Prediction of Agro Products Sales Using Regression Algorithm

Terungwa Simon Yange,Charity Ojochogwu Egbunu,Oluoha Onyekwere,Kater Amos Foga

doi:10.11648/j.ajdmkd.20200501.12

Terungwa Simon Yange, Charity Ojochogwu Egbunu + Show 2 more

Open Access

https://doi.org/10.11648/j.ajdmkd.20200501.12

Copy DOI

Abstract

This study aimed at developing a system using support vector machine (SVM) that will forecast sales of farm products for an agricultural farm so that managers can take strategic decisions timely to better market the excess farm products which some by nature are perishable. The sales prediction model used SVMs and Fuzzy Theory. The implementation was done using Python Programming Language. The system comprised of three (3) modules: web interface, flask and the SVM Framework. To evaluate the result of the SVM model, the RBF neural network was used as a benchmark. Data of previous sales records from University of Agriculture Makurdi (UAM) farm was used to train and test the system. After training the network with data which covered the time period from 21st January, 2017 to 30th June, 2019, the remaining data which covered from 1st July 2019 up to the 31st December, 2019 was used to test and validate the forecasting performance of the system. The Forecasting Precision (FP) value for the SVM was 96.75% and that of the RBF neural network forecasting value was 90.55%. Analysis from the results shows that the forecasting system with SVM had a greater precision in the sales of agricultural products.

Highlights

Nigeria is one of the leading countries that deals with agriculture [1]
This study aims at developing an algorithm based on support vector machine (SVM) that will forecast sales of agricultural farm produce for a farm that deals with perishable agricultural products
Our study aims to develop an SVM model combined with Linear Regression to predict sales for the University of Agriculture farm

Summary

Introduction

Nigeria is one of the leading countries that deals with agriculture [1]. Nigeria is known as the world’s largest producer of yam (23million tonnes), cassava (54 million tonnes), plantain and several other agricultural products ranging from plants, vegetables, fruits and poultry management involving rearing of goats, chickens, pigs, fish farming, eggs production and lots of others [2]. Agricultural products require lots of strategy in its management due to its quick nature of spoilage and difficulty in storage. When there is excess of the produce and the production is not commensurable with sales i.e. low sales turn over and high supply, the tendency to suffer loss becomes inexpiable as the perishable nature of farm produce remains a problem that requires considerate tactics to deal with. Losses from Postharvest apparently results in wastage of resources like fertilizer, water, land, seeds etc. Ability to predict future market demands of agricultural products is very important in determining the decisions to be taken before farm production and in the development of marketing strategies. Business operations with perishable agricultural products will profit immensely from accurate forecasting of sales. Business operations with perishable agricultural products will profit immensely from accurate forecasting of sales. losses [4]

Objectives

Methods

Results

Discussion

Conclusion