references.bib

@article{Benavoli2017,
  author  = {Alessio Benavoli and Giorgio Corani and Janez Dem{\v{s}}ar and Marco Zaffalon},
  title   = {Time for a Change: a Tutorial for Comparing Multiple Classifiers Through Bayesian Analysis},
  journal = {Journal of Machine Learning Research},
  year    = {2017},
  volume  = {18},
  number  = {77},
  pages   = {1--36},
  url     = {http://jmlr.org/papers/v18/16-305.html}
}

@ARTICLE{Vapnik1999,
  author={Vapnik, Vladimir Naumovich},
  journal={IEEE Transactions on Neural Networks},
  title={An overview of statistical learning theory},
  year={1999},
  volume={10},
  number={5},
  pages={988-999},
  doi={10.1109/72.788640}}

@book{Zumel2019,
  author={Nina Zumel and John Mount},
  title={Practical Data Science with {R}},
  year={2019},
  publisher={Manning},
  address={Shelter Island, NY, USA},
  edition=2}

@book{Wickham2023,
  author={Hadley Wickham and Mine Çetinkaya-Rundel and Garrett Grolemund},
  title={R for Data Science: Import, Tidy, Transform, Visualize, and Model Data},
  year={2023},
  publisher={O'Reilly Media},
  edition=2}

@book{Kelleher2018,
  author={John D. Kelleher and Brendan Tierney},
  title={Data science},
  year=2018,
  publisher={The MIT Press}}

@article{Paul1993,
  author = {Paul F. Velleman and Leland Wilkinson},
  title = {Nominal, Ordinal, Interval, and Ratio Typologies are Misleading},
  journal = {The American Statistician},
  volume = {47},
  number = {1},
  pages = {65-72},
  year = {1993},
  publisher = {Taylor \& Francis},
  doi = {10.1080/00031305.1993.10475938}}

@article{Beaumont2013,
  author = {Beaumont, Peter B and Bednarik, Robert G},
  year = {2013},
  publisher = {Australian Rock Art Research Association},
  address = {Caulfield South, Victoria, Australia},
  volume = {30},
  number = {1},
  doi = {10.3316/informit.488018706238392},
  abstract = {A comprehensive review of the pre-Holocene palaeoart evidence from sub-Saharan Africa is presented. The scant figurative component appears to be entirely confined to the Later Stone Age. Beads and pendants range back further, to the latter half of the Middle Stone Age. The same applies to the notched items that are invariably based on either bone or red ochre. Incised lines have been reported from both of those periods, and extend into the preceding Early Middle Stone Age. Preliminary data would suggest that a comparable timespan is probably covered by cupules and grooves. Pigment manuports, sometimes with use damage, are traceable to late in the Earlier Stone Age. And lastly are occasional exotic manuports, the collection of which could have spanned the entire Stone Age.},
  journal = {Rock Art Research},
  pages = {33–54},
  numpages = {22}}

@book{Ifrah1998,
  address = {London},
  author = {Ifrah, Georges},
  isbn = {1 86046 324 x},
  keywords = {mathematics},
  note = {First published in French, 1994},
  publisher = {Harvill},
  title = {The Universal History of Numbers, from Prehistory to the Invention of the Computer},
  year = 1998}

@article{Grajalez2013,
  author = {Grajalez, Carlos Gómez and Magnello, Eileen and Woods, Robert and Champkin, Julian},
  title = {Great moments in statistics},
  journal = {Significance},
  volume = {10},
  number = {6},
  pages = {21-28},
  doi = {10.1111/j.1740-9713.2013.00706.x},
  abstract = {How did the ancient Babylonians feed their people? How did Florence Nightingale transform nursing? How did the allies make D-Day a success? How do you know that smoking may kill you? The answers are all “by using statistics”. To accompany the timeline overleaf we present a selection of great statistical landmarks of the past – moments when statistics changed history.},
  year = {2013}}

