PresentationPDF Available

Increasing Customer Retention using Big Data Customer Analytics

June 2018

Conference: Seminar - Recent Topics in Business Informatics, Otto-von-Guericke University Magdeburg
At: Magdeburg, Germany
Affiliation: Otto-von-Guericke-Universität Magdeburg

Authors:

Rutuja Shivraj Pawar

Otto-von-Guericke University Magdeburg

Data Analytics is the process of extracting meaningful patterns from a given dataset with the help of specialized tools and technologies. Customer Analytics is the process of leveraging data analytics to maximize organizational throughput and maintain a long-lasting relationship with its customers. In the era of Big Data, using customer analytics by an organization to obtain a 360-degree view of its customers helping to retain them with the business is the need of the hour. This presentation constituting a structured literature review provides valuable insights on how Big Data customer analytics can help business towards customer retention and eventually towards sustainable growth for the business.

Content uploaded by Rutuja Shivraj Pawar

Content may be subject to copyright.

The full-text slides can be found at https://easychair.org/smart-slide/slide/R476

ResearchGate has not been able to resolve any citations for this publication.

ResearchGate has not been able to resolve any references for this publication.

Conference Paper

A modified condensed nearest neighbour rule using the symbolicapproach

January 1994

The Condensed Nearest Neighbour (CNN) method chooses samples randomly. This results in: retention of unnecessary samples; occasional retention of internal rather than boundary samples. A modification of the CNN method is presented which will overcome these disadvantages by considering only points close to the decision boundary. This is achieved by making use of the symbolic approach. In ... [Show full abstract] conventional data analysis, the samples are described by feature vectors of numeric type. However, more generalised description of samples contain interval type of features and qualitative features. Such a description of samples constitute symbolic data. A modified new similarity measure which takes into consideration the position, span and content of symbolic objects is proposed. The similarity measure used is of new type. The modified similarity measure is used for obtaining the samples of the condensed set. The performance of the proposed modified CNN rule is illustrated by an example. The results obtained by the proposed method are an improvement over the other existing methods

Article

Learning Analytics: The Emperor’s New Clothes?

September 2017 · The Journal of Educational Innovation Partnership and Change

Sue Milward

Learning Analytics is promising to deliver the power of big data to Higher Education. By extracting meaning from the myriad of data held against a student, Learning Analytics promises to improve student retention and attainment. However, there are challenges to be overcome before the reality can live up to the promises.

Article

Full-text available

datasets on employee value proposition (evp) and performance of selected fast moving consumer goods...

June 2018 · Data in Brief

The article presented an integrated dataset on employee value proposition (EVP) and performance of selected Fast Moving Consumer Goods (FMCGs) firms in Nigeria. The study adopted quantitative approach with a descriptive research design to establish the major determinants of employee value proposition. The population of this study included staff and management of the selected firms. Data was ... [Show full abstract] analysed with the use of measurement and structural equation modelling and the field data set is made widely accessible to enable critical or a more comprehensive investigation. The findings identified career growth and reward flexibility as predictive determinants of EVP for increased performance of sampled firms. It was recommended that FCMGs firms need to adopt consistent range of strategies to improve company strength and ethical culture for performance to be heightened.

Article

Development of a Modified Capillary Pressure J-Function

March 1995

Noaman El-Khatib

Capillary pressure curves are represented by the equation Pc=a/ (Sw- Swi)b. It is shown that for the Leverett J-function to produce a single correlation, the tortuosity. the irreducible water saturation and the saturation exponent b must be the same for the different formations. A modified capillary pressure function J* is introduced that incorporates the tortuosity and irreducible water ... [Show full abstract] saturation in its definition. The modified function is correlated with the normalized saturation SD so that all curves will have their vertical asymptotes at a single point SD=0 The modified function represents a significant improvement over the original one since it is now sufficient to have the value of the saturation exponent b be the same for two samples to get the same correlation. This was verified by analyzing data from the literature and comparing the two correlations. A modified linear regression by means of weighted least squares method is used to fit the experimental capillary pressure data. Data sets from different sources were analyzed. It was found that a good single correlation can be obtained for samples from the same formation but the correlations were different for different formations. Introduction The capillary phenomena occurs in porous media when two or more immiscible fluids are present in the pore space. Due to the interfacial energy of the interface between the two phases. a difference in the pressure across the interface results and causes a curvature of the interface. The capillary forces causes retention of fluids in the pore space against the gravity forces. Immiscible fluids segregate due to gravity if placed in large containers such as tanks and pipes of large diameters. In porous rocks, however, the dense fluid (water) can be found at higher elevations above the oil-water contact. P. 547