The second case study addresses the problem of trying to build a stock trading
system based on prediction models obtained with daily stock quotes data. We
will apply different models to predict the returns of IBM stocks at the New York
Stock Exchange. These predictions will be used together with a trading rule
that will generate buy and sell signals. This chapter addresses several new data
mining issues: (1) how to use R to analyze data stored in a database; (2) how
to handle prediction problems where there is a time ordering among training
cases (usually known as a time series); (3) and the consequences of wanting to
translate model predictions into actions.