@techreport{ChandrasekaranZaeffererMoritzetal., type = {Working Paper}, author = {Sowmya Chandrasekaran and Martin Zaefferer and Steffen Moritz and J{\"o}rg Stork and Martina Friese and Andreas Fischbach and Thomas Bartz-Beielstein}, title = {Data Preprocessing: A New Algorithm for Univariate Imputation Designed Specifically for Industrial Needs}, url = {https://nbn-resolving.org/urn:nbn:de:hbz:832-cos4-4331}, pages = {24}, abstract = {Data pre-processing is a key research topic in data mining because it plays a crucial role in improving the accuracy of any data mining algorithm. In most real world cases, a significant amount of the recorded data is found missing due to most diverse errors. This loss of data is nearly always unavoidable. Recovery of missing data plays a vital role in avoiding inaccurate data mining decisions. Most multivariate imputation methods are not compatible to univariate datasets and the traditional univariate imputation techniques become highly biased as the missing data gap increases. With the current technological advancements abundant data is being captured every second. Hence, we intend to develop a new algorithm that enables maximum utilization of the available big datasets for imputation. In this paper, we present a Seasonal and Trend decomposition using Loess (STL) based Seasonal Moving Window Algorithm, which is capable of handling patterns with trend as well as cyclic characteristics. We show that the algorithm is highly suitable for pre-processing of large datasets.}, language = {en} }