@article{Codd1970,
  author = {Codd, E. F.},
  title = {A Relational Model of Data for Large Shared Data Banks},
  year = {1970},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  volume = {13},
  number = {6},
  issn = {0001-0782},
  doi = {10.1145/362384.362685},
  abstract = {Future users of large data banks must be protected from having to know how the data is organized in the machine (the internal representation). A prompting service which supplies such information is not a satisfactory solution. Activities of users at terminals and most application programs should remain unaffected when the internal representation of data is changed and even when some aspects of the external representation are changed. Changes in data representation will often be needed as a result of changes in query, update, and report traffic and natural growth in the types of stored information.Existing noninferential, formatted data systems provide users with tree-structured files or slightly more general network models of the data. In Section 1, inadequacies of these models are discussed. A model based on n-ary relations, a normal form for data base relations, and the concept of a universal data sublanguage are introduced. In Section 2, certain operations on relations (other than logical inference) are discussed and applied to the problems of redundancy and consistency in the user's model.},
  journal = {Commun. ACM},
  pages = {377–387}}

@thesis{Hillis1985,
  author = {Hillis, William Daniel},
  title = {The Connection Machine},
  year = {1985},
  school = {Massachusetts Institute of Technology},
  address = {Cambridge, MA, USA},
  note = {Hillis, W.D.: The Connection Machine. PhD thesis, MIT (1985)},
  url = {http://hdl.handle.net/1721.1/14719}}

@book{Vapnik1999b,
  author = {Vapnik, Vladimir Naumovich},
  isbn = {978-1-4419-3160-3},
  publisher = {Springer-Verlag New York, Inc.},
  title = {The nature of statistical learning theory},
  year = 1999,
  edition = 2}

@book{Hunt1966,
  author = {Hunt, Earl B. and Marin, John and Stone, Philip J.},
  title = {Experiments in Induction},
  year = {1966},
  publisher = {Academic Press},
  address = {New York, NY, USA}}

@article{Quinlan1986,
  title={Induction of Decision Trees},
  author={J. Ross Quinlan},
  journal={Machine Learning},
  year={1986},
  volume={1},
  pages={81-106},
  url={https://api.semanticscholar.org/CorpusID:13252401}}

@inproceedings{LeCun1986,
  author={{Le Cun}, Yann},
  title={Learning Process in an Asymmetric Threshold Network},
  booktitle={Disordered Systems and Biological Organization},
  year={1986},
  publisher={Springer Berlin Heidelberg},
  address={Berlin, Heidelberg},
  pages={233--240},
  isbn={978-3-642-82657-3}}

@article{Rumelhart1986,
  author = {Rumelhart, David E. and Hinton, Geoffrey E. and Williams, Ronald J.},
  title = {Learning representations by back-propagating errors},
  journal = {Nature},
  volume = {323},
  number = {6088},
  pages = {533-536},
  year = {1986},
  doi = {10.1038/323533a0}}

@article{Cortes1995,
  author = {Cortes, Corinna and Vapnik, Vladimir Naumovich},
  title = {Support-vector networks},
  journal = {Machine Learning},
  volume = {20},
  number = {3},
  pages = {273-297},
  year = {1995},
  doi = {10.1007/BF00994018}}

@article{Cover1965,
  author={Cover, Thomas M.},
  journal={IEEE Transactions on Electronic Computers},
  title={Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition},
  year={1965},
  volume={EC-14},
  number={3},
  pages={326-334},
  doi={10.1109/PGEC.1965.264137}}

@article{Schapire1990,
  author = {Schapire, Robert E.},
  title = {The strength of weak learnability},
  journal = {Machine Learning},
  volume = {5},
  number = {2},
  pages = {197-227},
  year = {1990},
  doi = {10.1007/BF00116037}}

@article{Breiman1996,
  author = {Breiman, Leo},
  title = {Bagging predictors},
  journal = {Machine Learning},
  volume = {24},
  number = {2},
  pages = {123-140},
  year = {1996},
  doi = {10.1007/BF00058655}}

