This document discusses two data mining techniques: linear modelling using R and clustering using WEKA. For linear modelling in R, the author analyzes the relationship between bid-ask spread of a company's stock and price volatility. Clustering in WEKA is demonstrated by segmenting customers based on their shopping attitudes using k-means clustering. The author finds that bid-ask spread does not have a linear or logarithmic relationship with volatility based on their analysis in R.