação e abordagem de clientes propensos a solicitar desligamento implica em ajustes no nível de certeza do modelo e consequente redução na quantidade de clientes a serem abordados.

Social-analytics firms churn out world cup visuals

Three weeks into the world's most famous football tournament, you'd be forgiven for thinking those charts, maps and infographics you've been seeing everywhere were some kind of symptom of your World Cup fever. They are actually the result of a strategy shift by marketing teams in the social-media-measurement space, which have been investing more heavily in designers and content that can show off their products in a visual way.

Evaluation of flow patterns and elongated bubble characteristics during the flow boiling of halocarbon refrigerants in a micro-scale channel

In the present study, quasi-diabatic two-phase flow pattern visualizations and measurements of elongated bubble velocity, frequency and length were performed. The tests were run for R134a and R245fa evaporating in a stainless steel tube with diameter of 2.32 mm, mass velocities ranging from 50 to 600 kg/m(2) s and saturation temperatures of 22 degrees C, 31 degrees C and 41 degrees C. The tube was heated by applying a direct DC current to its surface. Images from a high-speed video-camera (8000 frames/s) obtained through a transparent tube just downstream the heated sections were used to identify the following flow patterns: bubbly, elongated bubbles, churn and annular flows. The visualized flow patterns were compared against the predictions provided by Barnea et al. (1983) [1], Felcar et al. (2007) [10], Revellin and Thome (2007) [3] and Ong and Thome (2009) [11]. From this comparison, it was found that the methods proposed by Felcar et al. (2007) [10] and Ong and Thome (2009) [1] predicted relatively well the present database. Additionally, elongated bubble velocities, frequencies and lengths were determined based on the analysis of high-speed videos. Results suggested that the elongated bubble velocity depends on mass velocity, vapor quality and saturation temperature. The bubble velocity increases with increasing mass velocity and vapor quality and decreases with increasing saturation temperature. Additionally, bubble velocity was correlated as linear functions of the two-phase superficial velocity. (C) 2010 Elsevier Inc. All rights reserved.

Void fraction measurement and signal analysis from multiple-electrode impedance sensors

Void fraction sensors are important instruments not only for monitoring two-phase flow, but for furnishing an important parameter for obtaining flow map pattern and two-phase flow heat transfer coefficient as well. This work presents the experimental results obtained with the analysis of two axially spaced multiple-electrode impedance sensors tested in an upward air-water two-phase flow in a vertical tube for void fraction measurements. An electronic circuit was developed for signal generation and post-treatment of each sensor signal. By phase shifting the electrodes supplying the signal, it was possible to establish a rotating electric field sweeping across the test section. The fundamental principle of using a multiple-electrode configuration is based on reducing signal sensitivity to the non-uniform cross-section void fraction distribution problem. Static calibration curves were obtained for both sensors, and dynamic signal analyses for bubbly, slug, and turbulent churn flows were carried out. Flow parameters such as Taylor bubble velocity and length were obtained by using cross-correlation techniques. As an application of the void fraction tested, vertical flow pattern identification could be established by using the probability density function technique for void fractions ranging from 0% to nearly 70%.

Um algoritmo de disseminação filtrada baseado em super nós e na redundância de filtros

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Management consulting labs: Project TAP

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Management from the NOVA – School of Business and Economics

Management consulting labs: Project TAP

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Management from the NOVA – School of Business and Economics

Customer Lifetime Value: a framework for application in the insurance industry - Building a Business Process to Generate and Maintain an Automatic Estimation Agent

Research Project submited as partial fulfilment for the Master Degree in Statistics and Information Management

Management consulting labs Galp loyalty

The main objective of this project was to investigate methods to create a new loyalty approach for Galp Energia in order to improve customer retention and reduce churn, related with the expansion of hypermarket chains’ in the Fuel Retail Market and the country’s economical situation. The team carried out on-spot surveys and focus groups, researched loyalty programs’ best practices, analyzed peers practices and the company’s past performance in order to find important customer insights. These were used to develop the final recommendations resulting in a new paradigm to the group’s loyalty approach alongside incremental improvements to the current loyalty solutions.

Characterization of the clients retention in the tlecommunications companies

The ability of a company to be able to do a precisely churn prediction, so it can act on it, is paramount. For this reason, Deloitte addressed me the challenge of characterizing the client’s retention in the telecom companies. To do so, it was created a comprehensive tool that enables Deloitte to evaluate the churn management maturity level of a telecom operator and highlight its strengths and weaknesses. The development of this matrix was based on a depth churn research, a market research based on 40 interviews and 2 focus group and the valuable feedback from Deloitte consultants.