Title: Modelling the profitability of soya bean farming in Zambia using machine learning

Authors: Naomi Mutampuka Mwaba; Derrick Ntalasha

Addresses: School of Information and Communication Technology, Copperbelt University, Kitwe, Zambia ' School of Information and Communication Technology, Copperbelt University, Kitwe, Zambia

Abstract: Planning crops for any upcoming season has proven to be a tough chore for farmers since it is challenging to forecast the profits that their crops will fetch after harvest as most farmers base their choice of crop to grow on high-yield crops and previous farming season profit margins. This introduces a problem of profit determination over time. This study uses soya bean data for the past ten farming seasons to develop and compare two machine learning (ML) models using support vector machine regression (SVMR) and autoregressive integrated moving average (ARIMA) to forecast the profitability of soya beans in Zambia. The experimental results demonstrate that the SVMR is best suited as it predicted profits with an accuracy of 79.25% compared to ARIMA with an accuracy of only 34.2%. This suggests that the SVMR model is efficient to use as a financial analysis tool to allow farmers to make informed decisions.

Keywords: profit prediction; machine learning; support vector machine regression; SVMR; autoregressive integrated moving average; ARIMA; Zambia.

DOI: 10.1504/IJAISC.2024.145611

International Journal of Artificial Intelligence and Soft Computing, 2024 Vol.8 No.3, pp.195 - 214

Received: 15 Nov 2023
Accepted: 15 May 2024
Published online: 09 Apr 2025 *

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