Search

Synthetic data has gained significant momentum thanks to sophisticated machine learning tools that enable the synthesis of high-dimensional datasets. However, many generation techniques do not give the data controller control over what statistical patterns are captured, leading to concerns over privacy protection. While synthetic records are not linked to a particular real-world individual, they can reveal information about users indirectly which may be unacceptable for data owners. There is thus a need to empirically verify the privacy of synthetic data -- a particularly challenging task in high-dimensional data. In this paper we present a general framework for synthetic data generation that gives data controllers full control over which statistical properties the synthetic data ought to preserve, what exact information loss is acceptable, and how to quantify it. The benefits of the approach are that (1) one can generate synthetic data that results in high utility for a given task, while (2) empirically validating that only statistics considered safe by the data curator are used to generate the data. We thus show the potential for synthetic data to be an effective means of releasing confidential data safely, while retaining useful information for analysts.

This work uses a data-driven approach to analyse how the resource requirements of patients with chronic obstructive pulmonary disease (COPD) may change, quantifying how those changes impact the hospital system with which the patients interact. This approach is composed of a novel combination of often distinct modes of analysis: segmentation, operational queuing theory, and the recovery of parameters from incomplete data. By combining these methods as presented here, this work demonstrates that potential limitations around the availability of fine-grained data can be overcome. Thus, finding useful operational results despite using only administrative data. The paper begins by finding a useful clustering of the population from this granular data that feeds into a multi-class M/M/c model, whose parameters are recovered from the data via parameterisation and the Wasserstein distance. This model is then used to conduct an informative analysis of the underlying queuing system and the needs of the population under study through several what-if scenarios. The analyses used to form and study this model consider, in effect, all types of patient arrivals and how those types impact the system. With that, this study finds that there are no quick solutions to reduce the impact of COPD patients on the system, including adding capacity to the system. In this analysis, the only effective intervention to reduce the strain caused by those presenting with COPD is to enact external policies which directly improve the overall health of the COPD population before they arrive at the hospital., Comment: 24 pages, 11 figures (19 including subfigures)

This paper presents a new way of selecting an initial solution for the k-modes algorithm that allows for a notion of mathematical fairness and a leverage of the data that the common initialisations from literature do not. The method, which utilises the Hospital-Resident Assignment Problem to find the set of initial cluster centroids, is compared with the current initialisations on both benchmark datasets and a body of newly generated artificial datasets. Based on this analysis, the proposed method is shown to outperform the other initialisations in the majority of cases, especially when the number of clusters is optimised. In addition, we find that our method outperforms the leading established method specifically for low-density data., Comment: 23 pages, 11 figures (31 panels)

In this paper we propose a novel method for learning how algorithms perform. Classically, algorithms are compared on a finite number of existing (or newly simulated) benchmark datasets based on some fixed metrics. The algorithm(s) with the smallest value of this metric are chosen to be the `best performing'. We offer a new approach to flip this paradigm. We instead aim to gain a richer picture of the performance of an algorithm by generating artificial data through genetic evolution, the purpose of which is to create populations of datasets for which a particular algorithm performs well on a given metric. These datasets can be studied so as to learn what attributes lead to a particular progression of a given algorithm. Following a detailed description of the algorithm as well as a brief description of an open source implementation, a case study in clustering is presented. This case study demonstrates the performance and nuances of the method which we call Evolutionary Dataset Optimisation. In this study, a number of known properties about preferable datasets for the clustering algorithms known as (k)-means and DBSCAN are realised in the generated datasets., Comment: 33 pages, 15 figures