Redeeming Data Science by Decision Modelling (2307.00088v1)
Abstract: With the explosion of applications of Data Science, the field is has come loose from its foundations. This article argues for a new program of applied research in areas familiar to researchers in Bayesian methods in AI that are needed to ground the practice of Data Science by borrowing from AI techniques for model formulation that we term ``Decision Modelling.'' This article briefly reviews the formulation process as building a causal graphical model, then discusses the process in terms of six principles that comprise \emph{Decision Quality}, a framework from the popular business literature. We claim that any successful applied ML modelling effort must include these six principles. We explain how Decision Modelling combines a conventional machine learning model with an explicit value model. To give a specific example we show how this is done by integrating a model's ROC curve with a utility model.
- Daron Acemoglu. Technical change, inequality, and the labor market. Journal of economic literature, 40(1):7–72, 2002.
- Deep end-to-end causal inference, 2022. URL https://arxiv.org/abs/2202.02195.
- A bayesian approach to causal discovery. Computation, causation, and discovery, 19:141–166, 1999.
- Finn V. Jensen. Bayesian Networks and Decision Graphs. Springer, 2001.
- Daniel Kahneman. Thinking, Fast and Slow. Farrar, Straus and Giroux, 2011.
- Probabilistic Graphical Models. MIT Press, 2009.
- Nicolas Kruchten. Machine learning meets economics, 2016. URL http://blog.mldb.ai/blog/posts/2016/01/ml-meets-economics/.
- Efficient multiclass roc approximation by decomposition via confusion matrix perturbation analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(5):810–823, 2008.
- Stuart Russell. Human Compatible. Viking, 2019.
- Decision Quality. Wiley, 2016.
- An algorithm for fast recovery of sparse causal graphs. Social Science Computer Review, 9:62–72, 1991.