Send Us an Email  |  Call Us (415) 904-4160
KXEN, An SAP Company

We've Revolutionized Predictive Analytics

Resource Library

Current View: Scientific Papers

Next Generation Tools for Business Analytics

Next Generation Tools for Business Analytics Scientific Papers

A common first reaction to KXEN’s approach to business analytics is, “That’s not how I was taught to do it!” KXEN’s approach is certainly different and as such, you might find it difficult to compare KXEN’s flagship product, InfiniteInsight® with other data mining tools. This document explains why we think our non-traditional approach to business analytics is growing in appeal and why automated predictive analytics is the way of the future.

This document is intended for anyone who thinks about how to apply data mining (i.e. both predictive and descriptive analytics) approaches to solving specific business problems, particularly within customer relationship management (CRM). It is also a useful tool for individuals who are evaluating Data Mining solutions and want to understand KXEN’s differentiators.

Download Resource »»

Industrial Mining of Massive Data Sets

Industrial Mining of Massive Data Sets Scientific Papers

Today, data mining is more and more extensively used by very competitive emprises. This development, brought by the increasing availability of massive data sets, is only possible if solutions to challenges, both theoretic and operational, are found: identify algorithms which can be used to produce models when datasets have thousands of variables and millions of observations; learn how to run and control the correct execution of hundreds of models; automate the data mining process. We will present these constraints in industrial contexts; we will show to exploit theoretical results (coming from Vladimir Vapnik's work) to produce robust models; we will give a few examples of real-life applications. We will thus demonstrate that it is indeed possible to industrialize data mining so as to turn it into an easy-to-use component whenever data is available.

Download Resource »»

Domain Driven Data Mining to Improve Promotional Campaign ROI and Select Marketing Channels

Domain Driven Data Mining to Improve Promotional Campaign ROI and Select Marketing Channels Scientific Papers

The trading activities of materials retail is concerned with an extremely competitive market. However, business people are not well informed about how to proceed and what to do during marketing activities. Data mining methods could be interesting to generate substantial profits for decision makers and to optimize the choice of different marketing activities. In this paper, we propose an actionable knowledge discovery methodology, for one-to-one marketing, which allows to contact the right customer through the right communication channel. This methodology first requires a measurement of the tendency for the customers to purchase a given item, and second requires an optimization of the Return On Investment by selecting the most effective communication channels for attracting these customers. Our methodology has been applied to the VM Mat´eriaux company. Thanks to the collaboration between data miners and decision makers, we present a domain-driven view of knowledge discovery satisfying real business needs to improve the efficiency and outcome of several promotional marketing campaigns.

Download Resource »»

Mining on Social Networks

Mining on Social Networks Scientific Papers

Data mining on networked data is a new area of research based on social network analysis techniques which has recently started to be used in industrial applications. In this article, we will describe some of the major social networks concepts. We will present KXEN's InfiniteInsight Social and show how it can be used for improving data mining models on networked data. We will then introduce a few applications in telecommunications, fraud and retail, where the use of social network analysis has brought significant improvements to data mining models.

Download Resource »»

Using Social Networks for Online Credit Card Fraud Analysis

Using Social Networks for Online Credit Card Fraud Analysis Scientific Papers

Internet sales are growing very fast, thus becoming a major target for fraudsters. This fraud is mostly perpetrated by international organized crime rings. Fighting fraud is thus critical for our socities' security. Classically, fraud detection has been implemented through data mining techniques; however, social network analysis techniques have recently emerged in the security domain. We present a methodology to use social networks together with data mining for fraud analysis and illustrate the approach through results recently obtained in an ongoing project, with transaction data provided by a major national network.

Download Resource »»

A Case Study in a Recommender System Based on Purchase Data

A Case Study in a Recommender System Based on Purchase Data Scientific Papers

Collaborative fitering has been extensively studied in the context of ratings prediction. However, industrial recommender systems often aim at predicting a few items of immediate interest to the user, typically products that (s)he is likely to buy in the near future. In a collaborative filtering setting, the prediction may be based on the user's purchase history rather than rating information, which may be unreliable or unavailable. In this paper, we present an experimental evaluation of various collaborative filtering algorithms on a real-world dataset of purchase history from customers in a store of a French home improvement and building supplies chain. These experiments are part of the development of a prototype recommender system for salespeople in the store. We show how di erent settings for training and applying the models, as well as the introduction of domain knowledge may dramatically influence both the absolute and the relative performances of the diff erent algorithms. To the best of our knowledge, the influence of these parameters on the quality of the predictions of recommender systems has rarely been reported in the literature.

Download Resource »»

Next Best Activity

Learn how to make every interaction the Next Best Action using best-in-class predictive analytics and business rules.

Hit the Jackpot

Learn how Tipp24, the lottery website is boosting targeting accuracy up to 300%.