Abstract
Nowadays we rely heavily on technology to understand the world around us. Databases and machine learning are key components in this endeavour. In the data exploration realm, users can have difficulties formulating the right queries for various reasons, e.g., the dataset has a large number of attributes, the user doesn’t have a clear idea of what they’re looking for in their data. In our previous work, we aimed to bridge the gap between SQL and machine learning by providing the user who poses an SQL query with an answer set and a reformulation of their query, generated using the C4.5 decision tree algorithm. We now investigate the use of three different machine learning models in a new experimental study and interaction paradigm: LightGbm, FastTree, and GAM. Upon posing an SQL query, the user is presented with: the answer set, three trained models along with a rich set of new metrics that assess the models’ quality, and the most important features for each model, computed with Permutation Feature Importance. By analyzing the metrics’ results, the user can decide for themselves which model(s) they’ll use further in their exploratory quest. Once a model is chosen, the user can formulate new SQL queries using some of the most important features for the model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cumin, J., Petit, J.-M., Rouge, F., Scuturici, V.-M., Surace, C., Surdu, S.: Requêtes discriminantes pour l’exploration des données. In: de Runz, C., Crémilleux, B. (eds.) 16ème Journées Francophones Extraction et Gestion des Connaissances, EGC 2016, 18–22 Janvier 2016, Reims, France, Revue des Nouvelles Technologies de l’Information, vol. E-30, pp. 195–206. Éditions RNTI (2016)
Cumin, J., Petit, J.-M., Scuturici, V.-M., Surdu, S.: Data exploration with SQL using machine learning techniques. In: Markl, V., Orlando, S., Mitschang, B., Andritsos, P., Sattler, K.-U., Breß, S. (eds.) Proceedings of the 20th International Conference on Extending Database Technology, EDBT 2017, Venice, Italy, 21–24 March 2017, pp. 96–107. OpenProceedings.org (2017). https://doi.org/10.5441/002/edbt.2017.10
DB-Engines Ranking. https://db-engines.com/en/ranking_categories. Accessed 29 Aug 2022
Dimitriadou, K., Papaemmanouil, O., Diao, Y.: Explore-by-example: an automatic query steering framework for interactive data exploration. In: Dyreson, C.E., Li, F., Özsu, M. T. (eds.) International Conference on Management of Data, SIGMOD 2014, Snowbird, UT, USA, 22–27 June 2014, pp. 517–528. ACM (2014). https://doi.org/10.1145/2588555.2610523
Han, J., Kamber, M., Pei, J.: Data Mining: Concepts and Techniques, 3rd edn. Morgan Kaufmann, Burlington (2011)
Idreos, S., Papaemmanouil, O., Chaudhuri, S.: Overview of data exploration techniques. In: Sellis, T.K., Davidson, S.B., Ives, Z.G. (eds.) Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, Victoria, Australia, 31 May–4 June 2015, pp. 277–281. ACM (2015). https://doi.org/10.1145/2723372.2731084
Li, H., Chan, C.-Y., Maier, D.: Query from examples: an iterative, data-driven approach to query construction. Proc. VLDB Endow. 8(13), 2158–2169 (2015)
ML.NET. https://dotnet.microsoft.com/en-us/apps/machinelearning-ai/ml-dotnet. Accessed 15 Aug 2022
ML.NET Documentation. https://docs.microsoft.com/en-us/dotnet/machine-learning/. Accessed 15 Aug 2022
Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, Burlington (1993)
Rahman, P., Jiang, L., Nandi, A.: Evaluating interactive data systems. VLDB J. 29(1), 119–146 (2020)
Stack Overflow 2022 Developer Survey. https://survey.stackoverflow.co/2022/#section-most-loved-dreaded-and-wanted-programming-scripting-and-markup-languages. Accessed 29 Aug 2022
Ste, A.: How to Become More Marketable as a Data Scientist. https://www.kdnuggets.com/2019/08/marketable-data-scientist.html. Accessed 29 Aug 2022
Tun, L.L.: Why Non-Programmers Should Learn SQL. https://www.udacity.com/blog/2020/06/why-non-programmers-should-learn-sql.html. Accessed 29 Aug 2022
UCI Machine Learning Repository, Wine Data Set. https://archive.ics.uci.edu/ml/datasets/wine. Accessed 15 Aug 2022
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Surdu, S. (2023). Enriching SQL-Driven Data Exploration with Different Machine Learning Models. In: Simian, D., Stoica, L.F. (eds) Modelling and Development of Intelligent Systems. MDIS 2022. Communications in Computer and Information Science, vol 1761. Springer, Cham. https://doi.org/10.1007/978-3-031-27034-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-27034-5_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-27033-8
Online ISBN: 978-3-031-27034-5
eBook Packages: Computer ScienceComputer Science (R0)