@inproceedings{Ho1995,
  author={Tin Kam Ho},
  booktitle={Proceedings of 3rd International Conference on Document Analysis and Recognition},
  title={Random decision forests},
  year={1995},
  volume={1},
  number={},
  pages={278-282 vol.1},
  keywords={Classification tree analysis;Decision trees;Training data;Optimization methods;Testing;Tin;Stochastic processes;Handwriting recognition;Hidden Markov models;Multilayer perceptrons},
  doi={10.1109/ICDAR.1995.598994}}

@inproceedings{Fagin1979,
  author = {Fagin, Ronald},
  title = {Normal forms and relational database operators},
  year = {1979},
  isbn = {089791001X},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  doi = {10.1145/582095.582120},
  booktitle = {Proceedings of the 1979 ACM SIGMOD International Conference on Management of Data},
  pages = {153–160},
  location = {Boston, Massachusetts},
  series = {SIGMOD '79}}

@article{Vincent1997,
title = {A corrected 5NF definition for relational database design},
journal = {Theoretical Computer Science},
volume = {185},
number = {2},
pages = {379-391},
year = {1997},
note = {Theoretical Computer Science in Australia and New Zealand},
issn = {0304-3975},
doi = {10.1016/S0304-3975(97)00050-9},
author = {Millist W. Vincent},
keywords = {Relational database, Database design, Normalisation, Join dependencies, Fifth normal form}}

@article{Wickham2014,
 title={Tidy Data},
 volume={59},
 doi={10.18637/jss.v059.i10},
 number={10},
 journal={Journal of Statistical Software},
 author={Wickham, Hadley},
 year={2014},
 pages={1–23}
}

@inproceedings{Takens1980,
  title={Detecting strange attractors in turbulence},
  author={Takens, Floris},
  booktitle={Dynamical Systems and Turbulence, Warwick 1980: proceedings of a symposium held at the University of Warwick 1979/80},
  pages={366--381},
  year={2006},
  organization={Springer}
}

@inproceedings{Song2021,
  author = {Song, Jie and Jagadish, H. V. and Alter, George},
  title = {SDTA: An Algebra for Statistical Data Transformation},
  year = {2021},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  doi = {10.1145/3468791.3468811},
  booktitle = {Proc. of 33rd International Conference on Scientific and Statistical Database Management (SSDBM 2021)},
  pages = {12},
  location = {Tampa, FL, USA}
}

@article{Silva2013,
title = {Detecting and preventing error propagation via competitive learning},
journal = {Neural Networks},
volume = {41},
pages = {70-84},
year = {2013},
note = {Special Issue on Autonomous Learning},
issn = {0893-6080},
doi = {10.1016/j.neunet.2012.11.001},
author = {Thiago Christiano Silva and Liang Zhao},
}

@inproceedings{Martin1997,
  author = {Martin, Alvin F. and Doddington, George R. and Kamm, Terri and Ordowski, Mark and Przybocki, Mark A.},
  booktitle = {EUROSPEECH},
  editor = {Kokkinakis, George and Fakotakis, Nikos and Dermatas, Evangelos},
  pages = {1895-1898},
  publisher = {ISCA},
  title = {The DET curve in assessment of detection task performance.},
  url = {http://dblp.uni-trier.de/db/conf/interspeech/eurospeech1997.html#MartinDKOP97},
  year = 1997
}

@book{Naur1974,
  author = {Naur, Peter},
  title = {Concise Survey of Computer Methods},
  year = {1974},
  publisher = {Studentlitteratur},
  address = {Lund, Sweden},
  isbn = {91-44-07881-1},
  url = {http://www.naur.com/Conc.Surv.html}}

@inproceedings{Cleveland2001,
  author = {Cleveland, William S.},
  title = {Data Science: An Action Plan for Expanding the Technical Areas of the Field of Statistics},
  booktitle = {ISI Review},
  volume = {69},
  pages = {21-26},
  year = {2001}}

