Title: When and where? Proactively predicting traffic accident in South Africa: our machine learning competition winning approach

Authors: Sulaimon Afolabi; Warrie Warrie; Oluwatobi Banjo; Opeoluwa Iwashokun; Abimbola Olawale; Naledi Ngqambela; Fata Soliu; Olawumi Olasunkanmi; Folorunso Sakinat; Sibusiso Matshika

Addresses: Africa4AI, Johannesburg, South Africa ' Department of Computer Engineering, University of Uyo, Uyo AkwaIbom, Nigeria ' Department of Mathematical Sciences, Olabisi Onabanjo University, Ago-Iwoye, Nigeria ' Department of Applied Information Systems, School of Consumer Intelligence and Information Systems, College of Business and Economics, University of Johannesburg, South Africa ' Department of Mathematics and Statistics, Federal Polytechnic Ilaro, Ilaro, Nigeria ' Department of Public Administration, University of the Western Cape, South Africa ' Department of Biochemistry, University of Ilorin, Ilorin, Kwara State, Nigeria ' Department of Computer Science, Ladoke Akintola University of Technology, Ogbomoso, Nigeria ' Department of Mathematical Sciences, Olabisi Onabanjo University, Ago-Iwoye, Nigeria ' Platinum Mines-Plant Engineer, Pretoria, South Africa

Abstract: South Africa (SA) records high mortality originating from traffic accident annually making the country to be ranked highly among nations with the highest traffic mortality globally. There is seemingly no study that has attempted to forecast when and where next accident will occur in SA. This study aims to use machine learning method to predict traffic accident in SA for every hour ranging between 1 January and 31 March 2019 at a segment ID. We obtained details of accidents that occurred in Cape Town, SA between 2016 and 2019 SANRAL, Uber Movement and Cape Town FMS via Zindi competition platform. This research adopted Catboost and LightGBM models to predict the traffic incident occurrence. Our model shows a F1 score of 0.11. The results of this research will aid prediction of accident occurrence at a particular road segment hourly.

Keywords: road accident; machine learning; Cape Town; forecast; data science; South Africa.

DOI: 10.1504/IJSSS.2021.116374

International Journal of Society Systems Science, 2021 Vol.13 No.2, pp.151 - 170

Received: 05 Sep 2020
Accepted: 21 Dec 2020
Published online: 21 Jul 2021 *

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