Data Preparation for Data Mining

By Dorian Pyle. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Benchmark and Survey of Automated Machine Learning Frameworks (2019, background): “By building good features, the performance of an ML pipeline can be increased many times over (Pyle, 1999).”
Survey on Automated Machine Learning (2019, background): “By building good features, the performance of an ML pipeline can be increased many times over (Pyle, 1999).”
Predictive data mining in clinical medicine: Current issues and guidelines (2008, background): “Currently, the most widely used data mining algorithms require data to be placed in a tabular form that includes predictive factors and outcomes and is constructed by querying single or several dedicated databases [91].”
Toward integrating feature selection algorithms for classification and clustering (2005, background): “Researchers and practitioners realize that in order to use data mining tools effectively, data preprocessing is essential to successful data mining [53], [74].”
Exploratory Data Mining and Data Cleaning (2003, background): “The most closely related book is Pyle [102], which discusses data preparation for data mining.”
Mortality assessment in intensive care units via adverse events using artificial neural networks (2006, methodology): “In addition, four entries were removed due to the presence of missing values [ 17 ], remaining a total of 13164 records.”
Predicting academic success in higher education: literature review and best practices (2020, methodology): “Also, it is worth noticing that models obtained from a reduced number of features will be easier to understand (Pyle et al., 1999).”
Big data preprocessing: methods and prospects (2016, background): “It is well-known that low quality data will lead to low quality knowledge [15].”
A Survey on Evolutionary Instance Selection and Generation (2010, methodology): “Data reduction (Pyle, 1999) is one of the data preprocessing tasks which can be applied in a data mining process.”
Leakage in data mining: formulation, detection, and avoidance (2011, background): “Pyle [9, 10, 11] refers to the phenomenon which we call here leakage, in the context of predictive modeling, as Anachronisms (something that is out of place in time), and says that "too good to be true" performance is "a dead giveaway" of its existence.”
Opcode sequences as representation of executables for data-mining-based unknown malware detection (2013, methodology): “In order to solve this issue, data reduction is normally considered an appropriate preprocessing optimisation technique [59, 78].”
Supervised Machine Learning: A Review of Classification Techniques (2007, unknown): “It contains in most cases noise and missing feature values, and therefore requires significant pre-processing (Zhang et al., 2002).”
A survey on data preprocessing for data stream mining: Current status and future directions (2017, background): “Despite being less known than other steps like data mining, data preprocessing actually very often involves more effort and time within the entire data analysis process (> 50% of total effort) [3].”
Open challenges for data stream mining research (2014, background): “[33]; however, the data stream setting introduces new challenges that have not received sufficient research attention yet.”
Dimensionality reduction based on rough set theory: A review (2009, background): “However, 5–15% must be handled by complicated methods, and more than 15% may severely impact any kind of interpretation [82].”
Clustering of the self-organizing map (2000, background): “Finally, the whole mining process is meaningless if the new knowledge will not be used [1].”
A survey of evolutionary algorithms for data mining and knowledge discovery (2003, methodology): “We use the term data preprocessing in a general sense, including the following steps (among others) [55]: (a) Data Integration - This is necessary if the data to be mined comes from several different sources, such as several departments of an organization.”
Characteristic-Based Clustering for Time Series Data (2006, unknown): “Using anything less than the most convenient methods hardly contributes to easy and efficient completion of a task (Pyle, 1999).”
Data Matching (2012, background): “Outliers can affect the results of data clustering, while missing values can lead to biased classification results or frequent patterns that include missing values and that therefore are not practically useful [135, 218].”