Data Mining

"The Forest or the Trees? Tackling Simpson's Paradox in Big Data with Trees" - at ECIS 2014

Earlier this month, Inbal Yahav (Bar Ilan University) and I presented our joint work on detecting Simpson's Paradox in big data as a poster at ECIS 2014 (thanks to the many interested visitors!), and at 2014 SCECR. This work describes an unusual use of classification and regression trees for a causal goal, rather than their normal use in prediction. We develop a tree variant that helps detect possible paradoxes in large datasets.

New student projects uploaded

Last term I instructed over 200 students in two courses: "Business Analytics Using Data Mining" and "Forecasting Analytics". In each of the courses, students worked in teams on a project using real data, formulating a business problem and addressing it with data mining and/or forecasting tools. I have posted the top projects in the Students Projects area of my website (look for the 2013 projects). For each project, I posted the team's presentation slides and report.

My new book "Getting Started with Business Analytics" now available

David Hardoon and I wanted a book that de-mystifies "business analytics". What it is, what it is not, how to get started, etc. David comes with the rich experience of heading the analytics division at SAS Singapore. I've been teaching and consulting in the field for quite a while. We've been asked these question so many times, that it made sense to write the book!

Introduction to Business Analytics (ISB, June 24, 2012)

What is Business Analytics and why does BA knowledge give an advantage in the marketplace? Our age of data means that firms and organisations collect growing amounts of micro-data about customers, transactions, outcomes, and more. Yet, most organizations are data rich but information poor. Business analytics is a set of approaches and techniques for extracting useful information from large amounts of existing data. Different from statistics, BA focuses on predictions of future outcomes at the micro-level.

Forecasting Analytics

Forecasting Analytics is a post-graduate business analytics elective course at ISB. Forecasting describes the act of generating predictions of future values or events. Quantitative forecasting, which focuses on data for generating numerical forecasts, is an important component of decision making in a wide range of areas and across many business functions, including economic forecasting, workload projections, sales forecasts and transportation demand.

Business Analytics Using Data Mining

Business Analytics using Data Mining (BADM, formerly BIDM)  is a post-graduate elective course @ISB. The course covers data mining techniques and their use in strategic business decision making. This is a hands-on course that provides an understanding of the key methods of data visualization, exploration, classification, prediction, and clustering.

Online course: "Forecasting"

I will be instructing an online course on Practical Time Series Forecasting, starting Mar 25, 2010.

The course covers popular statistical forecasting methods in business, as well as various issues that relate to the entire forecasting process, from goal definition and data collection to model deployment.


Subscribe to Data Mining