In this paper a new technique is presented for detecting multiple outliers in regression datasets using genetic algorithms. Each dataset contained known outliers and the genetic algorithm implementation was exceptionally accurate in detecting these outliers in all of the datasets tested.The genetic algorithm is an optimization technique based on various biological principles. It is capable of searching for global optima among a vast number of choices. By intelligent but somewhat random generation of subsets of data, potential sets of outliers are identified by minimizing the residual sum of squares produced by the least squares method. Relative improvements across the outlier sets are then analyzed to determine which sets are indeed outlying.

Neural networks can be used to fit complex models to high dimensional data. High dimensionality often obscures the fact that the model overfits the data and it often arises in the publication industry because we are usually interested in a large number of concepts; for example, a moderate thesaurus will contain thousands of concepts. In addition, the discovery of ideas, sentiments, tendencies, and context requires that our modelling algorithms be aware of many different features such as the words themselves, length of sentences (and paragraphs), word frequency counts, phrases, punctuation, number of references, and links. Overfitting can be counterbalanced by Regularization, but the latter can also cause problems. This paper attempts to clarify the concepts of "overfitting" and "regularization" using two-dimensional graphs that demonstrate over fitting and how regularization can force a smoother fit to noisy data.