Approximate Functional Dependency Mining with Sequential Indexing Tables

Functional Dependency extraction is a useful way to find inherent rules that apply in a given dataset. However, not all of such rules are exact, datasets comprised of real-world measurements can often contain rules that are supported by a significant portion of the dataset (so-called Approximate Functional Dependencies), with only a few exceptions. Extracting such rules is also very beneficial, e.g. for estimating the achievable classification precision on a dataset. Sequential Indexing Tables (SITs) are an extended version of Lookup Tables, in which multidimensional problem space is broken down to a sequence of 1D and 2D lookup tables, where each member of the sequence forms a layer and processes the values of one given attribute. In this paper, a SIT -based dependency extractor is proposed that can be used to extract Approximate Functional Dependencies from datasets.