Data Farming Methods for Temporal Data Mining

Many temporal data mining projects use the existing data collected for various purposes, ranging from routinely collected data to process improvement projects and data required for regulatory purposes. In some cases, the set of considered features might be large (a wide data set) and sufficient for extraction of knowledge. In other cases the data set might be narrow and insufficient to extract meaningful knowledge or the data may not even exist. Mining wide data sets has received wide attention in the literature. Many models and algorithms for feature selection have been developed for wide data sets. Determining features for which data should be collected in the absence of an existing data set or its partial availability (a narrow set) has not been sufficiently addressed in the literature, especially for temporal data. Yet, this issue is of paramount importance as the interest in data mining is growing. The process and methods used to determine the most appropriate features for data collection and subsequent data analysis are referred to as data farming. This paper provides a foundation for the development of data farming science for temporal analysis of data.