@article{Friedman2001,
author = {Jerome H. Friedman},
title = {{Greedy function approximation: A gradient boosting machine.}},
volume = {29},
journal = {The Annals of Statistics},
number = {5},
publisher = {Institute of Mathematical Statistics},
pages = {1189 -- 1232},
keywords = {boosting, decision trees, Function estimation, robust nonparametric regression},
year = {2001},
doi = {10.1214/aos/1013203451},
}

@inproceedings{Vapnik2015,
author="Vapnik, Vladimir Naumovich and Izmailov, Rauf",
editor="Gammerman, Alexander and Vovk, Vladimir and Papadopoulos, Harris",
title="Learning with Intelligent Teacher: Similarity Control and Knowledge Transfer",
booktitle="Statistical Learning and Data Sciences",
year="2015",
publisher="Springer International Publishing",
address="Cham",
pages="3--32",
abstract="This paper introduces an advanced setting of machine learning problem in which an Intelligent Teacher is involved. During training stage, Intelligent Teacher provides Student with information that contains, along with classification of each example, additional privileged information (explanation) of this example. The paper describes two mechanisms that can be used for significantly accelerating the speed of Student's training: (1) correction of Student's concepts of similarity between examples, and (2) direct Teacher-Student knowledge transfer.",
isbn="978-3-319-17091-6"
}

@book{Cormen2022,
  author = {Thomas H. Cormen and Charles E. Leiserson and Ronald L. Rivest and Clifford Stein},
  title = {Introduction to Algorithms},
  edition = {4},
  year = {2022},
  publisher = {The MIT Press},
  isbn = {978-0262046305},
  pages = {1312},
}

@book{Rosen2018,
  author = {Kenneth H. Rosen},
  title = {Discrete Mathematics and Its Applications},
  edition = {8},
  year = {2018},
  publisher = {McGraw Hill},
  isbn = {9781259676512},
  pages = {1120},
}

@book{Ross2014,
  author = {Sheldon M. Ross},
  title = {Introduction to Probability Models},
  edition = {11},
  year = {2014},
  publisher = {Academic Press},
  isbn = {9780124079489},
  pages = {784},
}

@book{Ross2023,
  author = {Sheldon M. Ross},
  title = {Introduction to Probability Models},
  edition = {13},
  year = {2023},
  publisher = {Academic Press},
  isbn = {978-0443187612},
  pages = {870},
}

@book{Ross2019,
  author = {Sheldon M. Ross},
  title = {A First Course in Probability},
  edition = {10},
  year = {2018},
  publisher = {Pearson},
  isbn = {978-1292269207},
  pages = {528},
}

@book{Billingsley1995,
  author = {Patrick Billingsley},
  title = {Probability and Measure},
  edition = {3},
  year = {1995},
  publisher = {John Wiley \& Sons},
  isbn = {0-471-00710-2},
}

@book{Guttag2021,
  author = {John V. Guttag},
  title = {Introduction to Computation and Programming Using Python},
  subtitle = {With Application to Computational Modeling and Understanding Data},
  edition = {3},
  year = {2021},
  publisher = {The MIT Press},
  isbn = {978-0262542364},
  pages = {664},
}

@book{Strang2023,
  author = {Gilbert Strang},
  title = {Introduction to Linear Algebra},
  edition = {6},
  year = {2023},
  publisher = {Wellesley-Cambridge Press},
  isbn = {978-1733146678},
  pages = {440},
}

@inproceedings{Hayashi1998,
  author="Hayashi, Chikio",
  editor="Hayashi, Chikio and Yajima, Keiji and Bock, Hans-Hermann and Ohsumi, Noboru and Tanaka, Yutaka and Baba, Yasumasa",
  title="What is Data Science? Fundamental Concepts and a Heuristic Example",
  booktitle="Data Science, Classification, and Related Methods",
  year="1998",
  publisher="Springer Japan",
  address="Tokyo, Japan",
  pages="40--51",
  isbn="978-4-431-65950-1"
}

