Machine learning algorithms, applications, and practices in data science

Yeturu, Kalidas

doi:10.1016/bs.host.2020.01.002

Cited by 46 publications

(30 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Another approach to reducing computational time in classification is by using dimensionality reduction techniques. They can be built-in in the classification model (Kim & Shin, 2019) or used as a preprocessing step (Yeturu, 2020). Dimensionality reduction techniques may include feature selection, feature ranking, and principal component analysis (Yeturu, 2020).…”

Section: Discussionmentioning

confidence: 99%

“…They can be built-in in the classification model (Kim & Shin, 2019) or used as a preprocessing step (Yeturu, 2020). Dimensionality reduction techniques may include feature selection, feature ranking, and principal component analysis (Yeturu, 2020). These methods aim to choose the features that carry the most important information for the prediction.…”

Section: Discussionmentioning

confidence: 99%

“…Therefore, a subset of the independent variables is produced that is later used in classification. With the reduction of features, the classification model becomes less computationally expensive (Yeturu, 2020). However, the focus of this approach is not to reduce computational time but rather to improve the classification metrics like accuracy.…”

Section: Discussionmentioning

confidence: 99%

“…al., 2013). However, this approach is not widely used for reducing computational time as it has become a standard step in the building of a classification model (Yeturu, 2020). As Wong (2015) and machine learning textbooks (Yeturu, 2020), (James et.…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

The Proportion for Splitting Data into Training and Test Set for the Bootstrap in Classification Problems

Vrigazova

2021

Business Systems Research Journal

View full text Add to dashboard Cite

Background: The bootstrap can be alternative to cross-validation as a training/test set splitting method since it minimizes the computing time in classification problems in comparison to the tenfold cross-validation. Objectives: Тhis research investigates what proportion should be used to split the dataset into the training and the testing set so that the bootstrap might be competitive in terms of accuracy to other resampling methods. Methods/Approach: Different train/test split proportions are used with the following resampling methods: the bootstrap, the leave-one-out cross-validation, the tenfold cross-validation, and the random repeated train/test split to test their performance on several classification methods. The classification methods used include the logistic regression, the decision tree, and the k-nearest neighbours. Results: The findings suggest that using a different structure of the test set (e.g. 30/70, 20/80) can further optimize the performance of the bootstrap when applied to the logistic regression and the decision tree. For the k-nearest neighbour, the tenfold cross-validation with a 70/30 train/test splitting ratio is recommended. Conclusions: Depending on the characteristics and the preliminary transformations of the variables, the bootstrap can improve the accuracy of the classification problem.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

The Proportion for Splitting Data into Training and Test Set for the Bootstrap in Classification Problems

Vrigazova

2021

Business Systems Research Journal

View full text Add to dashboard Cite

show abstract

“…Each color corresponds to a grammatical category of the mentions. Within each graph, the different chains are sorted according to their similarity, by using the multidimentional scaling (Popper and Heymann, 1996;Yeturu, 2020), in order to better visualize the heterogeneity of the classes.…”

Section: Description Of the Clustersmentioning

confidence: 99%

Coreference Chains Categorization by Sequence Clustering

Federzoni¹,

Ho-Dac²,

Fabre³

2021

Proceedings of the 2nd Workshop on Computational Approaches to Discourse

View full text Add to dashboard Cite

The diversity of coreference chains is usually tackled by means of global features (length, types and number of referring expressions, distance between them, etc.). In this paper, we propose a novel approach that provides a description of their composition in terms of sequences of expressions. To this end, we apply sequence analysis techniques to bring out the various strategies for introducing a referent and keeping it active throughout discourse. We discuss a first application of this method to a French written corpus annotated with coreference chains. We obtain clusters that are linguistically coherent and interpretable in terms of reference strategies and we demonstrate the influence of text genre and semantic type of the referent on chain composition.

show abstract

Government Public Services Presence Index Based on Open Data

Núñez-del-Prado

Rojas-Bustamante

2022

Information Management and Big Data

View full text Add to dashboard Cite

Machine learning algorithms, applications, and practices in data science

Cited by 46 publications

References 36 publications

The Proportion for Splitting Data into Training and Test Set for the Bootstrap in Classification Problems

The Proportion for Splitting Data into Training and Test Set for the Bootstrap in Classification Problems

Coreference Chains Categorization by Sequence Clustering

Government Public Services Presence Index Based on Open Data

Contact Info

Product

Resources

About