Title: Wrapping practical problems into a machine learning framework: using water pipe failure prediction as a case study

Authors: Jianlong Zhou; Jinjun Sun; Yang Wang; Fang Chen

Addresses: DATA61, CSIRO, Level 5, 13 Garden Street, Eveleigh, NSW 2015, Australia ' Red Planet of Qantas Loyalty, 10 Bourke Road, Mascot, NSW 2020, Australia ' DATA61, CSIRO, Level 5, 13 Garden Street, Eveleigh, NSW 2015, Australia ' DATA61, CSIRO, Level 5, 13 Garden Street, Eveleigh, NSW 2015, Australia

Abstract: Despite the recognised value of machine learning (ML) techniques and high expectation of applying ML techniques within various applications, users often find it difficult to effectively apply ML techniques in practice because of complicated interfaces between ML algorithms and users. This paper presents a work flow of wrapping practical problems into an ML framework. The water pipe failure prediction is used as a case study to show that the applying process can be divided into various steps: obtain domain data, interview with domain experts, clean/pre-process and preview original domain data, extract ML features, set up ML models, explain ML results and make decisions, as well as make feedback to the system based on decision making. In this process, domain experts and ML developers need to collaborate closely in order to make this workflow more effective.

Keywords: machine learning; practical problems; human-computer interaction; water pipe failure prediction.

DOI: 10.1504/IJISTA.2017.085355

International Journal of Intelligent Systems Technologies and Applications, 2017 Vol.16 No.3, pp.191 - 207

Received: 27 Aug 2016
Accepted: 05 Dec 2016
Published online: 24 Jul 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article