@book{CategoriesUnesp,
  author = {Aristotle},
  title = {Categorias. ΚΑΤΗΓΟΡIΑΙ},
  translator = {José Veríssimo Teixeira da Mata},
  language = {greek and portuguese},
  publisher = {Editora Unesp},
  location = {São Paulo, Brasil},
  date = {2019},
  isbn = {978-85-393-0785-2},
}

@INPROCEEDINGS{Saltz2019,
  author={Saltz, Jeffrey and Suthrland, Alex},
  booktitle={2019 IEEE International Conference on Big Data (Big Data)},
  title={SKI: An Agile Framework for Data Science},
  year={2019},
  volume={},
  number={},
  pages={3468-3476},
  keywords={Data science;Big Data;Task analysis;Project management;Data mining;Data models;Data Science;Big Data;Agile;Process Methodology},
  doi={10.1109/BigData47090.2019.9005591}}


@INPROCEEDINGS{Baijens2020,
  author={Baijens, Jeroen and Helms, Remko and Iren, Deniz},
  booktitle={2020 IEEE 22nd Conference on Business Informatics (CBI)},
  title={Applying Scrum in Data Science Projects},
  year={2020},
  volume={1},
  number={},
  pages={30-38},
  keywords={Data science;Biological system modeling;Data models;Organizations;Task analysis;Software;Data Science;Agile;Scrum},
  doi={10.1109/CBI49978.2020.00011}}

@INPROCEEDINGS{Kraut2022,
  author={Kraut, Nils and Transchel, Fabian},
  booktitle={2022 7th International Conference on Big Data Analytics (ICBDA)},
  title={On the Application of SCRUM in Data Science Projects},
  year={2022},
  volume={},
  number={},
  pages={1-9},
  keywords={Data science;Big Data;Task analysis;Scrum (Software development);Software engineering;SCRUM;data science;project management},
  doi={10.1109/ICBDA55095.2022.9760341}}

@book{schwaber2020scrum,
  title={Scrum Guide: The Definitive Guide to Scrum: The Rules of the Game},
  author={Schwaber, Ken and Sutherland, Jeff},
  year={2020},
  publisher={Scrum.org},
  url={https://scrumguides.org/docs/scrumguide/v2020/2020-Scrum-Guide-US.pdf}
}

@article{openagile2019roles,
  title={Understanding Scrum Roles: Product Owner, Scrum Master, and Development Team},
  author={Smith, John},
  journal={Open Agile Journal},
  volume={12},
  pages={22-28},
  year={2019},
  publisher={Agile Publications}
}

@book{cobb2015scrum,
  title={The Project Manager's Guide to Mastering Agile: Principles and Practices for an Adaptive Approach},
  author={Cobb, Charles G.},
  year={2015},
  publisher={John Wiley \& Sons}
}

@article{rubin2012sprints,
  title={Scrum for Teams: Maximizing Efficiency in Short Iterations},
  author={Rubin, Steven},
  journal={Agile Processes Journal},
  volume={8},
  pages={45-52},
  year={2012},
  publisher={Agile Alliance}
}

@article{denning2016scrum,
  title={Why Agile Works: Understanding the Importance of Scrum in Modern Software Development},
  author={Denning, Steve},
  journal={Forbes},
  year={2016},
  url={https://www.forbes.com/sites/stevedenning/2016/08/10/why-agile-works/}
}

@article{chawla2002smote,
  title={SMOTE: synthetic minority over-sampling technique},
  author={Chawla, Nitesh V and Bowyer, Kevin W and Hall, Lawrence O and Kegelmeyer, W Philip},
  journal={Journal of artificial intelligence research},
  volume={16},
  pages={321--357},
  year={2002}
}

@article{Dean2008,
author = {Dean, Jeffrey and Ghemawat, Sanjay},
title = {MapReduce: simplified data processing on large clusters},
year = {2008},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {51},
number = {1},
issn = {0001-0782},
doi = {10.1145/1327452.1327492},
journal = {Commun. ACM},
month = jan,
pages = {107–113},
}

