EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

2243. Optimizing post-pandemic recovery: a comparative analysis of machine learning techniques for tourism SMMEs revenue predictive modelling

Invited abstract in session TD-18: AI and ESG for the small economy SDG agenda (EWG-ORD Workshop 2), stream OR for Development and Developing Countries.

Tuesday, 14:30-16:00
Room: 42 (building: 116)

Authors (first author is the speaker)

1. Helper Zhou
School of Accounting, Economics and Finance, University of KwaZulu Natal
2. Gordon Dash
Finance and Decision Sciences, University of Rhode Island
3. Nina Kajiji
Computer Science and Statistics, University of Rhode Island, and The NKD Group, Inc.
4. Mabutho Sibanda
Accounting, Economics & Finance, University of KwaZulu-Natal

Abstract

The COVID-19 pandemic dramatically affected global tourism, especially South African tour operating Small, Medium, and Micro Enterprises (SMMEs). These enterprises are now leveraging machine learning (ML) to make informed decisions using predictive models. However, choosing the right ML technique is challenging for these operators due to their limited technical expertise. This study compares shallow and deep learning methods for predicting tour operator performance, using a dataset from 650 South African SMMEs, spanning 2019-2021. The enhanced radial basis function (K4-RANN), a shallow learning model, outperformed deep learning models, showing better prediction accuracy with lower error rates and higher R² values. Therefore, the study recommend that tourism SMMEs adopt the K4-RANN model for more accurate booking and revenue projections, thereby improving decision-making and efficiency post the Covid-19 pandemic era.

Keywords

Status: accepted

Back to the list of papers