This talk is for you if you would like to learn how to combine various independent data sets to allow for better segmentation of your market. Data has been the foundation of research for many years, but as of late a paradigm shift is taking place. Nowadays researchers and practitioners are utilizing various data for patterns and structures that result in new hypotheses. Corporates are benefiting from this shift as there are large amounts of internal and external data available from search engines, meteorological services, etc.

In this talk, we present a case study about Market Segmentation in the era of Big Data. The core question we tackle is: How can we efficiently build customer groups from large and complex time series data? To study this question, the talk comprises two aspects: First, we focus on how we integrate the third-party data into our analysis. In particular, we will explain the use of state holidays, temperature and search engine data. On the other hand, we review state-of-the-art models and algorithms for clustering. Lastly, we present a first dependence analysis using the copula approach and show that a clustering approach that models the dependence between the clusters is beneficial.