@article{Vapnik1991,
  title={The necessary and sufficient conditions for consistency of the method of empirical risk minimization},
  author={Vapnik, Vladimir N and Chervonenkis, A},
  journal={Pattern Recognition and Image Analysis},
  volume={1},
  number={3},
  pages={284--305},
  year={1991}
}

@inproceedings{Vapnik1968,
  title={On the uniform convergence of relative frequencies of events to their probabilities},
  author={Vapnik, Vladimir and Chervonenkis, A},
  booktitle={Doklady Akademii Nauk USSR},
  volume={181},
  number={4},
  pages={781--787},
  year={1968}
}

@book{Goodfellow2016,
    title={Deep Learning},
    author={Ian Goodfellow and Yoshua Bengio and Aaron Courville},
    publisher={MIT Press},
    note={\url{http://www.deeplearningbook.org}},
    year={2016}
}

@article{Troyanskaya2001,
    author = {Troyanskaya, Olga and Cantor, Michael and Sherlock, Gavin and Brown, Pat and Hastie, Trevor and Tibshirani, Robert and Botstein, David and Altman, Russ B.},
    title = {Missing value estimation methods for DNA microarrays },
    journal = {Bioinformatics},
    volume = {17},
    number = {6},
    pages = {520-525},
    year = {2001},
    month = {06},
    issn = {1367-4803},
    doi = {10.1093/bioinformatics/17.6.520},
}

@inproceedings{Ester1996,
  title={A density-based algorithm for discovering clusters in large spatial databases with noise},
  author={Ester, Martin and Kriegel, Hans-Peter and Sander, J{\"o}rg and Xu, Xiaowei and others},
  booktitle={kdd},
  volume={96},
  number={34},
  pages={226--231},
  year={1996}
}

@article{Scholkopf2001,
  title={Estimating the support of a high-dimensional distribution},
  author={Sch{\"o}lkopf, Bernhard and Platt, John C and Shawe-Taylor, John and Smola, Alex J and Williamson, Robert C},
  journal={Neural computation},
  volume={13},
  number={7},
  pages={1443--1471},
  year={2001},
  publisher={MIT Press One Rogers Street, Cambridge, MA 02142-1209, USA journals-info~…}
}


@article{Freek2015,
title = {Many regression algorithms, one unified model: A review},
journal = {Neural Networks},
volume = {69},
pages = {60-79},
year = {2015},
issn = {0893-6080},
doi = {https://doi.org/10.1016/j.neunet.2015.05.005},
author = {Freek Stulp and Olivier Sigaud},
}

@Book{Jurafsky2024,
  author = "Daniel Jurafsky and James H. Martin",
  title = "Speech and Language Processing: An Introduction to
           Natural Language Processing, Computational Linguistics,
           and Speech Recognition with Language Models",
  year = "2024",
  url = {https://web.stanford.edu/~jurafsky/slp3/},
  note = "Online manuscript released August 20, 2024",
  edition = 3,
}

@book{Jurafsky2008,
  author = {Daniel Jurafsky and James H. Martin},
  title = {Speech and Language Processing},
  subtitle = {An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition},
  year = {2008},
  publisher = {Prentice Hall},
  address = {Hoboken, NJ, USA},
  edition = 2,
}

@book{Szeliski2022,
  title={Computer vision},
  subtitle={Algorithms and applications},
  author={Szeliski, Richard},
  year={2022},
  edition={2},
  publisher={Springer Nature},
  url={https://szeliski.org/Book/}
}

@article{Williams2021,
    author = {Williams, Christopher K. I.},
    title = {The Effect of Class Imbalance on Precision-Recall Curves},
    journal = {Neural Computation},
    volume = {33},
    number = {4},
    pages = {853-857},
    year = {2021},
    month = {04},
    issn = {0899-7667},
    doi = {10.1162/neco_a_01362},
}