{"title":"Sales forecasting of selected fresh vegetables in multiple channels for marginal and small-scale farmers in Kerala, India","authors":"R.S. Sreerag, Prasanna Venkatesan Shanmugam","doi":"10.1108/jadee-03-2023-0075","DOIUrl":null,"url":null,"abstract":"Purpose The choice of a sales channel for fresh vegetables is an important decision a farmer can make. Typically, the farmers rely on their personal experience in directing the produce to a sales channel. This study examines how sales forecasting of fresh vegetables along multiple channels enables marginal and small-scale farmers to maximize their revenue by proportionately allocating the produce considering their short shelf life. Design/methodology/approach Machine learning models, namely long short-term memory (LSTM), convolution neural network (CNN) and traditional methods such as autoregressive integrated moving average (ARIMA) and weighted moving average (WMA) are developed and tested for demand forecasting of vegetables through three different channels, namely direct (Jaivasree), regulated (World market) and cooperative (Horticorp). Findings The results show that machine learning methods (LSTM/CNN) provide better forecasts for regulated (World market) and cooperative (Horticorp) channels, while traditional moving average yields a better result for direct (Jaivasree) channel where the sales volume is less as compared to the remaining two channels. Research limitations/implications The price of vegetables is not considered as the government sets the base price for the vegetables. Originality/value The existing literature lacks models and approaches to predict the sales of fresh vegetables for marginal and small-scale farmers of developing economies like India. In this research, the authors forecast the sales of commonly used fresh vegetables for small-scale farmers of Kerala in India based on a set of 130 weekly time series data obtained from the Kerala Horticorp.","PeriodicalId":45976,"journal":{"name":"Journal of Agribusiness in Developing and Emerging Economies","volume":"92 1","pages":"0"},"PeriodicalIF":2.4000,"publicationDate":"2023-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Agribusiness in Developing and Emerging Economies","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1108/jadee-03-2023-0075","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AGRICULTURAL ECONOMICS & POLICY","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose The choice of a sales channel for fresh vegetables is an important decision a farmer can make. Typically, the farmers rely on their personal experience in directing the produce to a sales channel. This study examines how sales forecasting of fresh vegetables along multiple channels enables marginal and small-scale farmers to maximize their revenue by proportionately allocating the produce considering their short shelf life. Design/methodology/approach Machine learning models, namely long short-term memory (LSTM), convolution neural network (CNN) and traditional methods such as autoregressive integrated moving average (ARIMA) and weighted moving average (WMA) are developed and tested for demand forecasting of vegetables through three different channels, namely direct (Jaivasree), regulated (World market) and cooperative (Horticorp). Findings The results show that machine learning methods (LSTM/CNN) provide better forecasts for regulated (World market) and cooperative (Horticorp) channels, while traditional moving average yields a better result for direct (Jaivasree) channel where the sales volume is less as compared to the remaining two channels. Research limitations/implications The price of vegetables is not considered as the government sets the base price for the vegetables. Originality/value The existing literature lacks models and approaches to predict the sales of fresh vegetables for marginal and small-scale farmers of developing economies like India. In this research, the authors forecast the sales of commonly used fresh vegetables for small-scale farmers of Kerala in India based on a set of 130 weekly time series data obtained from the Kerala Horticorp.
期刊介绍:
The Journal of Agribusiness in Developing and Emerging Economies publishes double-blind peer-reviewed research on issues relevant to agriculture and food value chain in emerging economies in Asia, Africa, Latin America and Eastern Europe. The journal welcomes original research, particularly empirical/applied, quantitative and qualitative work on topics pertaining to policies, processes, and practices in the agribusiness arena in emerging economies to inform researchers, practitioners and policy makers